@article {pmid40048663,
year = {2025},
author = {Versoza, CJ and Ehmke, EE and Jensen, JD and Pfeifer, SP},
title = {Characterizing the Rates and Patterns of De Novo Germline Mutations in the Aye-Aye (Daubentonia madagascariensis).},
journal = {Molecular biology and evolution},
volume = {42},
number = {3},
pages = {},
pmid = {40048663},
issn = {1537-1719},
support = {/GM/NIGMS NIH HHS/United States ; R35GM151008/NH/NIH HHS/United States ; DBI-2012668//National Science Foundation/ ; DEB-2045343//National Science Foundation/ ; },
mesh = {Animals ; *Germ-Line Mutation ; *Mutation Rate ; Male ; Female ; Strepsirhini/genetics ; Pedigree ; Whole Genome Sequencing/methods ; },
abstract = {Given the many levels of biological variation in mutation rates observed to date in primates-spanning from species to individuals to genomic regions-future steps in our understanding of mutation rate evolution will not only be aided by a greater breadth of species coverage across the primate clade but also by a greater depth as afforded by an evaluation of multiple trios within individual species. In order to help bridge these gaps, we here present an analysis of a species representing one of the most basal splits on the primate tree (aye-ayes), combining whole-genome sequencing of seven parent-offspring trios from a three-generation pedigree with a novel computational pipeline that takes advantage of recently developed pan-genome graphs, thereby circumventing the application of (highly subjective) quality metrics that has previously been shown to result in notable differences in the detection of de novo mutations and ultimately estimates of mutation rates. This deep sampling has enabled both a detailed picture of parental age effects and sex dependency in mutation rates, which we here compare with previously studied primates, but has also provided unique insights into the nature of genetic variation in one of the most endangered primates on the planet.},
}

Animals
*Germ-Line Mutation
*Mutation Rate
Male
Female
Strepsirhini/genetics
Pedigree
Whole Genome Sequencing/methods

@article {pmid40045122,
year = {2025},
author = {Kamal, N and Spannagl, M},
title = {Genus-wide plant pangenome could inform next-generation crop design.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {40045122},
issn = {1476-4687},
}

@article {pmid40044854,
year = {2025},
author = {Benoit, M and Jenike, KM and Satterlee, JW and Ramakrishnan, S and Gentile, I and Hendelman, A and Passalacqua, MJ and Suresh, H and Shohat, H and Robitaille, GM and Fitzgerald, B and Alonge, M and Wang, X and Santos, R and He, J and Ou, S and Golan, H and Green, Y and Swartwood, K and Karavolias, NG and Sierra, GP and Orejuela, A and Roda, F and Goodwin, S and McCombie, WR and Kizito, EB and Gagnon, E and Knapp, S and Särkinen, TE and Frary, A and Gillis, J and Van Eck, J and Schatz, MC and Lippman, ZB},
title = {Solanum pan-genetics reveals paralogues as contingencies in crop engineering.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {40044854},
issn = {1476-4687},
abstract = {Pan-genomics and genome-editing technologies are revolutionizing breeding of global crops[1,2]. A transformative opportunity lies in exchanging genotype-to-phenotype knowledge between major crops (that is, those cultivated globally) and indigenous crops (that is, those locally cultivated within a circumscribed area)[3-5] to enhance our food system. However, species-specific genetic variants and their interactions with desirable natural or engineered mutations pose barriers to achieving predictable phenotypic effects, even between related crops[6,7]. Here, by establishing a pan-genome of the crop-rich genus Solanum[8] and integrating functional genomics and pan-genetics, we show that gene duplication and subsequent paralogue diversification are major obstacles to genotype-to-phenotype predictability. Despite broad conservation of gene macrosynteny among chromosome-scale references for 22 species, including 13 indigenous crops, thousands of gene duplications, particularly within key domestication gene families, exhibited dynamic trajectories in sequence, expression and function. By augmenting our pan-genome with African eggplant cultivars[9] and applying quantitative genetics and genome editing, we dissected an intricate history of paralogue evolution affecting fruit size. The loss of a redundant paralogue of the classical fruit size regulator CLAVATA3 (CLV3)[10,11] was compensated by a lineage-specific tandem duplication. Subsequent pseudogenization of the derived copy, followed by a large cultivar-specific deletion, created a single fused CLV3 allele that modulates fruit organ number alongside an enzymatic gene controlling the same trait. Our findings demonstrate that paralogue diversifications over short timescales are underexplored contingencies in trait evolvability. Exposing and navigating these contingencies is crucial for translating genotype-to-phenotype relationships across species.},
}

@article {pmid40042872,
year = {2025},
author = {Roberts, MD and Davis, O and Josephs, EB and Williamson, RJ},
title = {k-mer-based approaches to bridging pangenomics and population genetics.},
journal = {Molecular biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/molbev/msaf047},
pmid = {40042872},
issn = {1537-1719},
abstract = {Many commonly studied species now have more than one chromosome-scale genome assembly, revealing a large amount of genetic diversity previously missed by approaches that map short reads to a single reference. However, many species still lack multiple reference genomes and correctly aligning references to build pangenomes can be challenging for many species, limiting our ability to study this missing genomic variation in population genetics. Here, we argue that k-mers are a very useful but underutilized tool for bridging the reference-focused paradigms of population genetics with the reference-free paradigms of pangenomics. We review current literature on the uses of k-mers for performing three core components of most population genetics analyses: identifying, measuring, and explaining patterns of genetic variation. We also demonstrate how different k-mer-based measures of genetic variation behave in population genetic simulations according to the choice of k, depth of sequencing coverage, and degree of data compression. Overall, we find that k-mer-based measures of genetic diversity scale consistently with pairwise nucleotide diversity (π) up to values of about π = 0.025 (R2 = 0.97) for neutrally evolving populations. For populations with even more variation, using shorter k-mers will maintain the scalability up to at least π = 0.1. Furthermore, in our simulated populations, k-mer dissimilarity values can be reliably approximated from counting bloom filters, highlighting a potential avenue to decreasing the memory burden of k-mer based genomic dissimilarity analyses. For future studies, there is a great opportunity to further develop methods to identifying selected loci using k-mers.},
}

@article {pmid40039311,
year = {2024},
author = {Coggi, M and Sgarlata, A and Di Donato, GW and Santambrogio, MD},
title = {On the optimization of GWFA algorithm: enabling real-case applications supporting alignment backtracking.},
journal = {Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference},
volume = {2024},
number = {},
pages = {1-4},
doi = {10.1109/EMBC53108.2024.10781891},
pmid = {40039311},
issn = {2694-0604},
mesh = {*Algorithms ; Humans ; Sequence Alignment/methods ; Genome, Human ; Genomics/methods ; Sequence Analysis, DNA/methods ; Software ; },
abstract = {The Human Pangenome Reference Consortium (HPRC) proved that pangenome graphs represent a population's genetic variability more efficiently and accurately than linear references. Graphs can intrinsically encode variations as alternative paths inside a directed set of sequence nodes connected by edges. Despite their higher complexity, graph-based genome analysis pipelines are gaining significant interest, and the first sequence-to-graph aligners have already shown improvements in semi-global alignment. However, in pangenomics studies, the global alignment of long reads is fundamental for identifying structural variations and haplotype phasing. In this context, the Graph Wavefront Alignment (GWFA) algorithm emerged as the fastest strategy for aligning long reads to genomic graphs. However, the available GWFA implementation does not support alignment backtracking, a crucial feature in real-case studies. In this paper, we propose a new open-source[1] implementation of the GWFA algorithm that computes and reports the complete traceback in the standard GAF format. Our work achieves a 20× speedup in execution time compared to the state-of-the-art tool GraphAligner and competitive memory usage.},
}

*Algorithms
Humans
Sequence Alignment/methods
Genome, Human
Genomics/methods
Sequence Analysis, DNA/methods
Software

@article {pmid40038508,
year = {2025},
author = {Nassir, N and A Almarri, M and Akter, H and Hassan Khansaheb, H and Uddin, KMF and Abou Tayoun, A and Du Plessis, SS and Haber, M and Alsheikh-Ali, A and Uddin, M},
title = {Advancing clinical genomics with Middle Eastern and South Asian pangenomes.},
journal = {Nature medicine},
volume = {},
number = {},
pages = {},
pmid = {40038508},
issn = {1546-170X},
}

@article {pmid40038014,
year = {2025},
author = {Wang, N and Wang, W and Zhu, Q},
title = {Unlocking the genetic blueprint of bamboo for climate adaption.},
journal = {Trends in plant science},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tplants.2025.02.007},
pmid = {40038014},
issn = {1878-4372},
abstract = {In a recent study, Hou et al. developed a high-resolution, haplotype-based pangenome for moso bamboo (Phyllostachys edulis), revealing significant genetic diversity and over 1000 climate-associated variants. Their findings highlight adaptive mechanisms for the ecological resilience of bamboo, providing crucial insights for climate-resilient breeding and conservation to ensure the long-term ecological and economic benefits of moso bamboo amid climate change.},
}

@article {pmid40037844,
year = {2025},
author = {Horsfield, ST and Fok, BCT and Fu, Y and Turner, P and Lees, JA and Croucher, NJ},
title = {Optimizing nanopore adaptive sampling for pneumococcal serotype surveillance in complex samples using the graph-based GNASTy algorithm.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279435.124},
pmid = {40037844},
issn = {1549-5469},
abstract = {Serotype surveillance of Streptococcus pneumoniae (the pneumococcus) is critical for understanding the effectiveness of current vaccination strategies. However, existing methods for serotyping are limited in their ability to identify the co-carriage of multiple pneumococci and detect novel serotypes. To develop a scalable and portable serotyping method that overcomes these challenges, we employed Nanopore Adaptive Sampling (NAS), an on-sequencer enrichment method that selects for target DNA in real-time, for direct detection of S. pneumoniae in complex samples. Whereas NAS targeting the whole S. pneumoniae genome was ineffective in the presence of nonpathogenic streptococci, the method was both specific and sensitive when targeting the capsular biosynthetic locus (CBL), the operon that determines S. pneumoniae serotype. NAS significantly improved coverage and yield of the CBL relative to sequencing without NAS, and accurately quantified the relative prevalence of serotypes in samples representing co-carriage. To maximize the sensitivity of NAS to detect novel serotypes, we developed and benchmarked a new pangenome-graph algorithm, named GNASTy. We show that GNASTy outperforms the current NAS implementation, which is based on linear genome alignment, when a sample contains a serotype absent from the database of targeted sequences. The methods developed in this work provide an improved approach for novel serotype discovery and routine S. pneumoniae surveillance that is fast, accurate and feasible in low-resource settings. Although NAS facilitates whole-genome enrichment under ideal circumstances, GNASTy enables targeted enrichment to optimize serotype surveillance in complex samples.},
}

@article {pmid40036544,
year = {2025},
author = {Phillips, A and Schultz, CJ and Burton, RA},
title = {New crops on the block: effective strategies to broaden our food, fibre and fuel repertoire in the face of increasingly volatile agricultural systems.},
journal = {Journal of experimental botany},
volume = {},
number = {},
pages = {},
doi = {10.1093/jxb/eraf023},
pmid = {40036544},
issn = {1460-2431},
abstract = {Climate change poses significant challenges to our ability to keep a growing global population fed, clothed, and fuelled. This review sets the scene by summarising the impacts of climate change on production of the major grain crop species rice, wheat, and maize, with a focus on yield reductions due to abiotic stresses and altered disease pressures. We discuss efforts to improve resilience, emphasising traits such as water use efficiency (WUE), heat tolerance, and disease resistance. We move on to exploring production trends of established, re-emerging, and new crops, highlighting the challenges of developing and maintaining new arrivals in the global market. We analyse the potential of wild relatives for improving domesticated crops, or as candidates for de novo domestication. The importance of pangenomes for uncovering genetic variation for crop improvement is also discussed. We examine the impact of climate change on non-cereals, including fruit, nut, and fibre crops and the potential of alternative multiuse crops to increase global sustainability and address climate change-related challenges. Agave is used as an exemplar to demonstrate the strategic pathway for developing a robust new crop option. There is a need for sustained investment in research and development across the entire value chain to facilitate the exploration of diverse species and genetic resources to enhance crop resilience and adaptability to future environmental conditions.},
}

@article {pmid40034122,
year = {2025},
author = {Villani, F and Guarracino, A and Ward, RR and Green, T and Emms, M and Pravenec, M and Sharp, B and Prins, P and Garrison, E and Williams, RW and Chen, H and Colonna, V},
title = {Pangenome reconstruction in rats enhances genotype-phenotype mapping and variant discovery.},
journal = {iScience},
volume = {28},
number = {2},
pages = {111835},
pmid = {40034122},
issn = {2589-0042},
abstract = {The HXB/BXH family of recombinant inbred rat strains is a unique genetic resource that has been extensively phenotyped over 25 years, resulting in a vast dataset of quantitative molecular and physiological phenotypes. We built a pangenome graph from 10x Genomics Linked-Read data for 31 recombinant inbred rats to study genetic variation and association mapping. The pangenome includes 0.2Gb of sequence that is not present the reference mRatBN7.2, confirming the capture of substantial additional variation. We validated variants in challenging regions, including complex structural variants resolving into multiple haplotypes. Phenome-wide association analysis of validated SNPs uncovered variants associated with glucose/insulin levels and hippocampal gene expression. We propose an interaction between Pirl1l1, chromogranin expression, TNF-α levels, and insulin regulation. This study demonstrates the utility of linked-read pangenomes for comprehensive variant detection and mapping phenotypic diversity in a widely used rat genetic reference panel.},
}

@article {pmid40033060,
year = {2025},
author = {Yano, R and Li, F and Hiraga, S and Takeshima, R and Kobayashi, M and Toda, K and Umehara, Y and Kajiya-Kanegae, H and Iwata, H and Kaga, A and Ishimoto, M},
title = {The genomic landscape of gene-level structural variations in Japanese and global soybean Glycine max cultivars.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40033060},
issn = {1546-1718},
support = {JPJ012287//Cabinet Office, Government of Japan/ ; JPJ012287//Cabinet Office, Government of Japan/ ; JPJ012287//Cabinet Office, Government of Japan/ ; JPJ012287//Cabinet Office, Government of Japan/ ; JPJ009237//NARO | Bio-oriented Technology Research Advancement Institution (BRAIN)/ ; },
abstract = {Japanese soybeans are traditionally bred to produce soy foods such as tofu, miso and boiled soybeans. Here, to investigate their distinctive genomic features, including genomic structural variations (SVs), we constructed 11 nanopore-based genome references for Japanese and other soybean lines. Our assembly-based comparative method, designated 'Asm2sv', identified gene-level SVs comprehensively, enabling pangenome analysis of 462 worldwide cultivars and varieties. Based on these, we identified selective sweeps between Japanese and US soybeans, one of which was the pod-shattering resistance gene PDH1. Genome-wide association studies further identified several quantitative trait loci that accounted for large-seed phenotypes of Japanese soybean lines, some of which were also close to regions of the selective sweeps, including PDH1. Notably, specific combinations of alleles, including SVs, were found to increase the seed size of some Japanese landraces. In addition to the differences in cultivation environments, distinct food processing usages might result in changes in Japanese soybean genomes.},
}

@article {pmid40030162,
year = {2025},
author = {Lee, RRQ and Chae, E},
title = {Monkeys at Rigged Typewriters: A Population and Network View of Plant Immune System Incompatibility.},
journal = {Annual review of plant biology},
volume = {},
number = {},
pages = {},
doi = {10.1146/annurev-arplant-083023-041225},
pmid = {40030162},
issn = {1545-2123},
abstract = {Immune system incompatibilities between naturally occurring genomic variants underlie many hybrid defects in plants and present a barrier for crop improvement. In this review, we approach immune system incompatibilities from pan-genomic and network perspectives. Pan-genomes offer insights into how natural variation shapes the evolutionary landscape of immune system incompatibilities, and through it, selection, polymorphisms, and recombination resistance emerge as common features that synergistically drive these incompatibilities. By contextualizing incompatibilities within the immune network, immune receptor promiscuity, complex dysregulation, and single-point failure appear to be recurrent themes of immune system defects. As geneticists break genes to investigate their function, so can we investigate broken immune systems to enrich our understanding of plant immune systems and work toward improving them.},
}

@article {pmid40027674,
year = {2025},
author = {Bouzek, H and Srinivasan, S and Jones, DS and McMahon, EF and Strenk, SM and Fiedler, TL and Fredricks, DN and Johnston, CD},
title = {A Syntenic Pangenome for Gardnerella Reveals Taxonomic Boundaries and Stratification of Metabolic and Virulence Potential across Species.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.02.19.636902},
pmid = {40027674},
issn = {2692-8205},
abstract = {Bacterial vaginosis (BV) is a prevalent condition associated with an imbalance in the vaginal microbiota, often involving species of Gardnerella . The taxonomic complexity and inconsistent nomenclature of Gardnerella have impeded progress in understanding the role of specific species in health and disease. In this study, we conducted a comprehensive genomic and pangenomic analysis to resolve taxonomic ambiguities and elucidate metabolic and virulence potential across Gardnerella species. We obtained complete, closed genomes for 42 Gardnerella isolates from women with BV and curated publicly available genome sequences (n = 291). Average nucleotide identity (ANI) analysis, digital DNA-DNA hybridization (dDDH), and the cpn60 gene sequences identified nine species and eleven subspecies within Gardnerella , for which we refined species and subspecies boundaries and proposed updated nomenclature. Pangenome analysis revealed species-specific gene clusters linked to metabolic pathways, virulence factors, and niche adaptations, distinguishing species specialized for mucin degradation in the vaginal environment from those potentially adapted to urinary tract colonization. Notably, we identified lineage-specific evolutionary divergence in gene clusters associated with biofilm formation, carbohydrate metabolism, and antimicrobial resistance. We further discovered the first cryptic plasmids naturally present within the Gardnerella genus. Our findings provide a unified framework for Gardnerella taxonomy and nomenclature, and enhance our understanding of species-specific functional capabilities, with implications for Gardnerella research, diagnostics, and targeted therapeutics in BV.},
}

@article {pmid40025556,
year = {2025},
author = {Hwang, S and Brown, NK and Ahmed, OY and Jenike, KM and Kovaka, S and Schatz, MC and Langmead, B},
title = {Mem-based pangenome indexing for k-mer queries.},
journal = {Algorithms for molecular biology : AMB},
volume = {20},
number = {1},
pages = {3},
pmid = {40025556},
issn = {1748-7188},
support = {R01HG011392/NH/NIH HHS/United States ; U01CA253481/NH/NIH HHS/United States ; R01HG011392/NH/NIH HHS/United States ; 2216612//National Science Foundation/ ; RGP0025/2021//Human Frontier Science Program/ ; },
abstract = {Pangenomes are growing in number and size, thanks to the prevalence of high-quality long-read assemblies. However, current methods for studying sequence composition and conservation within pangenomes have limitations. Methods based on graph pangenomes require a computationally expensive multiple-alignment step, which can leave out some variation. Indexes based on k-mers and de Bruijn graphs are limited to answering questions at a specific substring length k. We present Maximal Exact Match Ordered (MEMO), a pangenome indexing method based on maximal exact matches (MEMs) between sequences. A single MEMO index can handle arbitrary-length queries over pangenomic windows. MEMO enables both queries that test k-mer presence/absence (membership queries) and that count the number of genomes containing k-mers in a window (conservation queries). MEMO's index for a pangenome of 89 human autosomal haplotypes fits in 2.04 GB, 8.8 × smaller than a comparable KMC3 index and 11.4 × smaller than a PanKmer index. MEMO indexes can be made smaller by sacrificing some counting resolution, with our decile-resolution HPRC index reaching 0.67 GB. MEMO can conduct a conservation query for 31-mers over the human leukocyte antigen locus in 13.89 s, 2.5 × faster than other approaches. MEMO's small index size, lack of k-mer length dependence, and efficient queries make it a flexible tool for studying and visualizing substring conservation in pangenomes.},
}

@article {pmid40024538,
year = {2025},
author = {Sliti, A and Kim, RH and Lee, D and Shin, JH},
title = {Whole Genome Sequencing and In Silico Analysis of the Safety and Probiotic Features of Lacticaseibacillus paracasei FMT2 Isolated from Fecal Microbiota Transplantation (FMT) Capsules.},
journal = {Microbial pathogenesis},
volume = {},
number = {},
pages = {107405},
doi = {10.1016/j.micpath.2025.107405},
pmid = {40024538},
issn = {1096-1208},
abstract = {Lacticaseibacillus paracasei is widely used as a probiotic supplement and food additive in the medicinal and food industries. However, its application requires careful evaluation of safety traits associated with probiotic pathogenesis, including the transfer of antibiotic-resistance genes, the presence of virulence and pathogenicity factors, and the potential disruptions of the gut microbiome and immune system. In this study, we conducted whole genome sequencing (WGS) of L. paracasei FMT2 isolated from fecal microbiota transplantation (FMT) capsules and performed genome annotation to assess its probiotic and safety attributes. Our comparative genomic analysis assessed this novel strain's genetic attributes and functional diversity and unraveled its evolutionary relationships with other L. paracasei strains. The assembly yielded three contigs: one corresponding to the chromosome and two corresponding to plasmids. Genome annotation revealed the presence of 2,838 DNA-coding sequences (CDS), 78 ribosomal RNAs (rRNAs), 60 transfer RNAs (tRNAs), three non-coding RNAs (ncRNAs), and 126 pseudogenes. The strain lacked antibiotic resistance genes and pathogenicity factors. Two intact prophages, one Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR) region, and three antimicrobial peptide gene clusters were identified, highlighting the genomic stability and antimicrobial potential of the strain. Furthermore, genes linked to probiotic functions, such as mucosal colonization, stress resistance, and biofilm formation, were characterized. The pan-genome analysis identified 3,358 orthologous clusters, including 1,775 single-copy clusters, across all L. paracasei strains. Notably, L. paracasei FMT2 contained many unique singleton genes, potentially contributing to its distinctive probiotic properties. Our findings confirm the potential of L. paracasei FMT2 for food and therapeutic applications based on its probiotic profile and safety.},
}

@article {pmid40018873,
year = {2025},
author = {Jaggi, KE and Krak, K and Štorchová, H and Mandák, B and Marcheschi, A and Belyayev, A and Jellen, EN and Sproul, J and Jarvis, D and Maughan, PJ},
title = {A pangenome reveals LTR repeat dynamics as a major driver of genome evolution in Chenopodium.},
journal = {The plant genome},
volume = {18},
number = {1},
pages = {e70010},
pmid = {40018873},
issn = {1940-3372},
support = {CZ.02.01.01/00/22_008/0004581//TowArds Next 997 GENeration Crops/ ; RVO67985939//Czech Science Foundation/ ; 20-20286S//Czech Science Foundation/ ; 1022158//National Institute of Food and Agriculture/ ; },
mesh = {*Genome, Plant ; *Terminal Repeat Sequences ; *Evolution, Molecular ; *Chenopodium/genetics ; Retroelements ; Phylogeny ; Genome Size ; },
abstract = {The genus Chenopodium L. is characterized by its wide geographic distribution and ecological adaptability. Species such as quinoa (Chenopodium quinoa Willd.) have served as domesticated staple crops for centuries. Wild Chenopodium species exhibit diverse niche adaptations and are important genetic reservoirs for beneficial agronomic traits, including disease resistance and climate hardiness. To harness the potential of the wild taxa for crop improvement, we developed a Chenopodium pangenome through the assembly and comparative analyses of 12 Chenopodium species that encompass the eight known genome types (A-H). Six of the species are new chromosome-scale assemblies, and many are polyploids; thus, a total of 20 genomes were included in the pangenome analyses. We show that the genomes vary dramatically in size with the D genome being the smallest (∼370 Mb) and the B genome being the largest (∼700 Mb) and that genome size was correlated with independent expansions of the Copia and Gypsy LTR retrotransposon families, suggesting that transposable elements have played a critical role in the evolution of the Chenopodium genomes. We annotated a total of 33,457 pan-Chenopodium gene families, of which ∼65% were classified as shell (2% private). Phylogenetic analysis clarified the evolutionary relationships among the genome lineages, notably resolving the taxonomic placement of the F genome while highlighting the uniqueness of the A genome in the Western Hemisphere. These genomic resources are particularly important for understanding the secondary and tertiary gene pools available for the improvement of the domesticated chenopods while furthering our understanding of the evolution and complexity within the genus.},
}

*Genome, Plant
*Terminal Repeat Sequences
*Evolution, Molecular
*Chenopodium/genetics
Retroelements
Phylogeny
Genome Size

@article {pmid40012965,
year = {2025},
author = {Munung, NS},
title = {Science and Society: Pathways to Equitable Access and Delivery of Genomics Medicine in Africa.},
journal = {Current genetic medicine reports},
volume = {13},
number = {1},
pages = {1},
pmid = {40012965},
issn = {2167-4876},
abstract = {PURPOSE OF REVIEW: Recent advances in genetics are pushing the frontiers of health research in Africa. Notable developments include the release of the draft human pangenome reference, regulatory approval of gene editing therapies for sickle cell disease, and the announcements of major initiatives such as the Ghana Genome Project, the Personalized Medicine in North Africa Initiative, Nigeria's 100K Genome Project and South Africa's 110K Human Genomes Project. Additionally, gene-based therapies for HIV are on the horizon, with clinical trials planned in some African countries. Despite this progress, a pressing challenge remains: ensuring equitable access and delivery of genomics medicine worldwide, particularly in Africa and other low and middle income regions.

SUMMARY AND A CALL TO ACTION: Science diplomacy and academic-industry partnerships are key to achieving "Genomics for All." This requires collaboration between African governments, academic institutions, funding agencies, commercial biotechnology companies, civil society, and international health organizations. Together, these stakeholders must define and establish a sustainable framework to support genetic research in Africa, increase the availability of genetic data from African populations, and set-up translational genomics medicine initiatives tailored to the continent's unique healthcare needs. Science advocacy and diplomacy is also needed to establish mechanisms that prevent the hoarding of genetic resources, including genetic data and novel interventions, and guarantee equitable access to the scientific, medical and economic benefits of genomics for all nations. Achieving this vision may necessitate international treaties to promote equitable access to genomic innovations, responsible and ethical cross-border data sharing, and long-term strategies to address funding gaps in genomic research and its application in medicine and healthcare in Africa.},
}

@article {pmid40011682,
year = {2025},
author = {Guo, L and Wang, X and Ayhan, DH and Rhaman, MS and Yan, M and Jiang, J and Wang, D and Zheng, W and Mei, J and Ji, W and Jiao, J and Chen, S and Sun, J and Yi, S and Meng, D and Wang, J and Bhuiyan, MN and Qin, G and Guo, L and Yang, Q and Zhang, X and Sun, H and Liu, C and Deng, XW and Ye, W},
title = {Super pangenome of Vitis empowers identification of downy mildew resistance genes for grapevine improvement.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {40011682},
issn = {1546-1718},
abstract = {Grapevine (Vitis) is one of the oldest domesticated fruit crops with great cultural and economic importance. Here we assembled and annotated haplotype-resolved genomes of 72 global Vitis accessions including 25 wild and 47 cultivated grapevines, among which genomes for 60 grapevines are newly released. Haplotype-aware phylogenomics disentangled the mysterious hybridization history of grapevines, revealing the enormous genetic diversity of the Vitis genus. Pangenomic analysis reveals that European cultivars, more susceptible to the destructive disease downy mildew (DM), have a smaller repertoire of resistance genes in the NLR family encoding the TIR-NBARC-LRR domain. Through extensive structural variation (SV) characterization, phenotyping, DM-infection transcriptome profiling of 113 Vitis accessions, and SV-expression quantitative trait loci analysis, we have identified over 63 SVs and their relevant genes significantly associated with DM resistance, exemplified by a lysine histidine transporter, VvLHT8. This haplotype-resolved super pangenome of the Vitis genus will accelerate breeding and enrich our understanding of the evolution and biology of grapevines.},
}

@article {pmid40007769,
year = {2024},
author = {Man, QC and Wang, YQ and Gao, SJ and Gao, ZC and Peng, ZP and Cui, JH},
title = {Pan-genome analysis and expression verification of the maize ARF gene family.},
journal = {Frontiers in plant science},
volume = {15},
number = {},
pages = {1506853},
pmid = {40007769},
issn = {1664-462X},
abstract = {Auxin transcription factors regulate auxin responses and play crucial roles in plant growth, development, and responses to abiotic stress. Utilizing the maize pan-genome data, this study identified 35 ARF family members in maize, comprising 21 core genes, 10 near-core genes, and 4 non-essential genes; no private genes were detected. The construction of a phylogenetic tree using Arabidopsis thaliana revealed that the G3 subfamily comprises the highest number of core genes, with a total of 10, and exhibits relative stability throughout the evolution of maize. The calculation of the Ka/Ks ratios for ARF family members across 26 genomes indicated that, aside from ARF8 and ARF11, which were subjected to positive selection, the remaining genes underwent purifying selection. Analysis of structural variation revealed that the expression level of the ARF4 gene significantly differed as a result of this variation. Simultaneously, the structural variation also influenced the conserved domain and cis-acting elements of the gene. Further combining the transcriptome data and RT-qPCR found that, The expression levels of ARF family members in maize were higher at the early stage of embryo and grain development, and the expression levels of each member in embryo and grain were complementary, and the ARF4 plays an important role in abiotic stress. In summary, this study utilizes the maize pan-genome and bioinformatics methods to investigate the evolutionary relationships and functional roles of ARF family members in maize, thereby providing a novel theoretical framework for further research on the maize ARF family.},
}

@article {pmid40006763,
year = {2025},
author = {Wang, D and Xie, J and Wang, J and Mu, M and Xiong, H and Ma, F and Li, P and Jia, M and Li, S and Li, J and Zhu, M and Li, P and Guan, H and Zhang, Y and Li, H},
title = {Unraveling Allelic Impacts on Pre-Harvest Sprouting Resistance in TaVP1-B of Chinese Wheat Accessions Using Pan-Genome.},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {4},
pages = {},
pmid = {40006763},
issn = {2223-7747},
support = {32441052//National Natural Science Foundation of China/ ; 32102487//National Natural Science Foundation of China/ ; 232102110194//Foundation of Henan Science and Technology Committee/ ; No.ZKNUC20211046//Doctoral Scientific Research Starting Foundation of Zhoukou Normal University/ ; 2021GGJS139//Training Plan of Young Backbone Teachers in Colleges and Universities of Henan Province, China/ ; 225101610054//Projects of the Joint Fund of Henan Province's Science and Technology Research and Development Program (Industrial Category, grant NO. 225101610054)/ ; },
abstract = {The TaVP1-B gene, located on the 3B chromosome of wheat, is a homolog of the Viviparous-1 (VP-1) gene of maize and was reported to confer resistance to pre-harvest sprouting (PHS) in wheat. In this study, the structure of the TaVP1-B gene was analyzed using the wheat pan-genome consisting of 20 released cultivars (19 wheat are from China), and 3 single nucleotide polymorphisms (SNPs), which were identified at the 496 bp, 524 bp, and 1548 bp of the TaVP1-B CDS region, respectively. Haplotypes analysis showed that these SNPs were in complete linkage disequilibrium and that only two haplotypes designated as hap1 (TGG) and hap2 (GAA) were present. Association analysis between TaVP1-B haplotypes and PHS resistance of the 20 wheat cultivars in four experiment environments revealed that the average PHS resistance of accessions with hap1 was significantly better than that of accessions with hap2, which infers the effects of TaVP1-B on wheat PHS resistance. To further investigate the impacts of alleles at the TaVP1-B locus on PHS resistance, the SNP at 1548 bp of the TaVP1-B CDS region was converted to a KASP marker, which was used for genotyping 304 Chinese wheat cultivars, whose PHS resistance was evaluated in three environments. The average sprouting rates (SRs) of 135 wheat cultivars with the hap1 were significantly lower than the 169 cultivars with the hap2, validating the impacts of TaVP1-B on PHS resistance in Chinese wheat. The present study provided the breeding-friendly marker for functional variants in the TaVP1-B gene, which can be used for genetic improvement of PHS resistance in wheat.},
}

@article {pmid40005925,
year = {2025},
author = {Ye, M and Jiang, Y and Han, Q and Li, X and Meng, C and Ji, C and Ji, F and Zhou, B},
title = {Probiotic Potential of Enterococcus lactis GL3 Strain Isolated from Honeybee (Apis mellifera L.) Larvae: Insights into Its Antimicrobial Activity Against Paenibacillus larvae.},
journal = {Veterinary sciences},
volume = {12},
number = {2},
pages = {},
pmid = {40005925},
issn = {2306-7381},
support = {R2110//Open Project Program of Jiangsu Key Laboratory of Zoonosis, China/ ; SJCX23_1960//Postgraduate Research & Practice Innovation Programs of Jiangsu Province (Yangzhou University)/ ; },
abstract = {This study aimed to address the need for effective probiotics and antibacterial agents to combat American foulbrood disease in honeybees, caused by Paenibacillus larvae. In the context of declining honeybee populations due to pathogens, we isolated eight lactic acid bacteria (LAB) strains from honeybee larvae (Apis mellifera L.) and evaluated their probiotic potential and inhibitory effects against P. larvae. Methods included probiotic property assessments, such as acid and bile salt resistance, hydrophobicity, auto-aggregation, co-aggregation with P. larvae, antioxidant capacities, osmotolerance to 50% sucrose, and antibiotic susceptibility. Results indicated that the GL3 strain exhibited superior probiotic attributes and potent inhibitory effects on P. larvae. Whole-genome sequencing revealed GL3 to be an Enterococcus lactis strain with genetic features tailored to the honeybee larval gut environment. Pangenome analysis highlighted genetic diversity among E. lactis strains, while molecular docking analysis identified aborycin, a lasso peptide produced by GL3, as a promising inhibitor of bacterial cell wall synthesis. These findings suggested that GL3 was a promising probiotic candidate and antibacterial agent for honeybee health management, warranting further investigation into its in vivo efficacy and potential applications in beekeeping practices.},
}

@article {pmid40005785,
year = {2025},
author = {Fauzia, KA and Rathnayake, J and Doohan, D and Lamawansa, MD and Alfaray, RI and Batsaikhan, S and Phuc, BH and Waskito, LA and Tuan, VP and Kabamba, ET and Ansari, S and Matsumoto, T and Akada, J and Matsuhisa, T and Yamaoka, Y},
title = {Beyond Low Prevalence: Exploring Antibiotic Resistance and Virulence Profiles in Sri Lankan Helicobacter pylori with Comparative Genomics.},
journal = {Microorganisms},
volume = {13},
number = {2},
pages = {},
doi = {10.3390/microorganisms13020420},
pmid = {40005785},
issn = {2076-2607},
support = {18KK0266//Ministry of Education, Culture, Sports, Science, and Technology (MEXT) of Japan/ ; 19H03473//Ministry of Education, Culture, Sports, Science, and Technology (MEXT) of Japan/ ; 21H00346//Ministry of Education, Culture, Sports, Science, and Technology (MEXT) of Japan/ ; 22H02871//Ministry of Education, Culture, Sports, Science, and Technology (MEXT) of Japan/ ; 21K07898//Ministry of Education, Culture, Sports, Science, and Technology (MEXT) of Japan/ ; 21K08010//Ministry of Education, Culture, Sports, Science, and Technology (MEXT) of Japan/ ; ) [e-ASIA JRP, Science and Technology Research Partnership for Sustainable Development (SATREPS)]//Japan Agency for Medical Research and Development (AMED)/ ; //Japan International Cooperation Agency (JICA)/ ; },
abstract = {Helicobacter pylori infects at least half the population worldwide, and its highly diverse genomic content correlates with its geographic distribution because of its prolonged relationship with humans. The extremely low infection prevalence alongside low inflammation severity observed in some countries might be caused by strains with low virulence potential. Therefore, this study aimed to investigate whole-genome analysis datasets of Sri Lankan H. pylori strains. H. pylori strains were isolated from biopsy specimens and underwent whole-genome sequencing to investigate their antibiotic resistance and virulence potential. The prevalence of H. pylori infection in Sri Lanka is extremely low (1.7% in a previous study), and only six H. pylori strains were successfully isolated from bacterial culture. Antibiotic resistance analysis showed a high prevalence of metronidazole resistance (83.3%, five out of six strains), and investigation of the related genes showed truncation of the rdxA and frxA genes and single-nucleotide polymorphisms in the rdxA, frxA, ribF, omp11, and fur genes. Most virulence genes of the 144 assessed were present, except for the cag pathogenicity island (cagPAI) (absent in four out of six strains), babA/B/C, and tlpB genes. An incomplete type 4 secretion system (tfs) was found in three strains. A pan-genome analysis with non-Sri Lankan H. pylori strains showed that the htpX gene was found only in Sri Lankan strains (p-corrected = 0.0008). A phylogenetic analysis showed that the Sri Lankan strains clustered with strains from hpAsia2 and hpEurope. This comparative genomic study shows that H. pylori strains with low virulence potential are present in countries with a low prevalence of infection and disease severity, indicating a strain-type geographical pattern. The tailored guidelines for screening and treatment strategy for each region are necessary to obtain effective and efficient eradication.},
}

@article {pmid40005542,
year = {2025},
author = {Dudley, EP and Scott, MA and Kittana, H and Thompson, AC and Valeris-Chacin, R},
title = {The Pathogenomics of the Respiratory Mycoplasma bovis Strains Circulating in Cattle Around the Texas Panhandle, USA.},
journal = {Pathogens (Basel, Switzerland)},
volume = {14},
number = {2},
pages = {},
doi = {10.3390/pathogens14020167},
pmid = {40005542},
issn = {2076-0817},
mesh = {Animals ; Cattle ; *Mycoplasma bovis/genetics/isolation & purification ; Texas/epidemiology ; *Mycoplasma Infections/veterinary/microbiology/epidemiology ; Cattle Diseases/microbiology/epidemiology ; Genetic Variation ; Whole Genome Sequencing ; Genome, Bacterial/genetics ; Female ; Virulence Factors/genetics ; Male ; },
abstract = {Bovine respiratory disease (BRD) is a major economic and animal welfare issue in the beef industry. Mycoplasma bovis is one of the main causal organisms, particularly in chronic cases. Due to the difficulty of isolating M. bovis from clinical isolates, there is a lack of information on the genetic diversity of this pathogen in the Texas panhandle region of the United States. Therefore, our objective was to provide genome-level characterization of M. bovis isolated from the lung lesions of beef and dairy cattle in the Texas panhandle. Fifty-four isolates displaying mycoplasma-like growth were recovered from bovine lung lesions by the Texas Veterinary Medical Diagnostic Laboratory in 2021 and 2022. Of these isolates, 32 were determined to be M. bovis via species-specific qPCR using the uvrC gene. Long-read whole-genome sequencing was used to identify key virulence factors, antimicrobial resistance genes, and to assess the genetic diversity of these isolates. Fisher's exact tests were used to identify associations between isolate characteristics and host metadata, including the state of origin, type of operation, animal age, and animal sex. Our results indicate that there is considerable genetic diversity among the M. bovis isolates, despite their shared geography in the Texas panhandle, though significant clustering based on host metadata was observed. Analysis of the pangenome showed that the M. bovis isolates in this study also harbor a diverse array of virulence genes, but no antimicrobial resistance genes were identified in this study.},
}

Animals
Cattle
*Mycoplasma bovis/genetics/isolation & purification
Texas/epidemiology
*Mycoplasma Infections/veterinary/microbiology/epidemiology
Cattle Diseases/microbiology/epidemiology
Genetic Variation
Whole Genome Sequencing
Genome, Bacterial/genetics
Female
Virulence Factors/genetics
Male

@article {pmid40002726,
year = {2025},
author = {Morey-León, G and Fernández-Cadena, JC and Andrade-Molina, D and Berná, L},
title = {Decoding Ecuadorian Mycobacterium tuberculosis Isolates: Unveiling Lineage-Associated Signatures in Beta-Lactamase Resistance via Pangenome Analysis.},
journal = {Biomedicines},
volume = {13},
number = {2},
pages = {},
doi = {10.3390/biomedicines13020313},
pmid = {40002726},
issn = {2227-9059},
abstract = {Background: Tuberculosis is the second largest public health threat caused by pathogens. Understanding Mycobacterium tuberculosis's transmission, virulence, and resistance profile is crucial for outbreak control. This study aimed to investigate the pangenome composition of Mycobacterium tuberculosis clinical isolates classified as L4 derived from Ecuador. Methods: We analyzed 88 clinical isolates of Mycobacterium tuberculosis by whole-genome sequencing (WGS) and bioinformatic tools for Lineage, Drug-resistance and Pangenome analysis. Results: In our analysis, we identified the dominance of the LAM lineage (44.3%). The pangenomic analysis revealed a core genome of approximately 3200 genes and a pangenome that differed in accessory and unique genes. According to the COG database, metabolism-related genes were the most representative of all partitions. However, differences were found within all lineages analyzed in the metabolic pathways described by KEGG. Isolates from Ecuador showed variations in genomic regions associated with beta-lactamase susceptibility, potentially leading to epistatic resistance to other drugs commonly used in TB treatment, warranting further investigation. Conclusions: Our findings provide valuable insights into the genetic diversity of Mycobacterium tuberculosis populations in Ecuador. These insights may be associated with increasing adaptation within host heterogeneity, variable latency periods, and reduced host damage, collectively contributing to disease spread. The application of WGS is essential to elucidating the epidemiology of TB in the country.},
}

@article {pmid40000832,
year = {2025},
author = {Du, W and Sun, Q and Hu, S and Yu, P and Kan, S and Zhang, W},
title = {Equus mitochondrial pangenome reveals independent domestication imprints in donkeys and horses.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {6803},
pmid = {40000832},
issn = {2045-2322},
support = {ZR2023QC278//Natural Science Foundation of Shandong Province/ ; 2022YFC3341002-2//National Key Research and Development Program of China/ ; },
mesh = {Animals ; *Equidae/genetics ; *Genome, Mitochondrial ; *Domestication ; Horses/genetics ; *Phylogeny ; Genetic Variation ; Mitochondria/genetics ; Animals, Domestic/genetics ; },
abstract = {Mitochondria are semi-autonomous organelles that play a crucial role in the energy budget of animal cells and are closely related to the locomotor abilities of animals. Equidae is renowned for including two domesticated species with distinct purposes: the endurance-oriented donkey and the power-driven horse, making it an ideal system for studying the relationship between mitochondria and locomotor abilities. In this study, to cover the genetic diversity of donkeys, we sequenced and assembled six new mitochondrial genomes from China. Meanwhile, we downloaded the published mitochondrial genomes of all species within Equus and conducted a comprehensive pan-mitochondrial genome analysis. We found that the mitochondrial genomes of Equus are highly conserved, each encoding 37 genes, including 13 protein-coding genes (PCGs). Phylogenetic analysis based on mitochondrial genomes supports previous research, indicating that the extant species in Equus are divided into three main branches: horses, donkeys, and zebras. Specifically, 761 genetic variants were identified between donkeys and horses, 68 of which were non-synonymous mutations in PCGs, potentially linked to their different locomotor abilities. Structural protein modeling indicated that despite genetic differences, the overall protein structures between donkeys and horses remain similar. This study revealed the mitochondrial genome variation patterns of domesticated animals, offering novelty perspectives on domestication imprints. Additionally, it provides reliable candidate molecular markers for the identification of donkeys and horses.},
}

Animals
*Equidae/genetics
*Genome, Mitochondrial
*Domestication
Horses/genetics
*Phylogeny
Genetic Variation
Mitochondria/genetics
Animals, Domestic/genetics

@article {pmid40000572,
year = {2025},
author = {Michealsamy, A and Jayapalan, S},
title = {Comparative Pan- and Phylo-Genomic Analysis of Ideonella and Thermobifida Strains: Dissemination of Biodegradation Potential and Genomic Divergence.},
journal = {Biochemical genetics},
volume = {},
number = {},
pages = {},
pmid = {40000572},
issn = {1573-4927},
abstract = {Ideonella and Thermobifida were the most promising bacterial candidates for degrading plastic polymers. A comparative pan- and phylogenomic analysis of 33 Ideonella and Thermobifida strains was done to determine their plastic degradation potential, niche adaptation and speciation. Our study disclosed that more accessory genes in the strains showed phenotypic plasticity, according to the BPGA data. Pan and core genes were employed for the phylogenetic reconstruction. Pathway enrichment analyses scrutinized the functional roles of the core and adaptive-associated genes. KEGG annotation revealed that most genes were associated with the metabolism of amino acids and carbohydrates. The detailed COG analysis disclosed that approximately 40% of the pan genes performed metabolic functions. The unique gene pool consisted of genes chiefly involved in "general function prediction" and "amino acid transport and metabolism". Our in silico study revealed that these strains could assist in agronomic applications in the future since they devour nitrogen compounds and their central metabolic pathways are involved in amino acid metabolism. The rational selection of strains of Ideonella is far more effective at depolymerising plastics than Thermobifida. A greater number of unique genes, 1701 and 692, were identified for Ideonella sakaiensis 201-F6 and Thermobifida alba DSM-43795, respectively. Furthermore, we examined the singletons involved in xenobiotic catabolism. The unique singleton data were used to construct a supertree. To characterize the conserved patterns, we used SMART and MEME to identify domain and transmembrane regions in the unique protein sequences. Therefore, our study unraveled the genomic insights into the ecology-driven speciation of Ideonella and Thermobifida.},
}

@article {pmid39997406,
year = {2025},
author = {He, Y and Liu, B and Ouyang, X and He, M and Hui, H and Tang, B and Feng, L and Ren, M and Chen, G and Liu, G and He, X},
title = {Whole-Genome Sequencing and Fine Map Analysis of Pholiota nameko.},
journal = {Journal of fungi (Basel, Switzerland)},
volume = {11},
number = {2},
pages = {},
pmid = {39997406},
issn = {2309-608X},
support = {No. 32260797//the National Natural Science Foundation of China/ ; No. 2024NC-YBXM-190, 2023-CX-TD-40//Shaanxi Provincial Science and Technology Department Project/ ; },
abstract = {Pholiota nameko (T. Ito) S. Ito and S. Imai is an emerging wild mushroom species belonging to the genus Pholiota. Its unique brown-yellow appearance and significant biological activity have garnered increasing attention in recent years. However, there is a relative lack of research on the biological characteristics and genetics of P. nameko, which greatly limits the potential for an in-depth exploration of this mushroom in the research fields of molecular breeding and evolutionary biology. This study aimed to address that gap by employing Illumina and Nanopore sequencing technologies to perform whole-genome sequencing, de novo assembly, and annotation analysis of the P. nameko ZZ1 strain. Utilizing bioinformatics methods, we conducted a comprehensive analysis of the genomic characteristics of this strain and successfully identified candidate genes associated with its mating type, carbohydrate-active enzymes, virulence factors, pan-genome, and drug resistance functions. The genome of P. nameko ZZ1 is 24.58 Mb in size and comprises 33 contigs, with a contig N50 of 2.11 Mb. A hylogenetic analysis further elucidated the genetic relationship between P. nameko and other Pholiota, revealing a high degree of collinearity between P. nameko and ZZ1. In our enzyme analysis, we identified 246 enzymes in the ZZ1 genome, including 68 key carbohydrate-active enzymes (CAZymes), and predicted the presence of 11 laccases, highlighting the strain's strong potential for cellulose degradation. We conducted a pan-genomic analysis of five closely related strains of Pholiota, yielding extensive genomic information. Among these, there were 2608 core genes, accounting for 21.35% of the total genes, and 135 dispensable genes, highlighting significant genetic diversity among Pholiota and further confirming the value of pan-genomic analysis in uncovering species diversity. Notably, while we successfully identified the A-mating-type locus, composed of the homeodomain protein genes HD1 and HD2 in ZZ1, we were unable to obtain the B-mating-type locus due to technical limitations, preventing us from acquiring the pheromone receptor of the B-mating-type. We plan to supplement these data in future studies and explore the potential impact of the B-mating-type locus on the current findings. In summary, the genome data of ZZ1 presented in this study are not only valuable resources for understanding the genetic basis of this species, but also serve as a crucial foundation for subsequent genome-assisted breeding, research into cultivation technology, and the exploration of its nutritional and potential medicinal value.},
}

@article {pmid39992097,
year = {2025},
author = {Salamzade, R and Kalan, LR},
title = {Context matters: assessing the impacts of genomic background and ecology on microbial biosynthetic gene cluster evolution.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0153824},
doi = {10.1128/msystems.01538-24},
pmid = {39992097},
issn = {2379-5077},
abstract = {Encoded within many microbial genomes, biosynthetic gene clusters (BGCs) underlie the synthesis of various secondary metabolites that often mediate ecologically important functions. Several studies and bioinformatics methods developed over the past decade have advanced our understanding of both microbial pangenomes and BGC evolution. In this minireview, we first highlight challenges in broad evolutionary analysis of BGCs, including delineation of BGC boundaries and clustering of BGCs across genomes. We further summarize key findings from microbial comparative genomics studies on BGC conservation across taxa and habitats and discuss the potential fitness effects of BGCs in different settings. Afterward, recent research showing the importance of genomic context on the production of secondary metabolites and the evolution of BGCs is highlighted. These studies draw parallels to recent, broader, investigations on gene-to-gene associations within microbial pangenomes. Finally, we describe mechanisms by which microbial pangenomes and BGCs evolve, ranging from the acquisition or origination of entire BGCs to micro-evolutionary trends of individual biosynthetic genes. An outlook on how expansions in the biosynthetic capabilities of some taxa might support theories that open pangenomes are the result of adaptive evolution is also discussed. We conclude with remarks about how future work leveraging longitudinal metagenomics across diverse ecosystems is likely to significantly improve our understanding on the evolution of microbial genomes and BGCs.},
}

@article {pmid39990550,
year = {2025},
author = {Monlong, J and Chen, X and Barseghyan, H and Rowell, WJ and Negi, S and Nokoff, N and Mohnach, L and Hirsch, J and Finlayson, C and Keegan, CE and Almalvez, M and Berger, SI and de Dios, I and McNulty, B and Robertson, A and Miga, KH and Speiser, PW and Paten, B and Vilain, E and Délot, EC},
title = {Long-read sequencing resolves the clinically relevant CYP21A2 locus, supporting a new clinical test for Congenital Adrenal Hyperplasia.},
journal = {medRxiv : the preprint server for health sciences},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.02.07.25321404},
pmid = {39990550},
abstract = {Congenital Adrenal Hyperplasia (CAH), one of the most common inherited disorders, is caused by defects in adrenal steroidogenesis. It is potentially lethal if untreated and is associated with multiple comorbidities, including fertility issues, obesity, insulin resistance, and dyslipidemia. CAH can result from variants in multiple genes, but the most frequent cause is deletions and conversions in the segmentally duplicated RCCX module, which contains the CYP21A2 gene and a pseudogene. The molecular genetic test to identify pathogenic alleles is cumbersome, incomplete, and available from a limited number of laboratories. It requires testing parents for accurate interpretation, leading to healthcare inequity. Less severe forms are frequently misdiagnosed, and phenotype/genotype correlations incompletely understood. We explored whether emerging technologies could be leveraged to identify all pathogenic alleles of CAH, including phasing in proband-only cases. We targeted long-read sequencing outputs that would be practical in a clinical laboratory setting. Both HiFi-based and nanopore-based whole-genome long-read sequencing datasets could be mined to accurately identify pathogenic single-nucleotide variants, full gene deletions, fusions creating non-functional hybrids between the gene and pseudogene ("30-kb deletion"), as well as count the number of RCCX modules and phase the resulting multimodular haplotypes. On the Hi-Fi data set of 6 samples, the PacBio Paraphase tool was able to distinguish nine different mono-, bi-, and tri-modular haplotypes, as well as the 30-kb and whole gene deletions. To do the same on the ONT-Nanopore dataset, we designed a tool, Parakit, which creates an enriched local pangenome to represent known haplotype assemblies and map ClinVar pathogenic variants and fusions onto them. With few labels in the region, optical genome mapping was not able to reliably resolve module counts or fusions, although designing a tool to mine the dataset specifically for this region may allow doing so in the future. Both sequencing techniques yielded congruent results, matching clinically identified variants, and offered additional information above the clinical test, including phasing, count of RCCX modules, and status of the other module genes, all of which may be of clinical relevance. Thus long-read sequencing could be used to identify variants causing multiple forms of CAH in a single test.},
}

@article {pmid39990470,
year = {2025},
author = {Edwards, SV and Fang, B and Khost, D and Kolyfetis, GE and Cheek, RG and Deraad, D and Chen, N and Fitzpatrick, JW and McCormack, JE and Funk, WC and Ghalambor, CK and Garrison, E and Guarracino, A and Li, H and Sackton, TB},
title = {Comparative population pangenomes reveal unexpected complexity and fitness effects of structural variants.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.02.11.637762},
pmid = {39990470},
issn = {2692-8205},
abstract = {Structural variants (SVs) are widespread in vertebrate genomes, yet their evolutionary dynamics remain poorly understood. Using 45 long-read de novo genome assemblies and pangenome tools, we analyze SVs within three closely related species of North American jays (Aphelocoma, scrub-jays) displaying a 60-fold range in effective population size. We find rapid evolution of genome architecture, including ~100 Mb variation in genome size driven by dynamic satellite landscapes with unexpectedly long (> 10 kb) repeat units and widespread variation in gene content, influencing gene expression. SVs exhibit slightly deleterious dynamics modulated by variant length and population size, with strong evidence of adaptive fixation only in large populations. Our results demonstrate how population size shapes the distribution of SVs and the importance of pangenomes to characterizing genomic diversity.},
}

@article {pmid39990346,
year = {2025},
author = {Prodanov, T and Plender, EG and Seebohm, G and Meuth, SG and Eichler, EE and Marschall, T},
title = {Locityper: targeted genotyping of complex polymorphic genes.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.05.03.592358},
pmid = {39990346},
issn = {2692-8205},
abstract = {The human genome contains numerous structurally-variable polymorphic loci, including several hundred disease-associated genes, almost inaccessible for accurate variant calling. Here we present Locityper, a tool capable of genotyping such challenging genes using short and long-read whole genome sequencing. For each target, Locityper recruits and aligns reads to locus haplotypes, for instance extracted from a pangenome, and finds the likeliest haplotype pair by optimizing read alignment, insert size and read depth profiles. Locityper accurately genotypes up to 194 of 256 challenging medically relevant loci (95% haplotypes at QV33), an 8.8-fold gain compared to 22 genes achieved with standard variant calling pipelines. Furthermore, Locityper provides access to hyperpolymorphic HLA genes and other gene families, including KIR, MUC and FCGR. With its low running time of 1h10m per sample at 8 threads, Locityper is scalable to biobank-sized cohorts, enabling association studies for previously intractable disease-relevant genes.},
}

@article {pmid39984482,
year = {2025},
author = {Ucuncu, MY and Ucuncu, MK and Karacan, I and Topcuoglu, N},
title = {Genome resequencing and comparative analysis of Streptococcus mutans in adults with high and low caries risk.},
journal = {Scientific data},
volume = {12},
number = {1},
pages = {313},
pmid = {39984482},
issn = {2052-4463},
support = {38340//Bilimsel Araştirma Projeleri Birimi, Istanbul Üniversitesi (Department of Scientific Research Projects, Istanbul University)/ ; 38340//Bilimsel Araştirma Projeleri Birimi, Istanbul Üniversitesi (Department of Scientific Research Projects, Istanbul University)/ ; 38340//Bilimsel Araştirma Projeleri Birimi, Istanbul Üniversitesi (Department of Scientific Research Projects, Istanbul University)/ ; 38340//Bilimsel Araştirma Projeleri Birimi, Istanbul Üniversitesi (Department of Scientific Research Projects, Istanbul University)/ ; },
mesh = {*Streptococcus mutans/genetics ; *Dental Caries/microbiology ; Humans ; *Genome, Bacterial ; Adult ; *Whole Genome Sequencing ; Saliva/microbiology ; },
abstract = {Streptococcus mutans, is considered the main microbial etiological agent of dental caries, therefore it has been proposed as a useful predictor of caries risk as well as a target for caries prevention strategies. We aimed to compare the genomic characteristics of S. mutans strains isolated from individuals with high and low caries risk, in order to determine their genotypic features related to dental caries in adults. A total of 25 S. mutans isolates, obtained from the saliva of 13 volunteers with high dental caries activity and 12 caries-free individuals, were analysed using whole-genome sequencing techniques. A total of 2904 protein-coding gene sequences were detected as a result of the pan-genome analysis. The number of core genes detected in all genomes sequenced in the study was found to be 1563. A total of 50584 mutations were detected using ATCC 25175 strain as a reference. This is a large genome dataset of 25 S. mutans strains which can be further used for all S. mutans genome analysis.},
}

*Streptococcus mutans/genetics
*Dental Caries/microbiology
Humans
*Genome, Bacterial
Adult
*Whole Genome Sequencing
Saliva/microbiology

@article {pmid39980694,
year = {2025},
author = {Hurtado, A and Ocejo, M and Oporto, B and Lavín, JL and Rodríguez, R and Marcos, MÁ and Urrutikoetxea-Gutiérrez, M and Alkorta, M and Marimón, JM},
title = {A One Health approach for the genomic characterization of antibiotic-resistant Campylobacter isolates using Nanopore whole-genome sequencing.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1540210},
pmid = {39980694},
issn = {1664-302X},
abstract = {In response to the growing threat posed by the spread of antimicrobial resistance in zoonotic Campylobacter, a One Health approach was used to examine the genomic diversity, phylogenomic relationships, and the distribution of genetic determinants of resistance (GDR) in C. jejuni and C. coli isolates from humans, animals (ruminants, swine, and chickens), and avian food products collected during a regionally (Basque Country, Spain) and temporally (mostly 2021-2022) restricted sampling. Eighty-three C. jejuni and seventy-one C. coli isolates, most exhibiting resistance to ciprofloxacin and/or erythromycin, were whole-genome sequenced using Oxford Nanopore Technologies long-fragment sequencing (ONT). Multilocus sequence typing (MLST) analysis identified a high genomic diversity among isolates. Phylogenomic analysis showed that clustering based on the core genome was aligned with MLST profiles, regardless of the sample source. In contrast, accessory genome content sometimes discriminated isolates within the same STs and occasionally differentiated isolates from different sources. The majority of the identified GDRs were present in isolates from different sources, and a good correlation was observed between GDR distribution and phenotypic susceptibility profiles (based on minimum inhibitory concentrations interpreted according to the EUCAST epidemiological cutoff values). Genotypic resistance profiles were independent of genotypes, indicating no apparent association between resistance and phylogenetic origin. This study demonstrates that ONT sequencing is a powerful tool for molecular surveillance of bacterial pathogens in the One Health framework.},
}

@article {pmid39979844,
year = {2025},
author = {Hong, H and Kang, M and Haymowicz, A and Le, HNM and Kim, E and Yang, SM and Ha, SD and Kim, HJ and Park, SH},
title = {Genetic characterization and in silico serotyping of 62 Salmonella enterica isolated from Korean poultry operations.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {166},
pmid = {39979844},
issn = {1471-2164},
mesh = {*Salmonella enterica/genetics/isolation & purification/classification/pathogenicity ; Animals ; *Serotyping ; *Poultry/microbiology ; *Phylogeny ; Republic of Korea ; Computer Simulation ; Genome, Bacterial ; Multilocus Sequence Typing ; Whole Genome Sequencing ; Virulence/genetics ; Drug Resistance, Bacterial/genetics ; Virulence Factors/genetics ; },
abstract = {BACKGROUND: The conventional method of antigen-based serotyping for Salmonella poses challenges due to the necessity of utilizing over 150 antisera. More recently, in silico Salmonella serotyping has emerged as a predictive alternative. The purpose of this study was to predict the serovars of 62 Salmonella enterica strains isolated from Korean poultry operations and their genetic characteristics using whole genome sequencing. The analysis employed diverse methods, including ribosomal, and core genome multi-locus sequence typing (MLST), based on Salmonella In Silico Typing Resource (SISTR). Pangenome, clusters of orthologous groups (COG) analysis, and identification of virulence and antibiotic resistance genes were conducted.

RESULTS: Salmonella enterica subspecies enterica serovars were observed and clustered based on the pangenome and phylogenetic tree: 21 Salmonella Albany (Albany), 13 Salmonella Bareilly (Bareilly), and 28 Salmonella Mbandaka (Mbandaka). The most frequently observed sequence types for the three serovars were ST292 in Albany, ST203 in Bareilly, and ST413 in Mbandaka. 18 antibiotic resistance genes showed varying presences based on the serovars, including Albany (qacEdelta1, tet(D), CARB-3 (blaCARB-3), and dfrA1) and Bareilly (aac(6')-ly). Intriguingly, a mutated gyrA (Ser83 → Phe, serine to phenylalanine) was observed in all 21 Albany strains, whereas Bareilly and Mbandaka carried the wild-type gyrA. Among 130 virulence genes analyzed, 107 were present in all 62 Salmonella strains, with Mbandaka strains exhibiting a higher prevalence of virulence genes related to fimbrial adherence compared to those of Albany and Bareilly.

CONCLUSIONS: The study identified distinct genetic characteristics among the three Salmonella serovars using whole genome sequencing. Albany carried a unique mutation in gyrA, occurring in the quinolone resistance-determining region. Additionally, the virulence gene profile of Mbandaka differed from the other serovars, particularly in fimbrial adherence genes. These findings demonstrate the effectiveness of in silico approaches in predicting Salmonella serovars and highlight genetic differences that may inform strategies for antibiotic resistance and virulence control, such as developing rapid diagnostic tools to detect the AMR (e.g. tet (D), and gyrA) or targeting serovar-specific virulence factors like fimbrial adherence genes in Mbandaka to mitigate pathogenicity.},
}

*Salmonella enterica/genetics/isolation & purification/classification/pathogenicity
Animals
*Serotyping
*Poultry/microbiology
*Phylogeny
Republic of Korea
Computer Simulation
Genome, Bacterial
Multilocus Sequence Typing
Whole Genome Sequencing
Virulence/genetics
Drug Resistance, Bacterial/genetics
Virulence Factors/genetics

@article {pmid39979599,
year = {2025},
author = {Secomandi, S and Gallo, GR and Rossi, R and Rodríguez Fernandes, C and Jarvis, ED and Bonisoli-Alquati, A and Gianfranceschi, L and Formenti, G},
title = {Author Correction: Pangenome graphs and their applications in biodiversity genomics.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41588-025-02132-2},
pmid = {39979599},
issn = {1546-1718},
}

@article {pmid39976902,
year = {2025},
author = {Rahman, MM and Siddique, N and Gilman, MAA and Hasnat, S and Haider, MG and Rahman, MM and Talukder, AK and Rahman, ANMA and Islam, T and Das, ZC and Hossain, MA and Hoque, MN},
title = {Genomic and In Vitro Analysis of Pediococcus pentosaceus MBBL4 Implicated Its Therapeutic Use Against Mastitis Pathogens and as a Potential Probiotic.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {39976902},
issn = {1867-1314},
abstract = {Pediococcus pentosaceus has the potential to be used as probiotics and biologics amid rising trends of global antimicrobial resistance (AMR) and non-communicable diseases. This study analyzed the genome of P. pentosaceus MBBL4, isolated from healthy cow milk, to assess its probiotic properties and antimicrobial efficacy. The strain was subjected to whole genome sequencing (WGS), assembly, and annotations, alongside phylogenetic and comparative genomic analyses. Additionally, carbohydrate utilization, metabolic pathways, genomic safety, and probiotic potential of MBBL4 were assessed. Its in vitro antimicrobial efficacy against mastitis pathogens was also evaluated. The WGS analysis uncovered many important probiotic traits in MBBL4. Phylogenetic analysis demonstrated a close genetic link with other 15 P. pentosaceus strains, sharing more than 99% of core genes within the pan-genome matrix. MBBL4 demonstrated extensive range of carbohydrate metabolism activity, supported by the presence of several genes encoded enzymes, including a complete elucidated lactose metabolism pathway along with 28 additional metabolic pathway modules. Notably, its genome contains regions associated with gallic acid metabolism and related genes. MBBL4 also harbored genes encoding immunity proteins like enterocin A and lactococcin, and antimicrobial compounds including penocin A, lysozymes, laccase, colicin V, and viguiepinol. Comparative analysis with other probiotic strains revealed seven novel exopolysaccharide biosynthesis proteins and one biofilm-related protein. Moreover, MBBL4 remained sensitive to 90% of the tested antibiotics and carried only a single lincosamide resistance gene (lnuA). It effectively inhibited the growth of two important bovine mastitis pathogens, Staphylococcus aureus D4C4 and Escherichia coli G1C5. These results, along with its low pathogenicity score, support the safety profile of MBBL4 and highlight its potential as bioactive natural therapeutic for mastitis and a promising probiotic candidate.},
}

@article {pmid39976625,
year = {2025},
author = {Lin, YJ and Chen, CH and Chang, IY and Chiang, RL and Wang, HY and Chiu, CH and Chen, YM},
title = {Genomic and transcriptomic insights into the virulence and adaptation of shock syndrome-causing Streptococcus anginosus.},
journal = {Microbiology (Reading, England)},
volume = {171},
number = {2},
pages = {},
doi = {10.1099/mic.0.001535},
pmid = {39976625},
issn = {1465-2080},
mesh = {*Streptococcus anginosus/genetics/pathogenicity ; *Genome, Bacterial ; Humans ; Virulence/genetics ; *Genomic Islands/genetics ; *Streptococcal Infections/microbiology ; Virulence Factors/genetics/metabolism ; Transcriptome ; Shock, Septic/microbiology ; Genomics ; Prophages/genetics ; Adolescent ; Gene Transfer, Horizontal ; Clustered Regularly Interspaced Short Palindromic Repeats ; Bacterial Proteins/genetics/metabolism ; Quorum Sensing/genetics ; },
abstract = {Streptococcus anginosus is a common isolate of the oral cavity and an opportunistic pathogen for systemic infections. Although the pyogenic infections caused by S. anginosus are similar to those caused by Streptococcus pyogenes, S. anginosus lacks most of the well-characterized virulence factors of S. pyogenes. To investigate the pathogenicity of S. anginosus, we analysed the genome of a newly identified S. anginosus strain, KH1, which was associated with toxic shock-like syndrome in an immunocompetent adolescent. The genome of KH1 contains nine genomic islands, two Clustered Regularly Interspaced Short Palindromic Repeats (CRISPR)/CRISPR-associated systems and many phage-related proteins, indicating that the genome is influenced by prophages and horizontal gene transfer. Comparative genome analysis of 355 S. anginosus strains revealed a significant difference between the sizes of the pan genome and core genome, reflecting notable strain variations. We further analysed the transcriptomes of KH1 under conditions mimicking either the oral cavity or the bloodstream. We found that in an artificial saliva medium, the expression of a putative quorum quenching system and pyruvate oxidase for H2O2 production was upregulated, which could optimize the competitiveness of S. anginosus in the oral ecosystem. Conversely, in a modified serum medium, purine and glucan biosynthesis, competence and bacteriocin production were significantly upregulated, likely facilitating the survival of KH1 in the bloodstream. These findings indicate that S. anginosus can utilize diverse mechanisms to adapt to different environmental niches and establish infection, despite its lack of toxin production.},
}

*Streptococcus anginosus/genetics/pathogenicity
*Genome, Bacterial
Humans
Virulence/genetics
*Genomic Islands/genetics
*Streptococcal Infections/microbiology
Virulence Factors/genetics/metabolism
Transcriptome
Shock, Septic/microbiology
Genomics
Prophages/genetics
Adolescent
Gene Transfer, Horizontal
Clustered Regularly Interspaced Short Palindromic Repeats
Bacterial Proteins/genetics/metabolism
Quorum Sensing/genetics

@article {pmid39975360,
year = {2025},
author = {Hu, M and Wan, P and Chen, C and Tang, S and Chen, J and Wang, L and Chakraborty, M and Zhou, Y and Chen, J and Gaut, BS and Emerson, JJ and Yi, L},
title = {Benchmarking, detection, and genotyping of structural variants in a population of whole-genome assemblies using the SVGAP pipeline.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.02.07.637096},
pmid = {39975360},
issn = {2692-8205},
abstract = {Comparisons of complete genome assemblies offer a direct procedure for characterizing all genetic differences among them. However, existing tools are often limited to specifi c aligners or optimized for specifi c organisms, narrowing their applicability, particularly for large and repetitive plant genomes. Here, we introduce SVGAP, a pipeline for structural variant (SV) discovery, genotyping, and annotation from high-quality genome assemblies at the population level. Through extensive benchmarks using simulated SV datasets at individual, population, and phylogenetic contexts, we demonstrate that SVGAP performs favorably relative to existing tools in SV discovery. Additionally, SVGAP is one of the few tools to address the challenge of genotyping SVs within large assembled genome samples, and it generates fully genotyped VCF fi les. Applying SVGAP to 26 maize genomes revealed hidden genomic diversity in centromeres, driven by abundant insertions of centromere-specifi c LTR-retrotransposons. The output of SVGAP is well-suited for pan-genome construction and facilitates the interpretation of previously unexplored genomic regions.},
}

@article {pmid39975203,
year = {2025},
author = {Khan, J and Dhulipala, L and Patro, R},
title = {Fast and Scalable Parallel External-Memory Construction of Colored Compacted de Bruijn Graphs with Cuttlefish 3.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.02.02.636161},
pmid = {39975203},
issn = {2692-8205},
abstract = {The rapid growth of genomic data over the past decade has made scalable and efficient sequence analysis algorithms, particularly for constructing de Bruijn graphs and their colored and compacted variants critical components of many bioinformatics pipelines. Colored compacted de Bruijn graphs condense repetitive sequence information, significantly reducing the data burden on downstream analyses like assembly, indexing, and pan-genomics. However, direct construction of these graphs is necessary as constructing the original uncompacted graph is essentially infeasible at large scale. In this paper, we introduce C uttlefish 3, a state-of-the-art parallel, external-memory algorithm for constructing (colored) compacted de Bruijn graphs. C uttlefish 3 introduces novel algorithmic improvements that provide its scalability and speed, including optimizations to significantly speed up local contractions within subgraphs, a parallel algorithm to join local solutions based on parallel list-ranking, and a sparsification method to vastly reduce the amount of data required to compute the colored graph. Leveraging these algorithmic strategies along with algorithm engineering optimizations in parallel and external-memory setting, C uttlefish 3 demonstrates state-of-the-art performance, surpassing existing approaches in speed and scalability across various genomic datasets in both colored and uncolored scenarios.},
}

@article {pmid39975192,
year = {2025},
author = {Dishuck, PC and Munson, KM and Lewis, AP and Dougherty, ML and Underwood, JG and Harvey, WT and Hsieh, P and Pastinen, T and Eichler, EE},
title = {Structural variation, selection, and diversification of the NPIP gene family from the human pangenome.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.02.04.636496},
pmid = {39975192},
issn = {2692-8205},
abstract = {The NPIP (nuclear pore interacting protein) gene family has expanded to high copy number in humans and African apes where it has been subject to an excess of amino acid replacement consistent with positive selection (1). Due to the limitations of short-read sequencing, NPIP human genetic diversity has been poorly understood. Using highly accurate assemblies generated from long-read sequencing as part of the human pangenome, we completely characterize 169 human haplotypes (4,665 NPIP paralogs and alleles). Of the 28 NPIP paralogs, just three (NPIPB2 , B11 , and B14) are fixed at a single copy, and only a single locus, B2 , shows no structural variation. Four NPIP paralogs map to large segmental duplication blocks that mediate polymorphic inversions (355 kbp-1.6 Mbp) corresponding to microdeletions associated with developmental delay and autism. Haplotype-based tests of positive selection and selective sweeps identify two paralogs, B9 and B15 , within the top percentile for both tests. Using full-length cDNA data from 101 tissue/cell types, we construct paralog-specific gene models and show that 56% (31/55 most abundant isoforms) have not been previously described in RefSeq. We define six distinct translation start sites and other protein structural features that distinguish paralogs, including a variable number tandem repeat that encodes a beta helix of variable size that emerged ∼3.1 million years ago in human evolution. Among the 28 NPIP paralogs, we identify distinct tissue and developmental patterns of expression with only a few maintaining the ancestral testis-enriched expression. A subset of paralogs (NPIPA1 , A5 , A6-9 , B3-5 , and B12/B13) show increased brain expression. Our results suggest ongoing positive selection in the human population and rapid diversification of NPIP gene models.},
}

@article {pmid39975036,
year = {2025},
author = {Sanaullah, A and Villalobos, S and Zhi, D and Zhang, S},
title = {Haplotype Matching with GBWT for Pangenome Graphs.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.02.03.634410},
pmid = {39975036},
issn = {2692-8205},
abstract = {Traditionally, variations from a linear reference genome were used to represent large sets of haplotypes compactly. In the linear reference genome based paradigm, the positional Burrows-Wheeler transform (PBWT) has traditionally been used to perform efficient haplotype matching. Pangenome graphs have recently been proposed as an alternative to linear reference genomes for representing the full spectrum of variations in the human genome. However, haplotype matches in pangenome graph based haplotype sets are not trivially generalizable from haplotype matches in the linear reference genome based haplotype sets. Work has been done to represent large sets of haplotypes as paths through a pangenome graph. The graph Burrows-Wheeler transform (GBWT) is one such work. The GBWT essentially stores the haplotype paths in a run length compressed BWT with compressed local alphabets. Although efficient in practice count and locate queries on the GBWT were provided by the original authors, the efficient haplotype matching capabilities of the PBWT have never been shown on the GBWT. In this paper, we formally define the notion of haplotype matches in pangenome graph-based haplotype sets by generalizing from haplotype matches in linear reference genome-based haplotype sets. We also describe the relationship between set maximal matches, long matches, locally maximal matches, and text maximal matches on the GBWT, PBWT, and the BWT. We provide algorithms for outputting some of these matches by applying the data structures of the r-index (introduced by Gagie et al.) to the GBWT. We show that these structures enable set maximal match and long match queries on the GBWT in almost linear time and in space close to linear in the number of runs in the GBWT. We also provide multiple versions of the query algorithms for different combinations of the available data structures. The long match query algorithms presented here even run on the BWT in the same time complexity as the GBWT due to their similarity.},
}

@article {pmid39974207,
year = {2025},
author = {Navasca, A and Singh, J and Rivera-Varas, V and Gill, U and Secor, G and Baldwin, T},
title = {Dispensable genome and segmental duplications drive the genome plasticity in Fusarium solani.},
journal = {Frontiers in fungal biology},
volume = {6},
number = {},
pages = {1432339},
pmid = {39974207},
issn = {2673-6128},
abstract = {Fusarium solani is a species complex encompassing a large phylogenetic clade with diverse members occupying varied habitats. We recently reported a unique opportunistic F. solani associated with unusual dark galls in sugarbeet. We assembled the chromosome-level genome of the F. solani sugarbeet isolate strain SB1 using Oxford Nanopore and Hi-C sequencing. The average size of F. solani genomes is 54 Mb, whereas SB1 has a larger genome of 59.38 Mb, organized into 15 chromosomes. The genome expansion of strain SB1 is due to the high repeats and segmental duplications within its three potentially accessory chromosomes. These chromosomes are absent in the closest reference genome with chromosome-level assembly, F. vanettenii 77-13-4. Segmental duplications were found in three chromosomes but are most extensive between two specific SB1 chromosomes, suggesting that this isolate may have doubled its accessory genes. Further comparison of the F. solani strain SB1 genome demonstrates inversions and syntenic regions to an accessory chromosome of F. vanettenii 77-13-4. The pan-genome of 12 publicly available F. solani isolates nearly reached gene saturation, with few new genes discovered after the addition of the last genome. Based on orthogroups and average nucleotide identity, F. solani is not grouped by lifestyle or origin. The pan-genome analysis further revealed the enrichment of several enzymes-coding genes within the dispensable (accessory + unique genes) genome, such as hydrolases, transferases, oxidoreductases, lyases, ligases, isomerase, and dehydrogenase. The evidence presented here suggests that genome plasticity, genetic diversity, and adaptive traits in Fusarium solani are driven by the dispensable genome with significant contributions from segmental duplications.},
}

@article {pmid39973926,
year = {2025},
author = {Magome, TG and Surleac, M and Hassim, A and Bezuidenhout, CC and van Heerden, H and Lekota, KE},
title = {Decoding the anomalies: a genome-based analysis of Bacillus cereus group strains closely related to Bacillus anthracis.},
journal = {Frontiers in microbiology},
volume = {16},
number = {},
pages = {1527049},
pmid = {39973926},
issn = {1664-302X},
abstract = {INTRODUCTION: The Bacillus cereus group encompasses a complex group of closely related pathogenic and non-pathogenic bacterial species. Key members include B. anthracis, B. cereus, and B. thuringiensis organisms that, despite genetic proximity, diverge significantly in morphology and pathogenic potential. Taxonomic challenges persist due to inconsistent classification methods, particularly for B. cereus isolates that resemble B. anthracis in genetic clustering.

METHODS: This study investigated B. cereus group isolates from blood smears of animal carcasses in Kruger National Park, uncovering an unusual isolate with B. cereus features based on classical microbiological tests yet B. anthracis-like genomic similarities with an Average Nucleotide Identity (ANI) of ≥95%. Using comparative genomics, pan-genomics and whole genome Single Nucleotide Polymorphism (wgSNP) analysis, a total of 103 B. cereus group genomes were analyzed, including nine newly sequenced isolates from South Africa and a collection of isolates that showed some classification discrepancies, thus classified as "anomalous."

RESULTS AND DISCUSSION: Of the 36 strains identified as B. anthracis in GenBank, 26 clustered phylogenetically with the four confirmed B. anthracis isolates from South Africa and shared 99% ANI. Isolates with less than 99% ANI alignment to B. anthracis exhibited characteristics consistent with B. cereus and/or B. thuringiensis, possessing diverse genetic profiles, insertion elements, resistance genes, and virulence genes features, contrasting with the genetic uniformity of typical B. anthracis. The findings underscore a recurrent acquisition of mobile genetic elements within B. cereus and B. thuringiensis, a process infrequent in B. anthracis.

CONCLUSION: This study highlights the pressing need for standardized taxonomic criteria in B. cereus group classification, especially as anomalous isolates emerge. This study supports the existing nomenclature framework which offers an effective solution for classifying species into genomospecies groups. We recommend isolates with ANI ≥99% to standard reference B. anthracis be designated as typical B. anthracis in GenBank to maintain taxonomic clarity and precision.},
}

@article {pmid39970851,
year = {2025},
author = {Mallappa, A and Kuralayanapalya Puttahonnappa, S and Shome, R and Patil, SS and Amachawadi, RG and Mohan, KSK and Venkatesh, SP and Ramesh, V and Sekar, YS and Thippeswamy, H and Patil, AV},
title = {Systematic review, Meta-analysis, and Pan-genome analytics predict the surging of Brucella melitensis by China and India-specific strains, elucidating the demand for enhanced preparedness.},
journal = {Journal of infection and public health},
volume = {18},
number = {4},
pages = {102693},
doi = {10.1016/j.jiph.2025.102693},
pmid = {39970851},
issn = {1876-035X},
abstract = {BACKGROUND: Brucellosis is an infectious disease in lower to moderate-income countries. It primarily affects small ruminant (sheep and goat) populations and can also be transmitted to mammals (humans). Brucella melitensis (B. melitensis) is the primary cause, posing a zoonotic threat. Controlling the spread of B. melitensis, especially in regions with high risk to humans and small ruminants, remains challenging. Current research explores the prevalence, genetic diversity, and prediction of brucellosis transmission in ruminants and humans.

METHODS: In this study, we developed an integrated database providing information on B. melitensis incidence in livestock from 2003 to 2024 and a systematic review and meta-analysis to assess the prevalence by following the Cochran collaborators' Preferred Reporting Items for Systematic Reviews and Meta-analysis guidelines. A comprehensive literature search was conducted using reputable sources. These included reputable sources of electronic databases such as PubMed, ScienceDirect, Scopus, Biomed Central, CeRA, Krishikosh, ProQuest Dissertations & Theses Global, and Web of Science, complemented by the Google Scholar search engine. We also utilized Zotero 5.0 and Rayyan QCR, two web-based tools. Time series model to predict incidence trends and pan-genomic analysis to determine genetic diversity across Asia and Africa.

RESULTS: Meta-analysis revealed an overall prevalence of 12 % of which the African continent rose at 7 % (95 % CI: 5-8 %, I[2] = 99 %, τ[2] = 0.03, P = 0), while the corresponding prevalence in the Asian continent constituted 12 % (95 % CI: 11-14 %, I[2] = 99 %, τ[2] = 0.02, P = 0). The Time series model predicts a rising trend in brucellosis incidence from 2023 to 2030. The pan-genome analysis identified Rev 1 (0.000712) strain from China and the CIIMS-PH-3 (0.000209) strains from India showed the highest branch length, considered to have more genetic diversity.

CONCLUSION: These findings underscore the critical need for ongoing surveillance models and research to monitor the evolving B. melitensis landscape. High-prevalence regions exhibit significant genetic diversity. Effective prevention & control and response & preparedness strategies, including precise detection through advanced diagnostics, robust surveillance models to track trends, and targeted vaccination of susceptible animals, are vital. Stringent quarantine protocols, biosecurity measures, and exploring herbal remedies as a complementary approach to conventional treatment are crucial to mitigate the brucellosis burden as a public health concern and its socioeconomic impact on livelihood.},
}

@article {pmid39969283,
year = {2025},
author = {Payne, CJ and Phuong, VH and Phuoc, NN and Dung, TT and Phuoc, LH and Crumlish, M},
title = {Genomic diversity and evolutionary patterns of Edwardsiella ictaluri affecting farmed striped catfish (Pangasianodon hypophthalmus) in Vietnam over 20 years.},
journal = {Microbial genomics},
volume = {11},
number = {2},
pages = {},
doi = {10.1099/mgen.0.001368},
pmid = {39969283},
issn = {2057-5858},
mesh = {*Edwardsiella ictaluri/genetics/pathogenicity ; Animals ; Vietnam ; *Catfishes/microbiology ; *Fish Diseases/microbiology ; *Enterobacteriaceae Infections/microbiology/veterinary ; *Phylogeny ; *Whole Genome Sequencing ; Genome, Bacterial ; Evolution, Molecular ; Genetic Variation ; Anti-Bacterial Agents/pharmacology ; Drug Resistance, Bacterial/genetics ; Plasmids/genetics ; Genomics ; Virulence Factors/genetics ; },
abstract = {Edwardsiella ictaluri continues to pose a significant risk to the health and production of striped catfish (Pangasianodon hypophthalmus) in Vietnam. Whilst recent advances in genomic sequencing provide an insight into the global genomic diversity of this important fish pathogen, genome-wide analysis of Vietnamese isolates recovered over time is lacking. In this study, we used a whole-genome sequencing approach to compare the genomes of 31 E. ictaluri isolates recovered over a 20-year period (2001-2021) and performed comparative genomic analysis to explore temporal changes in genome diversity, population structure and mechanisms driving pathogenesis and antimicrobial resistance. Our findings revealed an open pan-genome with 4148 genes and a core genome (3 060 genes) accounting for over two-thirds of the genome. Moreover, we found the genomes sequenced to classify into two distinct lineages and estimated the ancestral origin of these lineages within Vietnam to date back to the 1950s. Plasmids were highly prevalent in Vietnamese E. ictaluri, with isolates harbouring up to four plasmids within their genome. Further, a diverse mobilome was observed with nine different plasmid types detected across the genome collection. Exploration of putative plasmids revealed a diverse set of antimicrobial resistance genes (ARGs) against key antibiotics used in Vietnamese aquaculture and virulence genes associated with protein secretion systems. Correlation analysis revealed the total number of ARGs detected in genomes to increase with isolate recovery time. Whilst the number of virulence genes remained relatively stable, temporal variation was noted in several virulence factors related to motility and immune system modulation. Findings from this study highlight the need for continued genomic surveillance to monitor changes in antimicrobial resistance and pathogenesis, to help inform the development of disease control and management strategies.},
}

*Edwardsiella ictaluri/genetics/pathogenicity
Animals
Vietnam
*Catfishes/microbiology
*Fish Diseases/microbiology
*Enterobacteriaceae Infections/microbiology/veterinary
*Phylogeny
*Whole Genome Sequencing
Genome, Bacterial
Evolution, Molecular
Genetic Variation
Anti-Bacterial Agents/pharmacology
Drug Resistance, Bacterial/genetics
Plasmids/genetics
Genomics
Virulence Factors/genetics

@article {pmid39969228,
year = {2025},
author = {Adeniji, AA and Chukwuneme, CF and Conceição, EC and Ayangbenro, AS and Wilkinson, E and Maasdorp, E and de Oliveira, T and Babalola, OO},
title = {Unveiling novel features and phylogenomic assessment of indigenous Priestia megaterium AB-S79 using comparative genomics.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0146624},
doi = {10.1128/spectrum.01466-24},
pmid = {39969228},
issn = {2165-0497},
abstract = {UNLABELLED: Priestia megaterium strain AB-S79 isolated from active gold mine soil previously expressed in vitro heavy metal resistance and has a 5.7 Mb genome useful for biotechnological exploitation. This study used web-based bioinformatic resources to analyze P. megaterium AB-S79 genomic relatedness, decipher its secondary metabolite biosynthetic gene clusters (BGCs), and better comprehend its taxa. Genes were highly conserved across the 14 P. megaterium genomes examined here. The pangenome reflected a total of 61,397 protein-coding genes, 59,745 homolog protein family hits, and 1,652 singleton protein family hits. There were also 7,735 protein families, including 1,653 singleton families and 6,082 homolog families. OrthoVenn3 comparison of AB-S79 protein sequences with 13 other P. megaterium strains, 7 other Priestia spp., and 6 other Bacillus spp. highlighted AB-S79's unique genomic and evolutionary trait. antiSMASH identified two key transcription factor binding site regulators in AB-S79's genome: zinc-responsive repressor (Zur) and antibiotic production activator (AbrC3), plus putative enzymes for the biosynthesis of terpenes and ranthipeptides. AB-S79 also harbors BGCs for two unique siderophores (synechobactins and schizokinens), phosphonate, dienelactone hydrolase family protein, and phenazine biosynthesis protein (phzF), which is significant for this study. Phosphonate particularly showed specificity for the P. megaterium sp. validating the effect of gene family expansion and contraction. P. megaterium AB-S79 looks to be a viable source for value-added compounds. Thus, this study contributes to the theoretical framework for the systematic metabolic and genetic exploitation of the P. megaterium sp., particularly the value-yielding strains.

IMPORTANCE: This study explores microbial natural product discovery using genome mining, focusing on Priestia megaterium. Key findings highlight the potential of P. megaterium, particularly strain AB-S79, for biotechnological applications. The research shows a limited output of P. megaterium genome sequences from Africa, emphasizing the importance of the native strain AB-S79. Additionally, the study underlines the strain's diverse metabolic capabilities, reinforcing its suitability as a model for microbial cell factories and its foundational role in future biotechnological exploitation.},
}

@article {pmid39969192,
year = {2025},
author = {Haro-Moreno, JM and López-Pérez, M and Molina-Pardines, C and Rodriguez-Valera, F},
title = {Large diversity in the O-chain biosynthetic cluster within populations of Pelagibacterales.},
journal = {mBio},
volume = {},
number = {},
pages = {e0345524},
doi = {10.1128/mbio.03455-24},
pmid = {39969192},
issn = {2150-7511},
abstract = {Genomic diversity in prokaryotic species is largely due to the existence of extensive pangenomes, allowing different gene complements to be drawn depending on the strain. Here, we have studied the diversity of the O-chain polysaccharide biosynthesis cluster (OBC) in marine bacteria of the Pelagibacterales order as a proxy to measure such genetic diversity in a single population. The study of single-amplified genomes (SAGs) from the whole order found a pattern similar to that of other well-studied microbes, such as the Enterobacteriales or Alteromonas, where distinct OBCs represent strains containing different gene pools. We found that most of the OBC sharing happened among individuals of the same clonal frame (>99% average nucleotide identity). Moreover, given the parsimonious way this cluster changes, the diversity of the OBCs can be extrapolated to the size of the population's pangenome. This assumes that different OBCs correspond to lineages containing unique flexible gene pools, as seen in the aforementioned microbes. Through long-read metagenomics, we could detect 380 different OBCs at a single Mediterranean sampling site. Within a single population (single species and sample) of the endemic Ia.3/VII (gMED) genomospecies, we identified 158 OBCs, of which 130 were unique. These findings suggest that the gene pool within a single population might be substantial (several thousands). While this figure is large, it aligns with the complexity of the dissolved organic matter that these organisms can potentially degrade.IMPORTANCEDifferent strains of the same bacterial species contain very different gene pools. This has been long known by epidemiologists. However, it is unknown what gene pool is present in a single set of environmental conditions, i.e., the same time and place in free-living bacteria. Here, we have leveraged information from SAGs to analyze the diversity of the gene cluster coding for the O-chain polysaccharide, a typical component of the flexible gene pool classically used as a tool to differentiate strains in clinical microbiology. It evolves at a similar rate to the rest of the genome and does not seem to be affected by an arms race with phages. One single species of Pelagibacteriales (gMED) revealed an astounding diversity in one sample studied by long-read metagenomics. Our results point to a large gene pool (local pangenome) present in a single population, which is critical to interpreting the biological meaning of the pangenome, i.e., it provides intrapopulation diversity rather than characterizing strains with different distribution in time and/or space.},
}

@article {pmid39966674,
year = {2025},
author = {Mondol, SM and Hossain, MA and Haque, FKM},
title = {Comprehensive genomic insights into a highly pathogenic clone ST656 of mcr8.1 containing multidrug-resistant Klebsiella pneumoniae from Bangladesh.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {5909},
pmid = {39966674},
issn = {2045-2322},
mesh = {*Klebsiella pneumoniae/genetics/drug effects/pathogenicity ; Bangladesh ; *Drug Resistance, Multiple, Bacterial/genetics ; *Genome, Bacterial ; *Anti-Bacterial Agents/pharmacology ; Whole Genome Sequencing ; Humans ; Genomics/methods ; Klebsiella Infections/microbiology ; Virulence Factors/genetics ; Microbial Sensitivity Tests ; Plasmids/genetics ; Colistin/pharmacology ; },
abstract = {Antimicrobial resistance (AMR) is a pressing global health issue, intensified by the spread of resistant pathogens like Klebsiella pneumoniae (K. pneumoniae), which frequently causes hospital-acquired infections. This study focuses on a multidrug-resistant K. pneumoniae sequence type (ST) 656 strain, isolated from canal water in Bangladesh. Whole-genome sequencing and comparative genomic analysis revealed extensive resistance mechanisms and genetic elements underlying its adaptability. The strain exhibited resistance to colistin and multiple β-lactam antibiotics, containing key resistance genes such as mcr8.1, blaLAP-2, blaTEM-1, blaSHV-11 and blaOXA-1, alongside genes for copper, zinc, and silver resistance, indicating survival capability in metal-rich environments. Virulence factor analysis identified genes supporting adhesion, biofilm formation, and immune evasion, amplifying its pathogenic potential. Plasmid and phage analyses revealed mobile genetic elements, highlighting the role of horizontal gene transfer in AMR dissemination. The study included a pangenome analysis using a dataset of 32 publicly available K. pneumoniae sequence type (ST) 656 genomes, demonstrating evidence of an expanding pangenome for K. pneumoniae ST656. This study emphasized the role of environmental sources in AMR spread and the importance of continued surveillance, particularly in settings with intensive antibiotic usage, to mitigate the spread of high-risk, multidrug-resistant clones like K. pneumoniae ST656.},
}

*Klebsiella pneumoniae/genetics/drug effects/pathogenicity
Bangladesh
*Drug Resistance, Multiple, Bacterial/genetics
*Genome, Bacterial
*Anti-Bacterial Agents/pharmacology
Whole Genome Sequencing
Humans
Genomics/methods
Klebsiella Infections/microbiology
Virulence Factors/genetics
Microbial Sensitivity Tests
Plasmids/genetics
Colistin/pharmacology

@article {pmid39966226,
year = {2025},
author = {Bach, E and Ritter, AC and Silveira, RD and de Souza, MÁ and Passaglia, LMP and Welke, JE and Brandelli, A},
title = {Pangenome analysis of Bacillus velezensis exploring the probiotic potential and plant growth promotion traits of strains isolated from fish intestines.},
journal = {Molecular genetics and genomics : MGG},
volume = {300},
number = {1},
pages = {20},
pmid = {39966226},
issn = {1617-4623},
support = {308880/2021-8//Conselho Nacional de Desenvolvimento Científico e Tecnológico/ ; 304886/2022-0//Conselho Nacional de Desenvolvimento Científico e Tecnológico/ ; 23/2551-0001876-4//Fundação de Apoio à Pesquisa do Rio Grande do Norte/ ; },
mesh = {*Probiotics ; *Bacillus/genetics/isolation & purification ; *Genome, Bacterial/genetics ; Animals ; *Intestines/microbiology ; *Fishes/microbiology ; Plant Development ; Phylogeny ; },
abstract = {New Bacillus velezensis strains with impressive antimicrobial activities are being continuously described. Here we performed genomic comparisons of five B. velezensis strains isolated from Amazonian fish intestines with other 266 genomes from the RefSeq database through a pangenome approach. We aimed to analyze the commonalities and specificities of each strain within this clade to explore their potential as probiotics and for promoting plant growth (PGP). High-quality draft genome sequences were obtained for strains P7 and P11, with genome metrics confirming their identification as B. velezensis. The evaluation of 271 B. velezensis genome sequences revealed an open pangenome composed of 14,918 homologs, while 16% of them represented the core genome. Therefore, the majority of genes belonged to the accessory variable genome, with many strains harboring numerous unique genes, including the Amazonian strain P45. This strain also stood out as carrying the potential to produce many hydrolytic enzymes and PGP traits. Genome mining of all five Amazonian strains annotated secondary metabolites with unknown identifications. The evaluated probiotic genes are mostly conserved in all B. velezensis strains. Moreover, the investigation of the mobilome, resistome, and virulence factors showed that these strains can be considered safe for probiotic and agricultural applications, corroborating our previous studies. This data will be useful to improve our understanding and biotechnological exploration of these strains and other B. velezensis as well.},
}

*Probiotics
*Bacillus/genetics/isolation & purification
*Genome, Bacterial/genetics
Animals
*Intestines/microbiology
*Fishes/microbiology
Plant Development
Phylogeny

@article {pmid39962240,
year = {2025},
author = {Beaulieu, C and Libourel, C and Mbadinga Zamar, DL and El Mahboubi, K and Hoey, DJ and Greiff, GRL and Keller, J and Girou, C and San Clemente, H and Diop, I and Amblard, E and Castel, B and Théron, A and Cauet, S and Rodde, N and Zachgo, S and Halpape, W and Meierhenrich, A and Laker, B and Bräutigam, A and , and Szovenyi, P and Cheng, S and Tanizawa, Y and Aziz, S and Leebens-Mack, JH and Schmutz, J and Webber, J and Grimwood, J and Jacquet, C and Dunand, C and Nelson, JM and Roux, F and Philippe, H and Schornack, S and Bonhomme, M and Delaux, PM},
title = {The Marchantia polymorpha pangenome reveals ancient mechanisms of plant adaptation to the environment.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {39962240},
issn = {1546-1718},
support = {ANR-10-LABX-41//Agence Nationale de la Recherche (French National Research Agency)/ ; ANR-21-CE20-0010-01//Agence Nationale de la Recherche (French National Research Agency)/ ; ANR-21-CE20-0010-01//Agence Nationale de la Recherche (French National Research Agency)/ ; 32022006//National Natural Science Foundation of China (National Science Foundation of China)/ ; },
abstract = {Plant adaptation to terrestrial life started 450 million years ago and has played a major role in the evolution of life on Earth. The genetic mechanisms allowing this adaptation to a diversity of terrestrial constraints have been mostly studied by focusing on flowering plants. Here, we gathered a collection of 133 accessions of the model bryophyte Marchantia polymorpha and studied its intraspecific diversity using selection signature analyses, a genome-environment association study and a pangenome. We identified adaptive features, such as peroxidases or nucleotide-binding and leucine-rich repeats (NLRs), also observed in flowering plants, likely inherited from the first land plants. The M. polymorpha pangenome also harbors lineage-specific accessory genes absent from seed plants. We conclude that different land plant lineages still share many elements from the genetic toolkit evolved by their most recent common ancestor to adapt to the terrestrial habitat, refined by lineage-specific polymorphisms and gene family evolution.},
}

@article {pmid39962090,
year = {2025},
author = {Liu, X and Zhang, M and Zhao, X and Shen, M and Feng, R and Wei, Q},
title = {The evolution, variation and expression patterns of the annexin gene family in the maize pan-genome.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {5711},
pmid = {39962090},
issn = {2045-2322},
support = {2023QH17//Yibin University Research Projects/ ; H72313004//Yibin Agricultural Science and Technology Innovation Project/ ; },
mesh = {*Zea mays/genetics/metabolism ; *Annexins/genetics/metabolism ; *Gene Expression Regulation, Plant ; *Genome, Plant ; *Phylogeny ; *Evolution, Molecular ; *Multigene Family ; *Plant Proteins/genetics/metabolism ; Gene Expression Profiling ; Stress, Physiological/genetics ; Transcriptome ; },
abstract = {Annexins (Anns) are a family of evolutionarily conserved, calcium-dependent, phospholipid-binding proteins that play critical roles in plant growth, development, and stress responses. Utilizing the pan-genome of 26 high-quality maize genomes, we identified 12 Ann genes, comprising 9 core genes (present in all 26 lines) and 3 near-core genes (present in 24-25 lines). This highlights the limitations of studying ZmAnn genes based on a single reference genome. Evaluating the Ka/Ks values of Ann genes in 26 varieties revealed that ZmAnn10 was under positive selection in certain varieties, while the remaining genes had Ka/Ks values less than 1, indicating purifying selection. Phylogenetic analysis divided ZmAnn proteins into six groups, with group VI containing only ZmAnn12. Structural variation in certain varieties altered the conserved domains, generating many atypical genes. Transcriptome analysis showed that different Ann members have distinct expression patterns in various tissues and under different abiotic and biotic stress treatments. Weighted gene co-expression network analysis of transcriptome data from various maize tissues under cold stress identified four Ann genes (ZmAnn2, ZmAnn6, ZmAnn7, ZmAnn9) involved in co-expression modules. Overall, this study utilized high-quality maize pangenomes to perform a bioinformatic analysis of ZmAnn genes, providing a foundation for further research on ZmAnn genes.},
}

*Zea mays/genetics/metabolism
*Annexins/genetics/metabolism
*Gene Expression Regulation, Plant
*Genome, Plant
*Phylogeny
*Evolution, Molecular
*Multigene Family
*Plant Proteins/genetics/metabolism
Gene Expression Profiling
Stress, Physiological/genetics
Transcriptome

@article {pmid39956730,
year = {2025},
author = {Sari, RF and Fadilah, F and Maladan, Y and Sarassari, R and Khoeri, MM and Harimurti, K and Alimsardjono, L and Safari, D},
title = {An insight of Streptococcus pneumoniae serotype 3 genomic profile in Indonesia.},
journal = {Journal of microbiology, immunology, and infection = Wei mian yu gan ran za zhi},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jmii.2025.01.007},
pmid = {39956730},
issn = {1995-9133},
abstract = {BACKGROUND: Streptococcus pneumoniae Serotype 3 (SPN3) remains a significant cause of morbidity and mortality worldwide despite of pneumococcal conjugate vaccine (PCV) implementation. We explored genomic profile of SPN3 from children and adult groups to understand population structure and evolution dynamics of SPN3 in Indonesia.

METHODS: We undertook whole genome sequencing (WGS) from 19 isolates of SPN3 in Indonesia between 2017 and 2021 prior to PCV introduction. This study assessed sequence types (STs), global pneumococcal sequence cluster (GPSC), genome prediction of antimicrobial resistance (AMR) profile, pangenome analysis, phylogenetic tree, and genome comparative of capsular polysaccharide (cps) locus.

RESULTS: We identified ST451-GPSC234 (n = 5) and ST180-GPSC12 (n = 4), ST458-GPSC51 (n = 2), ST3805-GPSC12 (n = 2), ST4909-GPSC363 (n = 2), ST700-GPSC10 (n = 1), ST5292-GPSC309 (n = 1), ST505-GPSC12 (n = 1), and ST4233 (n = 1). Genome prediction of AMR discover isolates were resistant to tetracycline (n = 5); co-resistant of chloramphenicol and tetracycline (n = 2); co-trimoxazole and tetracycline (n = 1). We observed SPN3 possess closed pangenome characteristic, indicates more stable genetic repertoire. We found 5 absent genes in cps locus including cpsABCD and tnp in ST700-GPSC10 lineage.

CONCLUSIONS: SPN3 has potential genomic profile to enhance the ability of this strain to endure selective pressure such as PCV introduction.},
}

@article {pmid39954531,
year = {2025},
author = {Wang, S and Li, X and Zheng, C and Quereda, JJ and Sun, J and Yao, H and Wu, Z},
title = {Genomic characteristics and antimicrobial resistance of the underreported zoonotic pathogen Streptococcus pasteurianus and its co-colonization with Streptococcus suis.},
journal = {Veterinary microbiology},
volume = {303},
number = {},
pages = {110428},
doi = {10.1016/j.vetmic.2025.110428},
pmid = {39954531},
issn = {1873-2542},
abstract = {Streptococcus pasteurianus is an opportunistic pathogen affecting various animals and is an underreported zoonotic threat. It is also a causative agent of swine streptococcosis and can be co-detected with Streptococcus suis, another significant pig and zoonotic pathogen. However, the dynamics of co-colonization between these pathogens, along with the genomic features and antibiotic resistance profiles of S. pasteurianus, remain poorly understood. In this study, we developed a multiplex PCR (mPCR) assay to detect S. pasteurianus and S. suis in 827 tonsil samples from healthy pigs, with 81 samples positive for both pathogens. Pan-genome analysis revealed an open pan-genome, indicating an adaptable genome. Antibiotic resistance gene analysis identified 21 distinct genes, including the first identification of mef(A), msr(D), optrA, lnu(G), spw, dfrF, and fexA in S. pasteurianus. Strain WUSP082 carried 15 resistance genes, many of which were located on mobile genetic elements. ICEWUSP082-1 carries tet(O), erm(B), and ant(6)-Ia, showing 99.10 % sequence similarity to S. suis ICESsuZJ20091101-1. GIWUSP082-1, containing tet(L) and tet(M), shares 99.94 % similarity with S. suis 89-kb pathogenicity island. PlasmidWUSP082, carrying fexA, optrA, and erm(A), shares 98.85 % sequence homology with Enterococcus faecium plasmid pW6-2. All 15 strains collected from our lab displayed multidrug resistance, being resistant to at least four classes of antibiotics. Mouse infection experiments demonstrated the pathogenic potential of WUSP082, isolated from the tonsil of a healthy pig. This study advances our understanding of the genomic characteristics and antimicrobial resistance of S. pasteurianus, offering valuable insights for the surveillance and management of this under-recognized zoonotic pathogen.},
}

@article {pmid39952999,
year = {2025},
author = {Koper, P and Wysokiński, J and Żebracki, K and Decewicz, P and Dziewit, Ł and Kalita, M and Palusińska-Szysz, M and Mazur, A},
title = {Comparative analysis of Legionella lytica genome identifies specific metabolic traits and virulence factors.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {5554},
pmid = {39952999},
issn = {2045-2322},
support = {2019/03/X/NZ2/00976//Narodowe Centrum Nauki/ ; 2019/03/X/NZ2/00976//Narodowe Centrum Nauki/ ; 2019/03/X/NZ2/00976//Narodowe Centrum Nauki/ ; 2019/03/X/NZ2/00976//Narodowe Centrum Nauki/ ; 2019/03/X/NZ2/00976//Narodowe Centrum Nauki/ ; 2019/03/X/NZ2/00976//Narodowe Centrum Nauki/ ; },
mesh = {*Virulence Factors/genetics ; *Legionella/genetics/pathogenicity ; *Genome, Bacterial ; Plasmids/genetics ; Phylogeny ; Bacterial Proteins/genetics/metabolism ; Virulence/genetics ; Molecular Sequence Annotation ; },
abstract = {The complete genome of Legionella lytica PCM 2298 was sequenced and analyzed to provide insights into its genomic structure, virulence potential, and evolutionary position within the Legionella genus. The genome comprised a 3.2 Mbp chromosome and two plasmids, pLlyPCM2298_1 and pLlyPCM2298_2, contributing to a total genome size of 3.7 Mbp. Functional annotation identified 3,165 coding sequences, including genes associated with known virulence factors such as the major outer membrane protein (MOMP), the macrophage infectivity potentiator (Mip), and a comprehensive set of secretion systems (type II, type IVA, and type IVB Dot/Icm type IV secretion system). Notably, L. lytica contributed 383 unique genes to the Legionella pangenome, with 232 identified effector proteins, of which 35 were plasmid-encoded. The identification of unique genes, particularly those on plasmids, suggests an evolutionary strategy favoring horizontal gene transfer and niche adaptation. The effector repertoire included proteins with domains characteristic of host interaction strategies, such as ankyrin repeats and protein kinases. Comparative analyses showed that while L. lytica shares core virulence traits with other Legionella species, it has distinct features that may contribute to its adaptability and pathogenic potential. These findings underscore the genomic diversity within the genus and contribute to a deeper understanding of Legionella's ecological and clinical significance. A custom web application was developed using the R Shiny library, enabling users to interactively explore the expanded Legionella pangenome through UpSet plots.},
}

*Virulence Factors/genetics
*Legionella/genetics/pathogenicity
*Genome, Bacterial
Plasmids/genetics
Phylogeny
Bacterial Proteins/genetics/metabolism
Virulence/genetics
Molecular Sequence Annotation

@article {pmid39951298,
year = {2025},
author = {Liu, J and Kang, M and Wei, Y and Zhang, Z and Pang, J and Chen, Q and Xu, X and Wei, Z and Zhang, Y and Chen, K and Wang, Z and Lu, X and Liang, Q},
title = {kexB Gene Correlates With Aspergillus flavus Keratitis Severity: A Whole-Genome Analysis.},
journal = {Investigative ophthalmology & visual science},
volume = {66},
number = {2},
pages = {42},
pmid = {39951298},
issn = {1552-5783},
mesh = {*Aspergillus flavus/genetics ; Animals ; Mice ; *Eye Infections, Fungal/microbiology ; *Whole Genome Sequencing ; *Aspergillosis/microbiology ; *Disease Models, Animal ; *Keratitis/microbiology ; Virulence/genetics ; *Fungal Proteins/genetics ; Female ; Cornea/microbiology/pathology ; Mice, Inbred BALB C ; Mutation ; Humans ; Genome, Fungal ; },
abstract = {PURPOSE: Fungal keratitis caused by Aspergillus flavus (A. flavus) can result in severe inflammation and corneal stromal melting, leading to visual impairment. This study aimed to identify virulent genes correlated with the severity of A. flavus keratitis using whole-genome sequencing.

METHODS: Whole-genome sequencing of 21 clinical A. flavus strains from cornea was performed to elucidate the pathogenesis of A. flavus in infectious keratitis, followed by pan-genome analysis and virulence analysis. To further understand the results from the previous analyses, growth phenotypes and virulence effect of mutant strains were validated experimentally, including the spore counting, growth pattern under different conditions, and clinical and pathological evaluation of A. flavus keratitis in mice models.

RESULTS: The A. flavus pan-genome was composed of 17,326 gene clusters with a core genome of 5378 (31.0% of the pan-genome) orthogroups in all 21 isolates. Virulence gene analysis revealed 183 genes contributing to A. flavus pathogenesis and mutation of the kexB gene was associated with the severity of keratitis. The kexB mutant (ΔkexB) strains showed significantly reduced conidia formation and lower growth rates in the presence of the cell-wall perturbing agents. Further, the mice models validated that clinical score, and corneal perforation rates significantly decreased in the group infected by ΔkexB strains. Infiltration of immune cells, gene expression of cytokines, and matrix metalloproteinase (MMP) were also decreased in the mutant group.

CONCLUSIONS: The role of kexB gene in A. flavus keratitis was identified through whole-genome sequencing. Its mutation impairs conidia formation, cell wall integrity, and invasion, leading to milder clinical symptoms.},
}

*Aspergillus flavus/genetics
Animals
Mice
*Eye Infections, Fungal/microbiology
*Whole Genome Sequencing
*Aspergillosis/microbiology
*Disease Models, Animal
*Keratitis/microbiology
Virulence/genetics
*Fungal Proteins/genetics
Female
Cornea/microbiology/pathology
Mice, Inbred BALB C
Mutation
Humans
Genome, Fungal

@article {pmid39944816,
year = {2024},
author = {Ruzanova, VS and Oshikhmina, SG and Proskurina, AS and Ritter, GS and Kirikovich, SS and Levites, EV and Efremov, YR and Karamysheva, TV and Meschaninova, MI and Mamaev, AL and Taranov, OS and Bogachev, AS and Sidorov, SV and Nikonov, SD and Leplina, OY and Ostanin, AA and Chernykh, ER and Kolchanov, NA and Dolgova, EV and Bogachev, SS},
title = {A concept of natural genome reconstruction.Part 2. Effect of extracellular double-stranded DNA fragments on hematopoietic stem cells.},
journal = {Vavilovskii zhurnal genetiki i selektsii},
volume = {28},
number = {8},
pages = {993-1007},
doi = {10.18699/vjgb-24-106},
pmid = {39944816},
issn = {2500-0462},
abstract = {In this part of the study, the first component of the concept of "natural genome reconstruction" is being proven. It was shown with mouse and human model organisms that CD34+ hematopoietic bone marrow progenitors take up fragments of extracellular double-stranded DNA through a natural mechanism. It is known that the process of internalization of extracellular DNA fragments involves glycocalyx structures, which include glycoproteins/protein glycans, glycosylphosphatidylinositol-anchored proteins and scavenger receptors. The bioinformatic analysis conducted indicates that the main surface marker proteins of hematopoietic stem cells belong to the indicated groups of factors and contain specific DNA binding sites, including a heparin-binding domain and clusters of positively charged amino acid residues. A direct interaction of CD34 and CD84 (SLAMF5) glycoproteins, markers of hematopoietic stem cells, with double-stranded DNA fragments was demonstrated using an electrophoretic mobility shift assay system. In cells negative for CD34, which also internalize fragments, concatemerization of the fragments delivered into the cell occurs. In this case, up to five oligonucleotide monomers containing 9 telomeric TTAGGG repeats are stitched together into one structure. Extracellular fragments delivered to hematopoietic stem cells initiate division of the original hematopoietic stem cell in such a way that one of the daughter cells becomes committed to terminal differentiation, and the second retains its low-differentiated status. After treatment of bone marrow cells with hDNAgr, the number of CD34+ cells in the colonies increases to 3 % (humans as the model organism). At the same time, treatment with hDNAgr induces proliferation of blood stem cells and their immediate descendants and stimulates colony formation (mouse, rat and humans as the model organisms). Most often, the granulocyte-macrophage lineage of hematopoiesis is activated as a result of processing extracellular double-stranded DNA. The commitment process is manifested by the appearance and repair of pangenomic single-strand breaks. The transition time in the direction of differentiation (the time it takes for pangenomic single-strand breaks to appear and to be repaired) is about 7 days. It is assumed that at the moment of initiation of pangenomic single-strand breaks, a "recombinogenic situation" ensues in the cell and molecular repair and recombination mechanisms are activated. In all experiments with individual molecules, recombinant human angiogenin was used as a comparison factor. In all other experiments, one of the experimental groups consisted of hematopoietic stem cells treated with angiogenin.},
}

@article {pmid39943872,
year = {2025},
author = {Büttner, KA and Bregy, V and Wegner, F and Purushothaman, S and Imkamp, F and Roloff Handschin, T and Puolakkainen, MH and Hiltunen-Back, E and Braun, D and Kisakesen, I and Schreiber, A and Entrocassi, AC and Gallo Vaulet, ML and López Aquino, D and Svidler López, L and La Rosa, L and Egli, A and Rodríguez Fermepin, M and Seth-Smith, HM and On Behalf Of The Escmid Study Group For Mycoplasma And Chlamydia Infections Esgmac, },
title = {Evaluating methods for genome sequencing of Chlamydia trachomatis and other sexually transmitted bacteria directly from clinical swabs.},
journal = {Microbial genomics},
volume = {11},
number = {2},
pages = {},
doi = {10.1099/mgen.0.001353},
pmid = {39943872},
issn = {2057-5858},
mesh = {Humans ; *Chlamydia trachomatis/genetics/isolation & purification ; *Whole Genome Sequencing/methods ; *Genome, Bacterial ; Neisseria gonorrhoeae/genetics/isolation & purification/classification ; High-Throughput Nucleotide Sequencing ; Treponema pallidum/genetics/isolation & purification ; Sexually Transmitted Diseases, Bacterial/microbiology ; Switzerland ; DNA, Bacterial/genetics ; Mycoplasma genitalium/genetics/isolation & purification ; Chlamydia Infections/microbiology ; },
abstract = {Rates of bacterial sexually transmitted infections (STIs) are rising, and accessing their genomes provides information on strain evolution, circulating strains and encoded antimicrobial resistance (AMR). Notable pathogens include Chlamydia trachomatis (CT), Neisseria gonorrhoeae (NG) and Treponema pallidum (TP), globally the most common bacterial STIs. Mycoplasmoides (formerly Mycoplasma) genitalium (MG) is also a bacterial STI that is of concern due to AMR development. These bacteria are also fastidious or hard to culture, and standard sampling methods lyse bacteria, completely preventing pathogen culture. Clinical samples contain large amounts of human and other microbiota DNA. These factors hinder the sequencing of bacterial STI genomes. We aimed to overcome these challenges in obtaining whole-genome sequences and evaluated four approaches using clinical samples from Argentina (39), and Switzerland (14), and cultured samples from Finland (2) and Argentina (1). First, direct genome sequencing from swab samples was attempted through Illumina deep metagenomic sequencing, showing extremely low levels of target DNA, with under 0.01% of the sequenced reads being from the target pathogens. Second, host DNA depletion followed by Illumina sequencing was not found to produce enrichment in these very low-load samples. Third, we tried a selective long-read approach with the new adaptive sequencing from Oxford Nanopore Technologies, which also did not improve enrichment sufficiently to provide genomic information. Finally, target enrichment using a novel pan-genome set of custom SureSelect probes targeting CT, NG, TP and MG followed by Illumina sequencing was successful. We produced whole genomes from 64% of CT-positive samples, from 36% of NG-positive samples and 60% of TP-positive samples. Additionally, we enriched MG DNA to gain partial genomes from 60% of samples. This is the first publication to date to utilize a pan-genome STI panel in target enrichment. Target enrichment, though costly, proved essential for obtaining genomic data from clinical samples. These data can be utilized to examine circulating strains and genotypic resistance and guide public health strategies.},
}

Humans
*Chlamydia trachomatis/genetics/isolation & purification
*Whole Genome Sequencing/methods
*Genome, Bacterial
Neisseria gonorrhoeae/genetics/isolation & purification/classification
High-Throughput Nucleotide Sequencing
Treponema pallidum/genetics/isolation & purification
Sexually Transmitted Diseases, Bacterial/microbiology
Switzerland
DNA, Bacterial/genetics
Mycoplasma genitalium/genetics/isolation & purification
Chlamydia Infections/microbiology

@article {pmid39940933,
year = {2025},
author = {Stack, GM and Quade, MA and Wilkerson, DG and Monserrate, LA and Bentz, PC and Carey, SB and Grimwood, J and Toth, JA and Crawford, S and Harkess, A and Smart, LB},
title = {Comparison of Recombination Rate, Reference Bias, and Unique Pangenomic Haplotypes in Cannabis sativa Using Seven De Novo Genome Assemblies.},
journal = {International journal of molecular sciences},
volume = {26},
number = {3},
pages = {},
pmid = {39940933},
issn = {1422-0067},
support = {CM04068//New York State Department of Agriculture and Markets/ ; 2239530//National Science Foundation/ ; 2023-67013-39620//United States Department of Agriculture/ ; 2022-67012-38987//United States Department of Agriculture/ ; },
mesh = {*Cannabis/genetics ; *Genome, Plant ; *Recombination, Genetic ; *Haplotypes ; Chromosome Mapping/methods ; Genomics/methods ; Genotype ; Chromosomes, Plant/genetics ; },
abstract = {Genomic characterization of Cannabis sativa has accelerated rapidly in the last decade as sequencing costs have decreased and public and private interest in the species has increased. Here, we present seven new chromosome-level haplotype-phased genomes of C. sativa. All of these genotypes were alive at the time of publication, and several have numerous years of associated phenotype data. We performed a k-mer-based pangenome analysis to contextualize these assemblies within over 200 existing assemblies. This allowed us to identify unique haplotypes and genomic diversity among Cannabis sativa genotypes. We leveraged linkage maps constructed from F2 progeny of two of the assembled genotypes to characterize the recombination rate across the genome showing strong periphery-biased recombination. Lastly, we re-aligned a bulk segregant analysis dataset for the major-effect flowering locus Early1 to several of the new assemblies to evaluate the impact of reference bias on the mapping results and narrow the locus to a smaller region of the chromosome. These new assemblies, combined with the continued propagation of the genotypes, will contribute to the growing body of genomic resources for C. sativa to accelerate future research efforts.},
}

*Cannabis/genetics
*Genome, Plant
*Recombination, Genetic
*Haplotypes
Chromosome Mapping/methods
Genomics/methods
Genotype
Chromosomes, Plant/genetics

@article {pmid39939499,
year = {2025},
author = {Liqi, Z and Yuanyuan, L and Linghan, Y and Jun, Y and Tao, W and Quan, Z},
title = {Genome and pathogenicity analysis of Helicobacter mastomyrinus isolated from mice.},
journal = {Archives of microbiology},
volume = {207},
number = {3},
pages = {55},
pmid = {39939499},
issn = {1432-072X},
support = {Project Number 4//the International Research Laboratory of Prevention and Control of Important Animal Infectious Diseases and Zoonotic Diseases of Jiangsu Higher Education Institutions/ ; YZ2024072//the Key Research and Development Program of Social Development of Yangzhou City/ ; 32273004//National Natural Science Foundation of China/ ; },
mesh = {Animals ; Mice ; *Helicobacter/genetics/isolation & purification/pathogenicity/classification ; *Helicobacter Infections/microbiology ; *Genome, Bacterial ; *Mice, Inbred C57BL ; *Phylogeny ; *Mice, Inbred BALB C ; RNA, Ribosomal, 16S/genetics ; Bacterial Toxins/genetics ; Liver/microbiology/pathology ; Virulence ; },
abstract = {The increasing attention given to the potential risk offered by enterohepatic Helicobacter species to the well-being of human beings and animals is of significant importance. Helicobacter mastomyrinus (H. mastomyrinus), a bacterium predominantly associated with rodents, has been implicated in liver and intestinal pathologies. Here, a strain of H. mastomyrinus, designated as Hm-17 (GenBank: CP145316.1), was isolated from asymptomatic C57BL/6 mice. Subsequently, an in-depth and comprehensive investigation was undertaken, which included genome sequencing analysis, micro-biochemical identification, evaluation of growth characteristic, cytotoxicity assessment, and testing of animal pathogenicity. The analysis of 16 S rRNA reveals a close phylogenetic relationship between H. mastomyrinus and H. canadensis. However, core-pan genome analysis and an evaluation of pathogenic factors indicates a more robust association between H. mastomyrinus and H. hepaticus. Cytotoxicity analysis revealed that Hm-17 exhibits robust cytolethal distending toxin (CDT) activity, inducing pronounced cellular swelling and death. Furthermore, Hm-17 infection in BALB/c mice results in rapid and characteristic focal necrotic hepatitis. Genome sequencing and pathogenicity analysis indicate that H. mastomyrinus isolates from asymptomatic mice possess significant pathogenic potential. These findings underscore the need for further investigation into the epidemiology and mechanisms of pathogenesis associated with this organism.},
}

Animals
Mice
*Helicobacter/genetics/isolation & purification/pathogenicity/classification
*Helicobacter Infections/microbiology
*Genome, Bacterial
*Mice, Inbred C57BL
*Phylogeny
*Mice, Inbred BALB C
RNA, Ribosomal, 16S/genetics
Bacterial Toxins/genetics
Liver/microbiology/pathology
Virulence

@article {pmid39939176,
year = {2025},
author = {Zhang, P and Wei, Y and Tian, Q and Zou, Q and Wang, Y},
title = {Fast sequence alignment for centromere with RaMA.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279763.124},
pmid = {39939176},
issn = {1549-5469},
abstract = {The release of the first draft of the human pangenome has revolutionized genomic research by enabling access to complex regions like centromeres, composed of extra-long tandem repeats (ETRs). However, a significant gap remains as current methodologies are inadequate for producing sequence alignments that effectively capture genetic events within ETRs, highlighting a pressing need for improved alignment tools. Inspired by UniAligner, we develope Rare Match Aligner (RaMA), using rare matches as anchors and 2-piece affine gap cost to generate complete pairwise alignment that better capture genetic evolution. RaMA also employs parallel computing and the wavefront algorithm to accelerate anchor discovery and sequence alignment, achieving up to 13.66 times faster processing and using only 11% of UniAligner's memory. Downstream analysis of simulated data and the CHM13 and CHM1 Higher Order Repeat (HOR) arrays demonstrates that RaMA achieves more accurate alignment, effectively capturing true HOR structures. RaMA also introduces two methods for defining reliable alignment regions, further refining and enhancing the accuracy of centromeric alignment statistics.},
}

@article {pmid39938413,
year = {2025},
author = {Collins, AM and Mizzi, R},
title = {Virulence determinants in Klebsiella pneumoniae associated with septicaemia outbreaks in neonatal pigs.},
journal = {Veterinary microbiology},
volume = {302},
number = {},
pages = {110409},
doi = {10.1016/j.vetmic.2025.110409},
pmid = {39938413},
issn = {1873-2542},
abstract = {Klebsiella pneumoniae is recognized as an opportunistic pathogen in pigs causing pneumonia, mastitis and diarrhoea, but can also cause mortalities due to septicaemia and meningitis in previously healthy piglets. This study aimed to identify virulence genes present in K. pneumoniae that caused outbreaks of septicaemia in neonatal pigs. The genomes of thirty-eight Australian K. pneumoniae isolates from pigs with septicaemia, meningitis, myocarditis, pneumonia, enteritis and healthy cohorts were sequenced. The presence of antimicrobial resistance, siderophore and enhanced capsule production genes were identified by sequence analysis and verified by either PCR or phenotypic tests. An additional 52 international K. pneumoniae genomes from healthy and clinically affected pigs (28), humans (16), birds (3), one rodent and environmental isolates (4) were included in a pangenome analysis. Porcine septicaemic K. pneumoniae genomes from the UK and Australia clustered together and had higher virulence scores than all other clinical and non-clinical isolates. Septicaemic isolates were predominantly ST25, had enhanced capsule polysaccharide production with K2 capsule type and contained genes for the siderophores aerobactin, salmochelin and yersiniabactin. Septicaemic K. pneumoniae were more likely to have genes encoding the assembly of LPS, fimbriae and adhesins, and enzymes needed for the integration of mobile genetic elements. No single virulence gene was solely associated with isolates causing septicaemia. These findings indicate that there may be genotypes associated with clinical disease outcomes for K. pneumoniae. In the absence of some virulence genes, K. pneumoniae was still able to cause significant disease if the pig's immune system was immature or compromised.},
}

@article {pmid39938192,
year = {2025},
author = {Aguilar-Zamora, E and Rodríguez, C and Torres, J and Ortiz-Olvera, N and Aparicio-Ozores, G and Flores-Luna, L and Quesada-Gómez, C and Camorlinga-Ponce, M},
title = {Predominance of FQR1 NAP1/RT027 Clostridioides difficile Among Mexican Children and Adult Patients, and its Resistance to Eleven Antibiotics.},
journal = {Archives of medical research},
volume = {56},
number = {4},
pages = {103171},
doi = {10.1016/j.arcmed.2024.103171},
pmid = {39938192},
issn = {1873-5487},
abstract = {AIMS: Clostridioides difficile is a major cause of antibiotic-associated diarrhea. This study investigated the diversity, clonality, and antimicrobial resistance of C. difficile isolates from Mexican children and adults with diarrhea.

METHODS: Between 2014 and 2016, we isolated 37 C. difficile strains in three hospitals in Mexico City. C. difficile strains were typed by PCR-ribotyping and pulsed-field gel electrophoresis (PFGE). Antimicrobial susceptibility to eleven antibiotics was determined. Whole-genome sequencing (WGS) was used to investigate the presence of antimicrobial resistance genes (ARG) and perform a pangenome analysis of 53 genomes from Mexico and 137 publicly available C. difficile genomes.

RESULTS: Toxigenic strains comprised six isolates from children and 31 from adults. While NAP1/RT027 isolates were found in three children, they were predominant in adults (n = 31, 90.3 %) and showed the 1058 and 008 PFGE macrorestriction patterns. All isolates were susceptible to vancomycin and metronidazole but resistant to ciprofloxacin, and over 90 % of the isolates were resistant to linezolid and carried cfr(E). The pangenome of these isolates contained 4,852 genes, of which 3,455 (81.2 %) were categorized as core genes and 801 (18.8 %) as accessory genes. In addition, our isolates demonstrated a close relationship with strains from the United States, Canada, and France.

CONCLUSIONS: Our work provides, for the first time, genomic insights into C. difficile strains present in Mexico. In our hospital setting, the predominant strains were primarily NAP1/RT027 and exhibited resistance to linezolid, a pattern observed in both pediatric and adult populations. This unique combination of characteristics has not been previously reported in Latin America.},
}

@article {pmid39936904,
year = {2025},
author = {Lupo, V and Roomans, C and Royen, E and Ongena, L and Jacquemin, O and Mullender, C and Kerff, F and Baurain, D},
title = {Identification and characterization of archaeal pseudomurein biosynthesis genes through pangenomics.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0140124},
doi = {10.1128/msystems.01401-24},
pmid = {39936904},
issn = {2379-5077},
abstract = {The peptidoglycan (PG, or murein) is a mesh-like structure, which is made of glycan polymers connected by short peptides and surrounds the cell membrane of nearly all bacterial species. In contrast, there is no PG counterpart that would be universally found in Archaea but rather various polymers that are specific to some lineages. Methanopyrales and Methanobacteriales are two orders of Euryarchaeota that harbor pseudomurein (PM), a structural analog of the bacterial PG. Owing to the differences between PG and PM biosynthesis, some have argued that the origin of both polymers is not connected. However, recent studies have revealed that the genomes of PM-containing Archaea encode homologs of the bacterial genes involved in PG biosynthesis, even though neither their specific functions nor the relationships within the corresponding inter-domain phylogenies have been investigated so far. In this work, we devised a pangenomic bioinformatic pipeline to identify proteins for PM biosynthesis in Archaea without prior genetic knowledge. The taxonomic distribution and evolutionary relationships of the candidate proteins were studied in detail in Archaea and Bacteria through HMM sequence mining and phylogenetic inference of the Mur domain-containing family, the ATP-grasp superfamily, and the MraY-like family. Our results show that archaeal muramyl ligases are of bacterial origin but diversified through a mixture of horizontal gene transfers and gene duplications. However, in the ATP-grasp and MraY-like families, the archaeal members were not found to originate from Bacteria. Our pangenomic approach further identified five new genes potentially involved in PM synthesis and that would deserve functional characterization.IMPORTANCEMethanobrevibacter smithii is an archaea commonly found in the human gut, but its presence alongside pathogenic bacteria during infections has led some researchers to consider it as an opportunistic pathogen. Fortunately, endoisopeptidases isolated from phages, such as PeiW and PeiP, can cleave the cell walls of M. smithii and other pseudomurein-containing archaea. However, additional research is required to identify effective anti-archaeal agents to combat these opportunistic microorganisms. A better understanding of the pseudomurein cell wall and its biosynthesis is necessary to achieve this goal. Our study sheds light on the origin of cell wall structures in those microorganisms, showing that the archaeal muramyl ligases responsible for its formation have bacterial origins. This discovery challenges the conventional view of the cell-wall architecture in the last archaeal common ancestor and shows that the distinction between "common origin" and "convergent evolution" can be blurred in some cases.},
}

@article {pmid39935480,
year = {2025},
author = {Guo, W and Wang, X and Hu, J and Zhang, B and Zhao, L and Zhang, G and Qi, J and Wei, Z and Bao, Y and Tian, M and Wang, S},
title = {In silico design of a multi-epitope vaccine against Mycobacterium avium subspecies paratuberculosis.},
journal = {Frontiers in immunology},
volume = {16},
number = {},
pages = {1505313},
pmid = {39935480},
issn = {1664-3224},
mesh = {*Mycobacterium avium subsp. paratuberculosis/immunology ; *Epitopes, B-Lymphocyte/immunology ; *Epitopes, T-Lymphocyte/immunology ; *Bacterial Vaccines/immunology ; *Paratuberculosis/immunology/prevention & control ; *Molecular Docking Simulation ; *Molecular Dynamics Simulation ; Animals ; Computer Simulation ; Antigens, Bacterial/immunology/genetics/chemistry ; Toll-Like Receptor 4/immunology ; },
abstract = {The widespread chronic enteritis known as Paratuberculosis (PTB) or Johne's disease (JD) is caused by Mycobacterium avium subspecies paratuberculosis (MAP), posing a significant threat to global public health. Given the challenges associated with PTB or JD, the development and application of vaccines are potentially important for disease control. The aim of this study was to design a multi-epitope vaccine against MAP. A total of 198 MAP genomes were analyzed using pan-genome and reverse vaccinology approaches. B-cell and T-cell epitope analysis was performed on the selected promising cross-protective antigens followed by selection of epitopes with high antigenicity, no allergenicity, and no toxicity for the design of the vaccine. The designed vaccine was evaluated through molecular dynamics simulations, molecular docking, and immunological simulations. The results revealed the identification of five promising cross-protective antigens. In total, 10 B-cell epitopes, 10 HTL epitopes, and 9 CTL epitopes were selected for the design of the vaccine. Both the vaccine candidate and the vaccine-TLR4 complex demonstrated considerable stability in molecular dynamics simulations. Molecular docking studies confirmed that the vaccine candidate successfully interacted with TLR4. Immunological simulations showed an increase in both B-cell and T-cell populations after vaccination. Additionally, the vaccine candidate exhibited a codon adaptability index of 1.0 and a GC content of 53.64%, indicating strong potential for successful expression in Escherichia coli. This research developed a multi-epitope vaccine targeting MAP through pan-genomes and reverse vaccinology methods, offering innovative strategies for creating effective vaccines against MAP.},
}

*Mycobacterium avium subsp. paratuberculosis/immunology
*Epitopes, B-Lymphocyte/immunology
*Epitopes, T-Lymphocyte/immunology
*Bacterial Vaccines/immunology
*Paratuberculosis/immunology/prevention & control
*Molecular Docking Simulation
*Molecular Dynamics Simulation
Animals
Computer Simulation
Antigens, Bacterial/immunology/genetics/chemistry
Toll-Like Receptor 4/immunology

@article {pmid39933516,
year = {2025},
author = {Paauw, M and Schravesande, WEW and Taks, NW and Rep, M and Pfeilmeier, S and van den Burg, HA},
title = {Evolution of a vascular plant pathogen is associated with the loss of CRISPR-Cas and an increase in genome plasticity and virulence genes.},
journal = {Current biology : CB},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.cub.2025.01.003},
pmid = {39933516},
issn = {1879-0445},
abstract = {A major question in infectious disease research is how bacteria have evolved into highly niche-adapted pathogens with efficient host infection strategies. The plant pathogenic bacterium Xanthomonas campestris is subdivided into pathovars that occupy two distinct niches of the same plant leaf: the vasculature and the mesophyll tissue. Using a pangenome comparison of 94 X. campestris isolates, we discovered that the vasculature-infecting pathovar emerged in one monophyletic clade, has lost its CRISPR-Cas system, and showed an increase in both genomic plasticity and acquisition of virulence factors, such as type III effector proteins, compared with the ancestral pathovar. In addition, we show that the CRISPR spacers of isolates belonging to the ancestral pathovar map to plasmids that circulate in Xanthomonas populations and encode high numbers of transposons and virulence factors, suggesting that CRISPR-Cas restricts gene flow toward this pathovar. Indeed, we demonstrate experimentally reduced plasmid uptake in a CRISPR-Cas-encoding isolate. Based on our data, we propose that the loss of the CRISPR-Cas system was a pivotal step in X. campestris evolution by facilitating increased genome dynamics and the emergence of the vasculature-adapted X. campestris pathovar campestris, a major pathogen of Brassica crops.},
}

@article {pmid39932497,
year = {2025},
author = {Burgaya, J and Damaris, BF and Fiebig, J and Galardini, M},
title = {microGWAS: a computational pipeline to perform large-scale bacterial genome-wide association studies.},
journal = {Microbial genomics},
volume = {11},
number = {2},
pages = {},
doi = {10.1099/mgen.0.001349},
pmid = {39932497},
issn = {2057-5858},
mesh = {*Genome-Wide Association Study/methods ; *Genome, Bacterial ; *Software ; *Escherichia coli/genetics ; *Computational Biology/methods ; *Phylogeny ; Virulence/genetics ; Phenotype ; Drug Resistance, Bacterial/genetics ; Polymorphism, Single Nucleotide ; },
abstract = {Identifying genetic variants associated with bacterial phenotypes, such as virulence, host preference and antimicrobial resistance, has great potential for a better understanding of the mechanisms involved in these traits. The availability of large collections of bacterial genomes has made genome-wide association studies (GWAS) a common approach for this purpose. The need to employ multiple software tools for data pre- and postprocessing limits the application of these methods by experienced bioinformaticians. To address this issue, we have developed a pipeline to perform bacterial GWAS from a set of assemblies and annotations, with multiple phenotypes as targets. The associations are run using five sets of genetic variants: unitigs, gene presence/absence, rare variants (i.e. gene burden test), gene-cluster-specific k-mers and all unitigs jointly. All variants passing the association threshold are further annotated to identify overrepresented biological processes and pathways. The results can be further augmented by generating a phylogenetic tree and predicting the presence of antimicrobial resistance and virulence-associated genes. We tested the microGWAS pipeline on a previously reported dataset on Escherichia coli virulence, successfully identifying the causal variants and providing further interpretation of the association results. The microGWAS pipeline integrates state-of-the-art tools to perform bacterial GWAS into a single, user-friendly and reproducible pipeline, allowing for the democratization of these analyses. The pipeline, together with its documentation, can be accessed at https://github.com/microbial-pangenomes-lab/microGWAS.},
}

*Genome-Wide Association Study/methods
*Genome, Bacterial
*Software
*Escherichia coli/genetics
*Computational Biology/methods
*Phylogeny
Virulence/genetics
Phenotype
Drug Resistance, Bacterial/genetics
Polymorphism, Single Nucleotide

@article {pmid39929826,
year = {2025},
author = {Gong, J and Sun, H and Wang, K and Zhao, Y and Huang, Y and Chen, Q and Qiao, H and Gao, Y and Zhao, J and Ling, Y and Cao, R and Tan, J and Wang, Q and Ma, Y and Li, J and Luo, J and Wang, S and Wang, J and Zhang, G and Xu, S and Qian, F and Zhou, F and Tang, H and Li, D and , and Sedlazeck, FJ and Jin, L and Guan, Y and Fan, S},
title = {Long-read sequencing of 945 Han individuals identifies structural variants associated with phenotypic diversity and disease susceptibility.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {1494},
pmid = {39929826},
issn = {2041-1723},
mesh = {Humans ; Animals ; *Phenotype ; Mice ; *Genetic Variation ; Genetic Predisposition to Disease ; Genome, Human ; Asian People/genetics ; Neanderthals/genetics ; China ; Male ; Female ; Cisplatin ; },
abstract = {Genomic structural variants (SVs) are a major source of genetic diversity in humans. Here, through long-read sequencing of 945 Han Chinese genomes, we identify 111,288 SVs, including 24.56% unreported variants, many with predicted functional importance. By integrating human population-level phenotypic and multi-omics data as well as two humanized mouse models, we demonstrate the causal roles of two SVs: one SV that emerges at the common ancestor of modern humans, Neanderthals, and Denisovans in GSDMD for bone mineral density and one modern-human-specific SV in WWP2 impacting height, weight, fat, craniofacial phenotypes and immunity. Our results suggest that the GSDMD SV could serve as a rapid and cost-effective biomarker for assessing the risk of cisplatin-induced acute kidney injury. The functional conservation from human to mouse and widespread signals of positive natural selection suggest that both SVs likely influence local adaptation, phenotypic diversity, and disease susceptibility across diverse human populations.},
}

Humans
Animals
*Phenotype
Mice
*Genetic Variation
Genetic Predisposition to Disease
Genome, Human
Asian People/genetics
Neanderthals/genetics
China
Male
Female
Cisplatin

@article {pmid39915889,
year = {2025},
author = {Azam, S and Sahu, A and Pandey, NK and Neupane, M and Van Tassell, CP and Rosen, BD and Gandham, RK and Rath, SN and Majumdar, SS},
title = {Advancing the Indian cattle pangenome: characterizing non-reference sequences in Bos indicus.},
journal = {Journal of animal science and biotechnology},
volume = {16},
number = {1},
pages = {21},
pmid = {39915889},
issn = {1674-9782},
support = {BT/PR26466/AAQ/1/704/2017//Department of Biotechnology (DBT), India/ ; BT/PR32758/AAQ/1/760/2019//Department of Biotechnology (DBT), India/ ; },
abstract = {BACKGROUND: India harbors the world's largest cattle population, encompassing over 50 distinct Bos indicus breeds. This rich genetic diversity underscores the inadequacy of a single reference genome to fully capture the genomic landscape of Indian cattle. To comprehensively characterize the genomic variation within Bos indicus and, specifically, dairy breeds, we aim to identify non-reference sequences and construct a comprehensive pangenome.

RESULTS: Five representative genomes of prominent dairy breeds, including Gir, Kankrej, Tharparkar, Sahiwal, and Red Sindhi, were sequenced using 10X Genomics 'linked-read' technology. Assemblies generated from these linked-reads ranged from 2.70 Gb to 2.77 Gb, comparable to the Bos indicus Brahman reference genome. A pangenome of Bos indicus cattle was constructed by comparing the newly assembled genomes with the reference using alignment and graph-based methods, revealing 8 Mb and 17.7 Mb of novel sequence respectively. A confident set of 6,844 Non-reference Unique Insertions (NUIs) spanning 7.57 Mb was identified through both methods, representing the pangenome of Indian Bos indicus breeds. Comparative analysis with previously published pangenomes unveiled 2.8 Mb (37%) commonality with the Chinese indicine pangenome and only 1% commonality with the Bos taurus pangenome. Among these, 2,312 NUIs encompassing ~ 2 Mb, were commonly found in 98 samples of the 5 breeds and designated as Bos indicus Common Insertions (BICIs) in the population. Furthermore, 926 BICIs were identified within 682 protein-coding genes, 54 long non-coding RNAs (lncRNA), and 18 pseudogenes. These protein-coding genes were enriched for functions such as chemical synaptic transmission, cell junction organization, cell-cell adhesion, and cell morphogenesis. The protein-coding genes were found in various prominent quantitative trait locus (QTL) regions, suggesting potential roles of BICIs in traits related to milk production, reproduction, exterior, health, meat, and carcass. Notably, 63.21% of the bases within the BICIs call set contained interspersed repeats, predominantly Long Interspersed Nuclear Elements (LINEs). Additionally, 70.28% of BICIs are shared with other domesticated and wild species, highlighting their evolutionary significance.

CONCLUSIONS: This is the first report unveiling a robust set of NUIs defining the pangenome of Bos indicus breeds of India. The analyses contribute valuable insights into the genomic landscape of desi cattle breeds.},
}

@article {pmid39915364,
year = {2025},
author = {de Castro Oliveira, W and Marques, PH and Erhardt, MM and Felice, AG and Tristão, CLAM and Aburjaile, FF and Oliveira, MBPP and Dos Santos Richards, NSP},
title = {Metagenomic analysis and proteins prediction of emerging pathogens in artisanal cheese.},
journal = {Molecular diversity},
volume = {},
number = {},
pages = {},
pmid = {39915364},
issn = {1573-501X},
abstract = {Currently, reports of the presence of emerging pathogens in cheeses are low and new outbreaks have occurred at an alarming rate, with the Vibrio and Aeromonas genera being the main causes of gastroenteritis in the world. Therefore, Multi-Omics integration has been a strategy to identify and develop detection methods for these pathogens in food. We investigated the presence of emerging pathogens in artisanal cheeses and predicted proteins with immunogenic potential, in silico, for food diagnostics. For this, multiomics integration was used: (a) metagenomics; (b) subtractive genomics; and (c) pan-genomics. Eight species of the genera Vibrio and Aeromonas were identified, the latter being the most abundant (89.7%) and identified in eight regions, with emphasis on the species A. caviae and A. veronii. Pan-genomic analyses revealed intra- and inter-species differences in both genera. Essential, non-cytoplasmic proteins were identified, without homology and with immunological potential for the species researched. Functional annotation of genes present in pan-genomic subsets reveals functionality between the core genome (transcription; amino acid transport and metabolism; and inorganic ion transport and metabolism) and the shared genome (signal transduction and carbohydrate transport and metabolism). A reinterpretation of the genomic plasticity of V. furnissii reveals the presence of mobile genetic elements critical for virulence in human isolates and the RTX toxin, also identified in this species, is present in the pathogenicity islands of V. alginolyticus and V. fluvialis. Collectively, the results provide important information for the development of a diagnostic strategy for emerging pathogens in food using immunoassays.},
}

@article {pmid39912232,
year = {2025},
author = {Vicente, J and Friedrich, A and Schacherer, J and Freel, K and Marquina, D and Santos, A},
title = {Whole-Genome Sequencing and Phenotyping Reveal Specific Adaptations of Lachancea thermotolerans to the Winemaking Environment.},
journal = {Molecular ecology},
volume = {},
number = {},
pages = {e17667},
doi = {10.1111/mec.17667},
pmid = {39912232},
issn = {1365-294X},
support = {CT58/21-CT59/21//Universidad Complutense de Madrid/ ; PID2020-119008RB-I00//Ministry of Science, Innovation and Universities/ ; ERC-CoG 772505/ERC_/European Research Council/International ; IDI-20210391//Centro para el Desarrollo Tecnológico Industrial/ ; },
abstract = {Adaptation to the environment plays an essential role in yeast evolution as a consequence of selective pressures. Lachancea thermotolerans, a yeast related to fermentation and one of the current trends in wine technology research, has undergone an anthropisation process, leading to a notable genomic and phenomic differentiation. Using whole-genome sequencing, of 145 L. thermotolerans strains, we identified six well-defined groups primarily delineated by their ecological origin and exhibiting high levels of genetic diversity. Anthropised strains showed lower genetic diversity due to the selective pressure imposed by the winemaking environment. Strong evidence of anthropisation and adaptation to the wine environment through modification of gene content was also found. Differences in genes involved in the assimilation of alternative carbon and nitrogen sources, such as the MAL31 and DAL5 genes, which confer greater fitness in the winemaking environment, were observed. Additionally, we found that phenotypic traits considered domestication hallmarks are present in anthropised strains. Among these, increased fitness in the presence of ethanol and sulphites, assimilation of non-fermentable carbon sources, and lower levels of residual fructose under fermentative conditions highlight. We hypothesise that lactic acid production in the Saccharomyces-Lachancea lineage is an anthropisation signature linked to winemaking, resulting from the loss of respiratory chain complex I and the evolutionary preference for fermentation over respiration, even in the presence of oxygen. Overall, the results of this work provide valuable insight into the anthropisation process in L. thermotolerans and demonstrate how fermentation environments give rise to similar adaptations in different yeast species.},
}

@article {pmid39911277,
year = {2025},
author = {Sarawad, A and Hosagoudar, S and Parvatikar, P},
title = {Pan-genomics: Insight into the Functional Genome, Applications, Advancements, and Challenges.},
journal = {Current genomics},
volume = {26},
number = {1},
pages = {2-14},
pmid = {39911277},
issn = {1389-2029},
abstract = {A pan-genome is a compilation of the common and unique genomes found in a given species. It incorporates the genetic information from all of the genomes sampled, producing a big and diverse set of genetic material. Pan-genomic analysis has various advantages over typical genomics research. It creates a vast and varied spectrum of genetic material by combining the genetic data from all the sampled genomes. Comparing pan-genomics analysis to conventional genomic research, there are a number of benefits. Although the most recent era of pan-genomic studies has used cutting-edge sequencing technology to shed fresh light on biological variety and improvement, the potential uses of pan-genomics in improvement have not yet been fully realized. Pan-genome research in various organisms has demonstrated that missing genetic components and the detection of significant Structural Variants (SVs) can be investigated using pan-genomic methods. Many individual-specific sequences have been linked to biological adaptability, phenotypic, and key economic attributes. This study aims to focus on how pangenome analysis uncovers genetic differences in various organisms, including human, and their effects on phenotypes, as well as how this might help us comprehend the diversity of species. The review also concentrated on potential problems and the prospects for future pangenome research.},
}

@article {pmid39905490,
year = {2025},
author = {Molina-Pardines, C and Haro-Moreno, JM and Rodriguez-Valera, F and López-Pérez, M},
title = {Extensive paralogism in the environmental pangenome: a key factor in the ecological success of natural SAR11 populations.},
journal = {Microbiome},
volume = {13},
number = {1},
pages = {41},
pmid = {39905490},
issn = {2049-2618},
support = {PRE2021-098122//Ministerio de Economía y Competitividad/ ; PID2020-118052GB-I00//Ministerio de Economía y Competitividad/ ; 2021/PER/00020//Ministerio de Universidades/ ; },
mesh = {*Metagenomics/methods ; Mediterranean Sea ; *Genetic Variation ; Microbiota/genetics ; Genome, Bacterial ; Metagenome ; Phylogeny ; Seawater/microbiology ; },
abstract = {BACKGROUND: The oceanic microbiome is dominated by members of the SAR11 clade. Despite their abundance, challenges in recovering the full genetic diversity of natural populations have hindered our understanding of the eco-evolutionary mechanisms driving intra-species variation. In this study, we employed a combination of single-amplified genomes and long-read metagenomics to recover the genomic diversity of natural populations within the SAR11 genomospecies Ia.3/VII, the dominant group in the Mediterranean Sea.

RESULTS: The reconstruction of the first complete genome within this genomospecies revealed that the core genome represents a significant proportion of the genome (~ 81%), with highly divergent areas that allow for greater strain-dependent metabolic flexibility. The flexible genome was concentrated in small regions, typically containing a single gene, and was located in equivalent regions within the genomospecies. Each variable region was associated with a specific set of genes that, despite exhibiting some divergence, maintained equivalent biological functionality within the population. The environmental pangenome is large and enriched in genes involved in nutrient transport, as well as cell wall synthesis and modification, showing an extremely high degree of functional redundancy in the flexible genome (i.e. paralogisms).

CONCLUSIONS: This genomic architecture promotes polyclonality, preserving genetic variation within the population. This, in turn, mitigates intraspecific competition and enables the population to thrive under variable environmental conditions and selective pressures. Furthermore, this study demonstrates the power of long-read metagenomics in capturing the full genetic diversity of environmental SAR11 populations, overcoming the limitations of second-generation sequencing technologies in genome assembly. Video Abstract.},
}

*Metagenomics/methods
Mediterranean Sea
*Genetic Variation
Microbiota/genetics
Genome, Bacterial
Metagenome
Phylogeny
Seawater/microbiology

@article {pmid39902180,
year = {2024},
author = {Li, X and Zhu, Y and Lu, Y and Wu, K and Che, Y and Wang, X and Wang, W and Gao, J and Gao, J and Liu, Z and Zhou, Z},
title = {Population genetic analysis of clinical Mycobacterium abscessus complex strains in China.},
journal = {Frontiers in cellular and infection microbiology},
volume = {14},
number = {},
pages = {1496896},
pmid = {39902180},
issn = {2235-2988},
mesh = {China ; *Mycobacterium abscessus/genetics/drug effects/classification/isolation & purification ; Humans ; *Multilocus Sequence Typing ; *Genome, Bacterial ; *Mycobacterium Infections, Nontuberculous/microbiology/epidemiology ; *Virulence Factors/genetics ; Anti-Bacterial Agents/pharmacology ; Genetic Variation ; Phylogeny ; Drug Resistance, Bacterial/genetics ; Microbial Sensitivity Tests ; Genetics, Population ; },
abstract = {BACKGROUND: To explore the genetic characteristics of the Mycobacterium abscessus complex (MABC) population in China, given its rising clinical importance among nontuberculous mycobacteria.

METHODS: We conducted population genetic analyses on 360 MABC genomes from China, focusing on core genome multilocus sequence typing (cgMLST), pan-genome characterization, population genetics, and antimicrobial resistance gene profiling.

RESULTS: Our analysis identified 273 M. abscessus subsp. abscessus (MabA) and 87 M. abscessus subsp. massiliense (MabM) isolates, uncovering 68 sequence types (STs), with ST5 being the most common. cgMLST classified 33.3% of isolates into six dominant circulating clones (DCCs) and 49.4% into 59 genomic clusters at a threshold of 25 different alleles, including 18 international clusters linking Chinese isolates with seven other countries. The MABC pan-genome is open, with MabA exhibiting greater accessory gene diversity and higher gene turnover compared to MabM. Mobile genetic elements (MGEs), such as prophages and genomic islands, were prevalent across all genomes. 139 to 151 virulence factors (VFs) were identified per genome, with distinct accessory VFs in MabA and MabM affecting immune modulation and metabolism. Resistance gene profiling revealed ubiquitous mtrA, RbpA, and bla MAB, with MabA-specific erm(41) conferring resistance to macrolides and β-lactams. Common rrs and rrl gene mutations indicated widespread resistance to aminoglycosides and macrolides, while gyrA mutations suggested emerging fluoroquinolone resistance. An acquired erm(46) gene, likely obtained via phage-mediated horizontal gene transfer, was detected in one MabA strain.

CONCLUSION: This study provides key genetic insights into the dynamics of MABC in China. The widespread distribution of DCCs, high genomic clustering rates, open pan-genome, and distinct resistance patterns between MabA and MabM, along with MGEs, highlight the need for targeted surveillance and tailored therapies to address emerging challenges in MABC infections.},
}

China
*Mycobacterium abscessus/genetics/drug effects/classification/isolation & purification
Humans
*Multilocus Sequence Typing
*Genome, Bacterial
*Mycobacterium Infections, Nontuberculous/microbiology/epidemiology
*Virulence Factors/genetics
Anti-Bacterial Agents/pharmacology
Genetic Variation
Phylogeny
Drug Resistance, Bacterial/genetics
Microbial Sensitivity Tests
Genetics, Population

@article {pmid39902049,
year = {2024},
author = {Verma, S and Sowdhamini, R},
title = {Toll-like receptor 4 pathway evolutionary trajectory and functional emergence.},
journal = {Frontiers in immunology},
volume = {15},
number = {},
pages = {1494017},
pmid = {39902049},
issn = {1664-3224},
mesh = {Humans ; *Toll-Like Receptor 4/metabolism/chemistry/genetics ; *Signal Transduction ; *Adaptor Proteins, Vesicular Transport/metabolism/genetics/chemistry ; *Evolution, Molecular ; *Myeloid Differentiation Factor 88/genetics/metabolism/chemistry ; Animals ; Molecular Docking Simulation ; Receptors, Interleukin-1/metabolism/genetics ; Protein Binding ; Membrane Glycoproteins ; },
abstract = {INTRODUCTION: Toll-like receptors 4 (TLR4) recognize lipopolysaccharides (LPS) from bacteria as their conventional ligands and undergo downstream signaling to produce cytokines. They mediate the signaling either by the TIRAP-MyD88 complex or by the TRAM-TRIF complex. The MyD88 pathway is common to all other TLRs, whereas the TRAM-TRIF complex is largely exclusive to TLR4. Here we study the TIR domain of TRAM and TRIF ortholog proteins that are crucial for downstream signaling. Our previous work on pan-genome-wide survey, indicates Callorhincus milli to be the ancestral organism with both TRAM and TRIF proteins.

METHODS: To gain a deeper insight into the protein function and to compare them with Homo sapiens adaptor proteins, we modeled the docking of the TRAM-TRIF complex of representative organisms across various taxa. These modeling experiments provide insights to ascertain a possible interaction surface and calculate the energetics and electrostatic potential of the complex. Furthermore, this enables us to employ normal mode analysis (NMA) to examine fluctuating, interacting, and other specific residue clusters that could have a role in protein functioning in both C. milli and H. sapiens. We also performed molecular dynamics simulations of these complexes and cross-validated the functionally important residues using network parameters.

RESULTS: We compared the stoichiometry of TRAM-TRIF complexes and found that the tetrameric models (TRAM and TRIF dimer) were more stable than the trimeric model (TRAM dimer and TRIF monomer). While the critical residues of TIRAP, TRIF, and MyD88 were preserved, we also found that the important residues of TRAM signaling were not conserved in C. milli.

DISCUSSION: This suggests the presence of functional TIRAP-MyD88-mediated TLR4 signaling and TRIF-mediated TLR3 signaling in the ancestral species. The overall biological function of this signaling domain appears to be gradually acquired through the orchestration of several motifs through an evolutionary scale.},
}

Humans
*Toll-Like Receptor 4/metabolism/chemistry/genetics
*Signal Transduction
*Adaptor Proteins, Vesicular Transport/metabolism/genetics/chemistry
*Evolution, Molecular
*Myeloid Differentiation Factor 88/genetics/metabolism/chemistry
Animals
Molecular Docking Simulation
Receptors, Interleukin-1/metabolism/genetics
Protein Binding
Membrane Glycoproteins

@article {pmid39901014,
year = {2025},
author = {Guo, W and Schreiber, M and Marosi, VB and Bagnaresi, P and Jørgensen, ME and Braune, KB and Chalmers, K and Chapman, B and Dang, V and Dockter, C and Fiebig, A and Fincher, GB and Fricano, A and Fuller, J and Haaning, A and Haberer, G and Himmelbach, A and Jayakodi, M and Jia, Y and Kamal, N and Langridge, P and Li, C and Lu, Q and Lux, T and Mascher, M and Mayer, KFX and McCallum, N and Milne, L and Muehlbauer, GJ and Nielsen, MTS and Padmarasu, S and Pedas, PR and Pillen, K and Pozniak, C and Rasmussen, MW and Sato, K and Schmutzer, T and Scholz, U and Schüler, D and Šimková, H and Skadhauge, B and Stein, N and Thomsen, NW and Voss, C and Wang, P and Wonneberger, R and Zhang, XQ and Zhang, G and Cattivelli, L and Spannagl, M and Bayer, M and Simpson, C and Zhang, R and Waugh, R},
title = {A barley pan-transcriptome reveals layers of genotype-dependent transcriptional complexity.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {39901014},
issn = {1546-1718},
support = {KJHI-B1-2//Rural and Environment Science and Analytical Services Division (Scottish Government's Rural and Environment Science and Analytical Services Division)/ ; KJHI-B1-2//Rural and Environment Science and Analytical Services Division (Scottish Government's Rural and Environment Science and Analytical Services Division)/ ; KJHI-B1-2//Rural and Environment Science and Analytical Services Division (Scottish Government's Rural and Environment Science and Analytical Services Division)/ ; KJHI-B1-2//Rural and Environment Science and Analytical Services Division (Scottish Government's Rural and Environment Science and Analytical Services Division)/ ; KJHI-B1-2//Rural and Environment Science and Analytical Services Division (Scottish Government's Rural and Environment Science and Analytical Services Division)/ ; KJHI-B1-2//Rural and Environment Science and Analytical Services Division (Scottish Government's Rural and Environment Science and Analytical Services Division)/ ; KJHI-B1-2//Rural and Environment Science and Analytical Services Division (Scottish Government's Rural and Environment Science and Analytical Services Division)/ ; KJHI-B1-2//Rural and Environment Science and Analytical Services Division (Scottish Government's Rural and Environment Science and Analytical Services Division)/ ; KJHI-B1-2//Rural and Environment Science and Analytical Services Division (Scottish Government's Rural and Environment Science and Analytical Services Division)/ ; BB/X018636/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/S020160/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; ERA-CAPS BB/S004610/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/S020160/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/X018636/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/S020160/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; ERA-CAPS BB/S004610/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/X018636/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/X018636/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/X018636/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; BB/S020160/1//RCUK | Biotechnology and Biological Sciences Research Council (BBSRC)/ ; UMU1806-002RTX//Grains Research and Development Corporation (Grains Research & Development Corporation)/ ; UMU1806-002RTX//Grains Research and Development Corporation (Grains Research & Development Corporation)/ ; UMU1806-002RTX//Grains Research and Development Corporation (Grains Research & Development Corporation)/ ; UMU1806-002RTX//Grains Research and Development Corporation (Grains Research & Development Corporation)/ ; UMU1806-002RTX//Grains Research and Development Corporation (Grains Research & Development Corporation)/ ; UMU1806-002RTX//Grains Research and Development Corporation (Grains Research & Development Corporation)/ ; UMU1806-002RTX//Grains Research and Development Corporation (Grains Research & Development Corporation)/ ; CF15-0236//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0476//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0672//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0236//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0476//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0672//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0236//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0476//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0672//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0236//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0476//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0672//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0236//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0476//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0672//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0236//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0476//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0672//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0236//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0476//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0672//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0236//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0476//Carlsbergfondet (Carlsberg Foundation)/ ; CF15-0672//Carlsbergfondet (Carlsberg Foundation)/ ; ERA-CAPS project 1844331//National Science Foundation (NSF)/ ; ERA-CAPS project 1844331//National Science Foundation (NSF)/ ; CTAG2//Genome Canada (Génome Canada)/ ; },
abstract = {A pan-transcriptome describes the transcriptional and post-transcriptional consequences of genome diversity from multiple individuals within a species. We developed a barley pan-transcriptome using 20 inbred genotypes representing domesticated barley diversity by generating and analyzing short- and long-read RNA-sequencing datasets from multiple tissues. To overcome single reference bias in transcript quantification, we constructed genotype-specific reference transcript datasets (RTDs) and integrated these into a linear pan-genome framework to create a pan-RTD, allowing transcript categorization as core, shell or cloud. Focusing on the core (expressed in all genotypes), we observed significant transcript abundance variation among tissues and between genotypes driven partly by RNA processing, gene copy number, structural rearrangements and conservation of promotor motifs. Network analyses revealed conserved co-expression module::tissue correlations and frequent functional diversification. To complement the pan-transcriptome, we constructed a comprehensive cultivar (cv.) Morex gene-expression atlas and illustrate how these combined datasets can be used to guide biological inquiry.},
}

@article {pmid39900839,
year = {2025},
author = {Mejía-Caballero, A and López-Sánchez, R and Ramos-Cerrillo, B and Garciarrubio, A and Segovia, L},
title = {Genomic insights into habitat adaptation of Lactobacillus species.},
journal = {World journal of microbiology & biotechnology},
volume = {41},
number = {2},
pages = {61},
pmid = {39900839},
issn = {1573-0972},
support = {IN209921//Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México/ ; IV200322//Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México/ ; IN209921//Dirección General de Asuntos del Personal Académico, Universidad Nacional Autónoma de México/ ; },
mesh = {*Phylogeny ; *Genome, Bacterial ; *Lactobacillus/genetics/classification ; *Ecosystem ; *Adaptation, Physiological/genetics ; Animals ; *Base Composition ; *Genomics ; Humans ; Insecta/microbiology ; Vegetables/microbiology ; Dairy Products/microbiology ; },
abstract = {Lactobacillus is one of the most important genera within the lactic acid bacteria group, due to its importance in the food industry and the health field. This diversity can be explained either by their radiation in different environments or by the domestication process in artificial habitats, such as fermented foods. In this study, we performed a comparative genomic analysis of 1020 Lactobacillus genomes, categorizing them into five broad habitats: insects, vertebrates (including humans and animals), vegetables, free-living environments, and dairy products. Utilizing phylogenetic relationships, genomic distances, and gene presence/absence profiles, we identified distinct clustering patterns associated with specific environmental adaptations. Notably, species within the Lactobacillus delbrueckii clade exhibited GC content variations fivefold greater than those observed in other bacterial genera, indicating significant genomic divergence. Insect-associated species showed a strong correlation between genes for carbohydrate utilization and those for amino acid biosynthesis across all habitats. However, individual gene analyses revealed no consistent correlation between habitat adaptation and phylogenetic proximity, suggesting that Lactobacillus employs strain-specific adaptive mechanisms rather than universal genetic markers. Notably, around 50% of the genes associated with specific habitats are hypothetical. Our findings highlight the genomic complexity of Lactobacillus, driven by diverse adaptive strategies, and underscore the need for more comprehensive sampling to fully elucidate the evolutionary dynamics within this important genus.},
}

*Phylogeny
*Genome, Bacterial
*Lactobacillus/genetics/classification
*Ecosystem
*Adaptation, Physiological/genetics
Animals
*Base Composition
*Genomics
Humans
Insecta/microbiology
Vegetables/microbiology
Dairy Products/microbiology

@article {pmid39899041,
year = {2025},
author = {Lv, H and Sun, J and Guo, Y and Hang, G and Wu, Q and Sun, Z and Zhang, H},
title = {Isolation of Enterococcus hirae From Fresh White Yak Milk in Ledu District, Qinghai Province, China: A Comparative Genomic Analysis.},
journal = {Current microbiology},
volume = {82},
number = {3},
pages = {111},
pmid = {39899041},
issn = {1432-0991},
support = {U22A20540//Natural Science Foundation of China/ ; 2023KYPT0019//Inner Mongolia Science & Technology planning project/ ; BR22-12-03//Basic Research Operating Expenses Program for Colleges and Universities directly under the Inner Mongolia Autonomous Region/ ; },
mesh = {Animals ; *Milk/microbiology ; China ; *Enterococcus hirae/genetics/classification/isolation & purification ; Cattle ; *Genome, Bacterial ; Genomics ; Bacteriocins/genetics ; Virulence Factors/genetics ; Food Microbiology ; Phylogeny ; Humans ; },
abstract = {Yak milk is a widely consumed dairy product rich in lactic acid bacteria. Although Enterococcus hirae (E. hirae) is commonly found in dairy products and other foods, there is limited information available on its genetic makeup in yak milk. In the present study, 10 E. hirae strains isolated and identified from fresh white yak milk samples, along with 442 E. hirae strains obtained from the NCBI database (totaling 452 strains), were subjected to comparative genomic analysis. The findings of this study revealed that E. hirae has an open pan-genomic structure that allows for its high adaptability and environmental plasticity. Notably, E. hirae isolates from fresh white yak milk had smaller genomes, encoded more functional genes, and had fewer copies of genes encoding carbohydrate-active enzymes involved in the degradation of oligosaccharide metabolism and autolysin synthesis (CE1, GH73, GH23, and GT4 families) than those from animal and human isolates (P < 0.05). Additionally, fresh white yak milk isolates carried only three intrinsic bacteriocins and lacked virulence factors, CRISPR-Cas systems, and resistance genes linked to pathogenicity, which may be attributed to their specialization in the milk-derived environment. This study provides new insights into the genetic and functional gene diversity of E. hirae and how it adapts to milk-derived habitats.},
}

Animals
*Milk/microbiology
China
*Enterococcus hirae/genetics/classification/isolation & purification
Cattle
*Genome, Bacterial
Genomics
Bacteriocins/genetics
Virulence Factors/genetics
Food Microbiology
Phylogeny
Humans

@article {pmid39898312,
year = {2025},
author = {O'Brien, B and Yushchenko, A and Suh, J and Jung, D and Cai, Z and Nguyen, NS and Semret, M and Dufour, S and Fanning, S and Ronholm, J},
title = {Subtle genomic differences in Klebsiella pneumoniae sensu stricto isolates indicate host adaptation.},
journal = {One health (Amsterdam, Netherlands)},
volume = {20},
number = {},
pages = {100970},
pmid = {39898312},
issn = {2352-7714},
abstract = {Klebsiella pneumoniae sensu stricto (KpI) is an opportunistic pathogen capable of residing as a commensal in both human and bovine intestinal tracts and can cause serious systemic infections in humans and severe clinical mastitis in dairy cattle. It is unclear what role zoonotic and anthroponotic transmission play in the dissemination of KpI. In this study, we use a comparative genomic approach to identify differences between KpI associated with disease in humans and cattle and aimed to identify any potential genetic barriers limiting transmission of KpI between these two hosts. A total of 128 KpI strains (bovine n = 65; human n = 63) were whole genome sequenced and human and bovine strains were compared based on phylogenomics, the pangenome, mobile genetic elements, and differential gene abundance. No obvious phylogenomic differentiation was observed between isolates from these hosts. However, subtle genetic differences exist between bovine and human KpI which likely reflect environmental adaptation to different host niches, including a higher representation of gene clusters encoding ferric citrate uptake transporters, as well as histidine, arginine, and lactose utilization pathways in bovine isolates. These gene clusters may be positively selected due to the unique metabolic environment of the mammary gland, where lactose, citrate-bound iron, and amino acids like histidine and arginine provide growth advantages for KpI during mastitis. Overall, our study identified no obvious genetic barriers to zoonotic transmission of KpI within the dairy environment and provides insight into the development of host-specific therapeutic options for KpI infections in humans and bovine.},
}

@article {pmid39894347,
year = {2025},
author = {Ruperao, P and Rangan, P and Shah, T and Sharma, V and Rathore, A and Mayes, S and Pandey, MK},
title = {Developing pangenomes for large and complex plant genomes and their representation formats.},
journal = {Journal of advanced research},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jare.2025.01.052},
pmid = {39894347},
issn = {2090-1224},
abstract = {BACKGROUND: The development of pangenomes has revolutionized genomic studies by capturing the complete genetic diversity within a species. Pangenome assembly integrates data from multiple individuals to construct a comprehensive genomic landscape, revealing both core and accessory genomic elements. This approach enables the identification of novel genes, structural variations, and gene presence-absence variations, providing insights into species evolution, adaptation, and trait variation. Representing pangenomes requires innovative visualization formats that effectively convey the complex genomic structures and variations.

AIM: This review delves into contemporary methodologies and recent advancements in constructing pangenomes, particularly in plant genomes. It examines the structure of pangenome representation, including format comparison, conversion, visualization techniques, and their implications for enhancing crop improvement strategies.

Earlier comparative studies have illuminated novel gene sequences, copy number variations, and presence-absence variations across diverse crop species. The concept of a pan-genome, which captures multiple genetic variations from a broad spectrum of genotypes, offers a holistic perspective of a species' genetic makeup. However, constructing a pan-genome for plants with larger genomes poses challenges, including managing vast genome sequence data and comprehending the genetic variations within the germplasm. To address these challenges, researchers have explored cost-effective alternatives to encapsulate species diversity in a single assembly known as a pangenome. This involves reducing the volume of genome sequences while focusing on genetic variations. With the growing prominence of the pan-genome concept in plant genomics, several software tools have emerged to facilitate pangenome construction. This review sheds light on developing and utilizing software tools tailored for constructing pan-genomes in plants. It also discusses representation formats suitable for downstream analyses, offering valuable insights into the genetic landscape and evolutionary dynamics of plant species. In summary, this review underscores the significance of pan-genome construction and representation formats in resolving the genetic architecture of plants, particularly those with complex genomes. It provides a comprehensive overview of recent advancements, aiding in exploring and understanding plant genetic diversity.},
}

@article {pmid39889851,
year = {2025},
author = {Alvarez-Maya, I and Garcia-Ulloa, M and Martinez-Guarneros, A and Vazquez-Chacon, CA and Martinez-Urtaza, J},
title = {Nationwide Phylogenomic Surveillance of Mycobacterium tuberculosis in Mexico Reveals Pathogenic and Drug Resistant Signatures of the Prevailing L4 Sublineage.},
journal = {Journal of global antimicrobial resistance},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jgar.2025.01.013},
pmid = {39889851},
issn = {2213-7173},
abstract = {BACKGROUND: Tuberculosis disease is a major global health concern. In Mexico, information regarding the genomic variants of Mycobacterium tuberculosis (MTB) prevailing in the country and the existence of specific biogeographical patterns remains extremely scarce.

OBJECTIVE: This study aimed to identify the genotypic patterns of MTB isolates in Mexico and determine the genes and specific single nucleotide polymorphisms involved in the evolution of these populations.

METHODS: Phylogenomic and pan-genomic analyses were performed using publicly available Mexican MTB genomes along with 33 newly sequenced genomes from Jalisco, considering a global context.

RESULTS: The L4 sublineages of MTB, such as L4.1.1 (X), L4.1.2 (H), and L4.3 (LAM), were the most prevalent in Mexico. We found exclusive mutations and gene clusters in a virulent sublineage L4.1.1.3 (X3), which is endemic to Mexico. These genes encoded three PE/PPE family proteins: a multidrug transporter, thioredoxin domain-containing protein, quinone-dependent L-lactate dehydrogenase, DUF1725 domain-containing protein, amidase, poly (A) polymerase, and six hypothetical/uncharacterized proteins. Additionally, the genes encode an ESX-1 secretion-associated protein and a deazaflavin-dependent nitroreductase (ddn).

CONCLUSION: X3 was distinguished from the rest of the sublineages by containing genes related to pathogenicity and virulence, as well as a gene linked to delamanid, an antibiotic for active multidrug-resistant tuberculosis. These findings provide valuable insight into the circulation and spread of MTB in Mexico.},
}

@article {pmid39882343,
year = {2024},
author = {Sholeh, M and Beig, M and Kouhsari, E and Rohani, M and Katouli, M and Badmasti, F},
title = {Global insights into the genome dynamics of Clostridioides difficile associated with antimicrobial resistance, virulence, and genomic adaptations among clonal lineages.},
journal = {Frontiers in cellular and infection microbiology},
volume = {14},
number = {},
pages = {1493225},
pmid = {39882343},
issn = {2235-2988},
mesh = {*Clostridioides difficile/genetics/drug effects/pathogenicity/classification ; *Genome, Bacterial ; *Virulence Factors/genetics ; *Drug Resistance, Bacterial/genetics ; Virulence/genetics ; Humans ; Clostridium Infections/microbiology ; Multilocus Sequence Typing ; Anti-Bacterial Agents/pharmacology ; Plasmids/genetics ; Genomics ; Bacterial Toxins/genetics ; Phylogeny ; },
abstract = {BACKGROUND: Clostridioides difficile is a significant cause of healthcare-associated infections, with rising antimicrobial resistance complicating treatment. This study offers a genomic analysis of C. difficile, focusing on sequence types (STs), global distribution, antibiotic resistance genes, and virulence factors in its chromosomal and plasmid DNA.

METHODS: A total of 19,711 C. difficile genomes were retrieved from GenBank. Prokka was used for genome annotation, and multi-locus sequence typing (MLST) identified STs. Pan-genome analysis with Roary identified core and accessory genes. Antibiotic resistance genes, virulence factors, and toxins were detected using the CARD and VFDB databases, and the ABRicate software. Statistical analyses and visualizations were performed in R.

RESULTS: Among 366 identified STs, ST1 (1,326 isolates), ST2 (1,141), ST11 (893), and ST42 (763) were predominant. Trends of genome streamlining included reductions in chromosomal length, gene count, protein-coding genes, and pseudogenes. Common antibiotic resistance genes-cdeA (99.46%), cplR (99.63%), and nimB (99.67%)-were nearly ubiquitous. Rare resistance genes like blaCTX-M-2, cfxA3, and blaZ appeared in only 0.005% of genomes. Vancomycin susceptibility-reducing vanG cluster genes were detected at low frequencies. Virulence factors showed variability, with highly prevalent genes such as zmp1 (99.62%), groEL (99.60%), and rpoB/rpoB2 (99.60%). Moderately distributed genes included cwp66 (54.61%) and slpA (79.02%). Toxin genes tcdE (91.26%), tcdC (89.67%), and tcdB (89.06%) were widespread, while binary toxin genes cdtA (26.19%) and cdtB (26.26%) were less common. Toxin gene prevalence, particularly tcdA and tcdB, showed a gradual decline over time, with sharper reductions for cdtA and cdtB. Gene presence patterns (GPP-1) for resistance, virulence, and toxin genes were primarily linked to ST2, ST42, and ST8.

CONCLUSION: This study highlights C. difficile's adaptability and genetic diversity. The decline in toxin genes reflects fewer toxigenic isolates, but the bacterium's increasing preserved resistance factors and virulence genes enable its rapid evolution. ST2, ST42, and ST8 dominate globally, emphasizing the need for ongoing monitoring.},
}

*Clostridioides difficile/genetics/drug effects/pathogenicity/classification
*Genome, Bacterial
*Virulence Factors/genetics
*Drug Resistance, Bacterial/genetics
Virulence/genetics
Humans
Clostridium Infections/microbiology
Multilocus Sequence Typing
Anti-Bacterial Agents/pharmacology
Plasmids/genetics
Genomics
Bacterial Toxins/genetics
Phylogeny

@article {pmid39871478,
year = {2025},
author = {Zhu, X and Yang, R and Liang, Q and Yu, Y and Wang, T and Meng, L and Wang, P and Wang, S and Li, X and Yang, Q and Guo, H and Sui, Q and Wang, Q and Du, H and Chen, Q and Liang, Z and Wu, X and Zeng, Q and Huang, B},
title = {Graph-based pangenome provides insights into the structural variation and genetic basis of metabolic traits in potato.},
journal = {Molecular plant},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.molp.2025.01.017},
pmid = {39871478},
issn = {1752-9867},
abstract = {Potato is the world's most important nongrain crop. Here, we report that 29 genomes from Petota and Etuberosum sections were de novo assembled, and that 248 accessions of wild potatoes, landraces and modern cultivars were re-sequenced at > 25× depth to assess genetic diversity within the Petota section. Subsequently, a graph-based pangenome was constructed by using DM8.1 as the backbone integrated 194,330 nonredundant structural variants. To characterize the metabolome of tubers and illuminate the genomic basis of metabolic traits, LC-MS/MS was employed to obtain the metabolome of 157 accessions, and 9,321 SVs were detected to be significantly associated with 1,258 distinct metabolites via PAV-based metabolomics-GWAS analysis, including metabolites of flavonoids, phenolic acids and phospholipids. To facilitate the utilization of pangenome resources, a comprehensive platform, the potato pangenome database (PPDB, http://101.201.107.228:16666/), was developed for the potato community worldwide. Our study provides a comprehensive genomic resource that enables us to assess the genomic basis of agronomic and metabolic traits, and the genomic dataset resources will accelerate functional genomics studies and genetic improvements in potato.},
}

@article {pmid39870503,
year = {2025},
author = {Jiao, D and Dong, X and Fan, S and Liu, X and Yu, Y and Wei, C},
title = {Gastric cancer genomics study using reference human pangenomes.},
journal = {Life science alliance},
volume = {8},
number = {4},
pages = {},
pmid = {39870503},
issn = {2575-1077},
mesh = {Humans ; *Stomach Neoplasms/genetics ; *Genomics/methods ; *Genome, Human/genetics ; Microsatellite Instability ; Male ; Female ; },
abstract = {A pangenome is the sum of the genetic information of all individuals in a species or a population. Genomics research has been gradually shifted to a paradigm using a pangenome as the reference. However, in disease genomics study, pangenome-based analysis is still in its infancy. In this study, we introduced a graph-based pangenome GGCPan from 185 patients with gastric cancer. We then systematically compared the cancer genomics study results using GGCPan, a linear pangenome GCPan, and the human reference genome as the reference. For small variant detection and microsatellite instability status identification, there is little difference in using three different genomes. Using GGCPan as the reference had a significant advantage in structural variant identification. A total of 24 candidate gastric cancer driver genes were detected using three different reference genomes, of which eight were common and five were detected only based on pangenomes. Our results showed that disease-specific pangenome as a reference is promising and a whole set of tools are still to be developed or improved for disease genomics study in the pangenome era.},
}

Humans
*Stomach Neoplasms/genetics
*Genomics/methods
*Genome, Human/genetics
Microsatellite Instability
Male
Female

@article {pmid39868538,
year = {2025},
author = {Zhang, W and Macias-Velasco, JF and Zhuo, X and Belter, EA and Tomlinson, C and Garza, J and Tekkey, N and Li, D and Wang, T},
title = {methylGrapher: genome-graph-based processing of DNA methylation data from whole genome bisulfite sequencing.},
journal = {Nucleic acids research},
volume = {53},
number = {3},
pages = {},
pmid = {39868538},
issn = {1362-4962},
support = {U41HG010972/NH/NIH HHS/United States ; },
mesh = {*DNA Methylation ; Humans ; *Genome, Human ; *Whole Genome Sequencing/methods ; *Sulfites/chemistry ; *CpG Islands ; Software ; Sequence Analysis, DNA/methods ; Genomics/methods ; },
abstract = {Genome graphs, including the recently released draft human pangenome graph, can represent the breadth of genetic diversity and thus transcend the limits of traditional linear reference genomes. However, there are no genome-graph-compatible tools for analyzing whole genome bisulfite sequencing (WGBS) data. To close this gap, we introduce methylGrapher, a tool tailored for accurate DNA methylation analysis by mapping WGBS data to a genome graph. Notably, methylGrapher can reconstruct methylation patterns along haplotype paths precisely and efficiently. To demonstrate the utility of methylGrapher, we analyzed the WGBS data derived from five individuals whose genomes were included in the first Human Pangenome draft as well as WGBS data from ENCODE (EN-TEx). Along with standard performance benchmarking, we show that methylGrapher fully recapitulates DNA methylation patterns defined by classic linear genome analysis approaches. Importantly, methylGrapher captures a substantial number of CpG sites that are missed by linear methods, and improves overall genome coverage while reducing alignment reference bias. Thus, methylGrapher is a first step toward unlocking the full potential of Human Pangenome graphs in genomic DNA methylation analysis.},
}

*DNA Methylation
Humans
*Genome, Human
*Whole Genome Sequencing/methods
*Sulfites/chemistry
*CpG Islands
Software
Sequence Analysis, DNA/methods
Genomics/methods

@article {pmid39868160,
year = {2025},
author = {Kaul, A and Souque, C and Holland, M and Baym, M},
title = {Genomic resistance in historical clinical isolates increased in frequency and mobility after the age of antibiotics.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.01.16.633422},
pmid = {39868160},
issn = {2692-8205},
abstract = {UNLABELLED: Antibiotic resistance is frequently observed shortly after the clinical introduction of an antibiotic. Whether and how frequently that resistance occurred before the introduction is harder to determine, as isolates could not have been tested for resistance before an antibiotic was discovered. Historical collections, like the British National Collection of Type Cultures (NCTC), stretching back to 1885, provide a window into this history. Here we match 1,817 sequenced high-quality genomes from the NCTC collection to their respective year of isolation to study resistance genes before and concurrent with the age of antibiotics. Concordant with previous work, we find resistance genes in both pathogens and environmental samples before the age of antibiotics. While generally rare before the introduction of an antibiotic, we find an associated increase in frequency with antibiotic introduction. Finally, we observe a trend of resistance elements becoming both increasingly mobile and nested within multiple mobile elements as time goes on. More broadly, our findings suggest that likely-functional antibiotic resistance genes were circulating in clinically relevant isolates before the age of antibiotics, but human usage is associated with increasing both their overall prevalence and mobility.

DATA SUMMARY: Genome assemblies downloaded and analyzed are in Supplementary Table 1, and computational tools used are found in the Methods. The authors confirm all supporting data, code and protocols have been provided within the article or through supplementary data files.

IMPACT STATEMENT: Historical collections of microbial isolates enable researchers to both investigate the past and identify interesting trends over time. In this study, we queried over 1,800 isolate genomes in one such collection for genomic variation linked to antibiotic resistance. We show that numerous isolates cultured before the introduction of a given antibiotic contain genomic variation linked to antibiotic resistance; however, this phenomenon remained relatively rare. We demonstrate a strong association between the year a given antibiotic was clinically introduced and a rise in prevalence of genomic resistance to that antibiotic. Finally, we show that while mobile elements are common throughout the isolates and timeframe analyzed, genomic resistance has become increasingly mobile as time has gone on. This study shows that as expected, the clinical introduction of a given antibiotic is correlated with an increase in resistance to that antibiotic but also was linked with increased mobility of genes and alleles conferring resistance. However, we note that the effect of deposition bias in the collection cannot be excluded. Our work also indicates that numerous microbial pangenomes of pathogens naturally contained genomic resistance to a given antibiotic even before anthropogenic use of that antibiotic. Taken together, we demonstrate that although human use may affect the prevalence and mobility of genomic resistance in clinical isolates; for most antibiotics, genomic resistance existed within the pangenomes of sampled pathogens prior to clinical introduction. Quantifying and understanding the impact of antibiotic introduction in the past helps us understand how the introduction of novel antibiotics can impact bacteria; allowing better reaction to novel resistant infections as they arise.},
}

@article {pmid39866568,
year = {2025},
author = {Pucci, N and Ujčič-Voortman, J and Verhoeff, AP and Mende, DR},
title = {Priority effects, nutrition and milk glycan-metabolic potential drive Bifidobacterium longum subspecies dynamics in the infant gut microbiome.},
journal = {PeerJ},
volume = {13},
number = {},
pages = {e18602},
pmid = {39866568},
issn = {2167-8359},
mesh = {Humans ; *Gastrointestinal Microbiome/physiology ; *Milk, Human/microbiology/chemistry/metabolism ; Infant ; *Bifidobacterium/metabolism/genetics ; *Bifidobacterium longum/metabolism ; Female ; *Polysaccharides/metabolism ; Infant, Newborn ; Feces/microbiology ; Metagenome ; Breast Feeding ; Male ; },
abstract = {BACKGROUND: The initial colonization of the infant gut is a complex process that defines the foundation for a healthy microbiome development. Bifidobacterium longum is one of the first colonizers of newborns' gut, playing a crucial role in the healthy development of both the host and its microbiome. However, B. longum exhibits significant genomic diversity, with subspecies (e.g., Bifidobacterium longum subsp. infantis and subsp. longum) displaying distinct ecological and metabolic strategies including differential capabilities to break down human milk glycans (HMGs). To promote healthy infant microbiome development, a good understanding of the factors governing infant microbiome dynamics is required.

METHODOLOGY: We analyzed newly sequenced gut microbiome samples of mother-infant pairs from the Amsterdam Infant Microbiome Study (AIMS) and four publicly available datasets to identify important environmental and bifidobacterial features associated with the colonization success and succession outcomes of B. longum subspecies. Metagenome-assembled genomes (MAGs) were generated and assessed to identify characteristics of B. longum subspecies in relation to early-life gut colonization. We further implemented machine learning tools to identify significant features associated with B. longum subspecies abundance.

RESULTS: B. longum subsp. longum was the most abundant and prevalent gut Bifidobacterium at one month, being replaced by B. longum subsp. infantis at six months of age. By utilizing metagenome-assembled genomes (MAGs), we reveal significant differences between and within B. longum subspecies in their potential to break down HMGs. We further combined strain-tracking, meta-pangenomics and machine learning to understand these abundance dynamics and found an interplay of priority effects, milk-feeding type and HMG-utilization potential to govern them across the first six months of life. We find higher abundances of B. longum subsp. longum in the maternal gut microbiome, vertical transmission, breast milk and a broader range of HMG-utilizing genes to promote its abundance at one month of age. Eventually, we find B. longum subsp. longum to be replaced by B. longum subsp. infantis at six months of age due to a combination of nutritional intake, HMG-utilization potential and a diminishment of priority effects.

DISCUSSION: Our results establish a strain-level ecological framework explaining early-life abundance dynamics of B. longum subspecies. We highlight the role of priority effects, nutrition and significant variability in HMG-utilization potential in determining the predictable colonization and succession trajectories of B. longum subspecies, with potential implications for promoting infant health and well-being.},
}

Humans
*Gastrointestinal Microbiome/physiology
*Milk, Human/microbiology/chemistry/metabolism
Infant
*Bifidobacterium/metabolism/genetics
*Bifidobacterium longum/metabolism
Female
*Polysaccharides/metabolism
Infant, Newborn
Feces/microbiology
Metagenome
Breast Feeding
Male

@article {pmid39860996,
year = {2025},
author = {Wang, C and Jia, X and Wei, M and Yan, J and Sun, Q and Long, S and Zheng, M and Shi, Y and Jiang, G and Zhao, Y and Huang, H and Yang, X and Gu, L and Wang, G},
title = {Discovery of Novel Diagnostic Biomarkers for Common Pathogenic Nocardia Through Pan-Genome and Comparative Genome Analysis, with Preliminary Validation.},
journal = {Pathogens (Basel, Switzerland)},
volume = {14},
number = {1},
pages = {},
pmid = {39860996},
issn = {2076-0817},
support = {2022-3-040//Beijing Public Health Experts Project/ ; KJ2022CX044//Beijing Tongzhou Municipal Science & Technology commission/ ; YH201917//Tongzhou Yunhe Project under Grant/ ; },
mesh = {*Nocardia/genetics/isolation & purification ; *Nocardia Infections/diagnosis/microbiology ; Humans ; *Genome, Bacterial/genetics ; *Biomarkers ; Genomics/methods ; },
abstract = {The aim of this study was to reveal diagnostic biomarkers of considerable importance for common pathogenic Nocardia, utilizing pan-genomic and comparative genome analysis to accurately characterize clinical Nocardia infections. In this study, complete or assembled genome sequences of common pathogenic Nocardia and closely related species were obtained from NCBI as discovery and validation sets, respectively. Genome annotation was performed using Prokka software, and pan-genomic analysis and extraction of Nocardia core genes were performed using BPGA software. Comparative genome analysis of these core genes with the validation-set gene sequences was then performed using BLAT, with a threshold of 30% amino acid coverage and identity, in order to distinguish specific core genes. Finally, candidate gene-specific primers were designed using Snapgene software and DNA samples were obtained from clinical Nocardia strains and closely related species for validation. The analysis identified eighteen core genes specific to Nocardia spp., four core genes specific to N. farcinica, and forty-six core genes specific to N. cyriacigeorgica. After rigorous clinical validation, one gene from Nocardia spp. and five genes from N. cyriacigeorgica were confirmed to have high specificity and therefore can be used as reliable biomarkers for accurate diagnosis of Nocardia infection. This pioneering research reveals diagnostic biomarkers of considerable significance, with the potential to substantially enhance the precise diagnosis of common pathogenic Nocardia infections, thereby laying the groundwork for innovative diagnostic methodologies in subsequent studies.},
}

*Nocardia/genetics/isolation & purification
*Nocardia Infections/diagnosis/microbiology
Humans
*Genome, Bacterial/genetics
*Biomarkers
Genomics/methods

@article {pmid39858976,
year = {2025},
author = {He, Y and Dykes, GE and Kanrar, S and Liu, Y and Gunther, NW and Counihan, KL and Lee, J and Capobianco, JA},
title = {Comparative Genomic Analysis of Campylobacter Plasmids Identified in Food Isolates.},
journal = {Microorganisms},
volume = {13},
number = {1},
pages = {},
pmid = {39858976},
issn = {2076-2607},
support = {Current Research Information System number 8072-42000-093//U.S. Department of Agriculture, Agricultural Research Service (USDA-ARS), National Program 108/ ; },
abstract = {Campylobacter is one of the leading bacterial causes of gastroenteritis worldwide. It frequently contaminates poultry and other raw meat products, which are the primary sources of Campylobacter infections in humans. Plasmids, known as important mobile genetic elements, often carry genes for antibiotic resistance, virulence, and self-mobilization. They serve as the main vectors for transferring genetic material and spreading resistance and virulence among bacteria. In this study, we identified 34 new plasmids from 43 C. jejuni and C. coli strains isolated from retail meat using long-read and short-read genome sequencing. Pangenomic analysis of the plasmid assemblies and reference plasmids from GenBank revealed five distinct groups, namely, pTet, pVir, mega plasmids (>80 kb), mid plasmids (~30 kb), and small plasmids (<6 kb). Pangenomic analysis identified the core and accessory genes in each group, indicating a high degree of genetic similarity within groups and substantial diversity between the groups. The pTet plasmids were linked to tetracycline resistance phenotypes in host strains. The mega plasmids carry multiple genes (e.g., aph(3')-III, type IV and VI secretion systems, and type II toxin-antitoxin systems) important for plasmid mobilization, virulence, antibiotic resistance, and the persistence of Campylobacter. Together, the identification and comprehensive genetic characterization of new plasmids from Campylobacter food isolates contributes to understanding the mechanisms of gene transfer, particularly the spread of genetic determinants of virulence and antibiotic resistance in this important pathogen.},
}

@article {pmid39858636,
year = {2025},
author = {Castillo, G and Contreras-Liza, SE and Arbizu, CI and Rodriguez-Grados, PM},
title = {Genome Sequencing Reveals the Potential of Enterobacter sp. Strain UNJFSC003 for Hydrocarbon Bioremediation.},
journal = {Genes},
volume = {16},
number = {1},
pages = {},
doi = {10.3390/genes16010089},
pmid = {39858636},
issn = {2073-4425},
support = {530//National University Toribio Rodríguez de Mendoza/ ; },
mesh = {*Biodegradation, Environmental ; *Enterobacter/genetics/metabolism ; *Genome, Bacterial ; *Phylogeny ; Polycyclic Aromatic Hydrocarbons/metabolism ; },
abstract = {Bioremediation induced by bacteria offers a promising alternative for the contamination of aromatic hydrocarbons due to their metabolic processes suitable for the removal of these pollutants, as many of them are carcinogenic molecules and dangerous to human health. Our research focused on isolating a bacterium from the rhizosphere of the tara tree with the ability to degrade polycyclic aromatic hydrocarbons, using draft genomic sequencing and computational analysis. Enterobacter sp. strain UNJFSC 003 possesses 4460 protein-coding genes, two rRNA genes, 77 tRNA genes, and a GC content of 54.38%. A taxonomic analysis of our strain revealed that it has an average nucleotide identity (ANI) of 87.8%, indicating that it is a new native Enterobacteria. Additionally, a pangenomic analysis with 15 strains demonstrated that our strain has a phylogenetic relationship with strain FDAARGOS 1428 (Enterobacter cancerogenus), with a total of 381 core genes and 4778 accessory genes. Orthologous methods predicted that strain UNJFSC 003 possesses genes with potential for use in hydrocarbon bioremediation. Genes were predicted in the sub-pathways for the degradation of homoprotocatechuate and phenylacetate, primarily located in the cytoplasm. Studies conducted through molecular modeling and docking revealed the affinity of the predicted proteins in the degradation of benzo[a]pyrene in the homoprotocatechuate sub-pathway, specifically hpcB, which has enzymatic activity as a dioxygenase, and hpcC, which functions as an aldehyde dehydrogenase. This study provides information on native strains from Lomas de Lachay with capabilities for the bioremediation of aromatic hydrocarbons and other compounds.},
}

*Biodegradation, Environmental
*Enterobacter/genetics/metabolism
*Genome, Bacterial
*Phylogeny
Polycyclic Aromatic Hydrocarbons/metabolism

@article {pmid39855357,
year = {2025},
author = {Zheng, X and Xiang, Y and Li, X and Du, X and Wang, Y and Tian, S and Xue, J and Huang, Y and Liu, H and Wang, Q and Liu, H and Wang, H and Wang, C and Yang, M and Jia, H and Wang, L and Xu, X and Song, L and Song, H and Qiu, S},
title = {An MDR Salmonella Enteritidis sublineage associated with gastroenteritis outbreaks and invasive disease in China.},
journal = {The Journal of infection},
volume = {},
number = {},
pages = {106421},
doi = {10.1016/j.jinf.2025.106421},
pmid = {39855357},
issn = {1532-2742},
abstract = {OBJECTIVES: Salmonella enterica serovar Enteritidis (S. Enteritidis) is a commonly reported pathogen which adapts to multiple hosts and causes critical disease burden at a global level. Here, we investigated a recently derived epidemic sublineage with multidrug resistance (MDR), which have caused extended time-period and cross-regional gastroenteritis outbreaks and even invasive nontyphoidal Salmonella disease (iNTS) in China.

METHODS: Whole-genome sequencing and antimicrobial resistance (AMR) testing were applied to 729 Chinese S. Enteritidis isolates in relation to gastroenteritis outbreaks, gastrointestinal-sporadic and iNTS infections, spanning 28 years (1994-2021) in China. Phylogenomic analysis was performed to explore the population structure and evolutionary history of the Chinese isolates within a global context. Molecular investigations of AMR genes, virulence factors, mobile genetic elements and pan-genomes were also performed.

RESULTS: The Chinese S. Enteritidis collections exhibited a high level of multidrug resistance (MDR), including high resistance to nalidixic acid (97.67%). Notably, the multidrug resistance rate of iNTS strains has significantly increased over the past decade. Phylogenomic analysis showed that the majority of the Chinese isolates (98.63%) were distributed in the global pandemic lineage L1, while the other lineages were highly continent-specific. Particularly, the Chinese isolates were predominantly distributed in sublineages L1.2 (37.45%) and L1.3 (59.26%), forming two main Chinese clades (MCC1&2). The most recent common ancestor of MCC1&2 dated back to 1944 and 2004, respectively. The lineage L1, especially MCC1&2, harbored the most amount of AMR determinants and virulence genes, which was mainly due to the presence of a hybrid virulence-resistance plasmid and coexistence of different types of AMR plasmids in S. Enteritidis.

CONCLUSIONS: S. Enteritidis has evolved unique clonal clusters, MCC1&2, with critical MDR in China, which phylogenetically constitute an extension of the globally epidemic lineage and were characterized by distinct genetic traits. These clades have induced extensive outbreaks of gastroenteritis and serious cases of iNTS in China, underscoring the pressing nature and severity of this public health crisis. Implementing the One-Health strategy, longstanding routine surveillance and further genomic epidemiological studies are urgently required to capture epidemics, monitor changes in bacterial populations and determine the consequent risk to global public health.},
}

@article {pmid39855107,
year = {2025},
author = {Gloanec, N and Guyard-Nicodème, M and Chemaly, M and Dory, D},
title = {Reverse vaccinology: A strategy also used for identifying potential vaccine antigens in poultry.},
journal = {Vaccine},
volume = {48},
number = {},
pages = {126756},
doi = {10.1016/j.vaccine.2025.126756},
pmid = {39855107},
issn = {1873-2518},
abstract = {Vaccination of livestock plays a major role in improving animal health, welfare and productivity, but also in public health by preventing zoonotic diseases. Advances in bioinformatics and whole-genome sequencing techniques since the 2000s have led to the development of genome-based vaccinology, called reverse vaccinology. Reverse vaccinology is a rapid and competitive strategy that uses pathogen genome sequences to screen for and identify potential vaccine antigens and, unlike conventional methods, does not require culturing the pathogenic microorganism, at least initially. Based on in silico approaches and dedicated software, reverse vaccinology has led to the identification of a wide range of proteins as putative vaccine candidates against human pathogens and has been applied more recently to several animal diseases. After a brief overview of the principle of the approach and its applications in human medicine, this review focuses on the use of reverse vaccinology for the development of vaccines specifically for poultry, a representative example of livestock vaccination, and discusses the important points to consider when using this method.},
}

@article {pmid39854309,
year = {2025},
author = {Coomber, AL and Saville, AC and Carbone, I and Martin, M and Bieker, VC and Ristaino, JB},
title = {A pangenome analysis reveals the center of origin and evolutionary history of Phytophthora infestans and 1c clade species.},
journal = {PloS one},
volume = {20},
number = {1},
pages = {e0314509},
doi = {10.1371/journal.pone.0314509},
pmid = {39854309},
issn = {1932-6203},
mesh = {*Phytophthora infestans/genetics/classification ; *Phylogeny ; *Evolution, Molecular ; South America ; Genetic Variation ; Mexico ; },
abstract = {We examined the evolutionary history of Phytophthora infestans and its close relatives in the 1c clade. We used whole genome sequence data from 69 isolates of Phytophthora species in the 1c clade and conducted a range of genomic analyses including nucleotide diversity evaluation, maximum likelihood trees, network assessment, time to most recent common ancestor and migration analysis. We consistently identified distinct and later divergence of the two Mexican Phytophthora species, P. mirabilis and P. ipomoeae, from P. infestans and other 1c clade species. Phytophthora infestans exhibited more recent divergence from other 1c clade species of Phytophthora from South America, P. andina and P. betacei. Speciation in the 1c clade and evolution of P. infestans occurred in the Andes. P. andina-P. betacei-P. infestans formed a species complex with indistinct species boundaries, hybridizations between the species, and short times to common ancestry. Furthermore, the distinction between modern Mexican and South American P. infestans proved less discrete, suggesting gene flow between populations over time. Admixture analysis indicated a complex relationship among these populations, hinting at potential gene flow across these regions. Historic P. infestans, collected from 1845-1889, were the first to diverge from all other P. infestans populations. Modern South American populations diverged next followed by Mexican populations which showed later ancestry. Both populations were derived from historic P. infestans. Based on the time of divergence of P. infestans from its closest relatives, P. andina and P. betacei in the Andean region, we consider the Andes to be the center of origin of P. infestans, with modern globalization contributing to admixture between P. infestans populations today from Mexico, the Andes and Europe.},
}

*Phytophthora infestans/genetics/classification
*Phylogeny
*Evolution, Molecular
South America
Genetic Variation
Mexico

@article {pmid39849617,
year = {2025},
author = {Yu, X and Qu, M and Wu, P and Zhou, M and Lai, E and Liu, H and Guo, S and Li, S and Yao, X and Gao, L},
title = {Super pan-genome reveals extensive genomic variations associated with phenotypic divergence in Actinidia.},
journal = {Molecular horticulture},
volume = {5},
number = {1},
pages = {4},
pmid = {39849617},
issn = {2730-9401},
support = {32170395//National Natural Science Foundation of China/ ; 32070377//National Natural Science Foundation of China/ ; 2024AFA035//Natural Science Foundation of Hubei Province/ ; },
abstract = {Kiwifruit is an economically and nutritionally important horticultural fruit crop worldwide. The genomic data of several kiwifruit species have been released, providing an unprecedented opportunity for pan-genome analysis to comprehensively investigate the inter- and intra-species genetic diversity and facilitate utilization for kiwifruit breeding. Here, we generated a kiwifruit super pan-genome using 15 high-quality assemblies of eight Actinidia species. For gene-based pan-genome, a total of 61,465 gene families were identified, and the softcore and dispensable genes were enriched in biological processes like response to endogenous stimulus, response to hormone and cell wall organization or biogenesis. Then, structural variations (SVs) against A. chinensis 'Donghong' were identified and then used to construct a graph-based genome. Further population-scale SVs based on resequencing data from 112 individuals of 20 species revealed extensive SVs which probably contributed to the phenotypic diversity among the Actinidia species. SV hotspot regions were found contributed to environmental adaptation. Furthermore, we systematically identified resistance gene analogs (RGAs) in the 15 assemblies and generated a pan-RGA dataset to reveal the diversity of genes potentially involved in disease resistance in Actinidia. The pan-genomic data obtained here is useful for evolutionary and functional genomic studies in Actinidia, and facilitates breeding design.},
}

@article {pmid39843749,
year = {2025},
author = {Cheng, L and Wang, N and Bao, Z and Zhou, Q and Guarracino, A and Yang, Y and Wang, P and Zhang, Z and Tang, D and Zhang, P and Wu, Y and Zhou, Y and Zheng, Y and Hu, Y and Lian, Q and Ma, Z and Lassois, L and Zhang, C and Lucas, WJ and Garrison, E and Stein, N and Städler, T and Zhou, Y and Huang, S},
title = {Leveraging a phased pangenome for haplotype design of hybrid potato.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {39843749},
issn = {1476-4687},
abstract = {The tetraploid genome and clonal propagation of the cultivated potato (Solanum tuberosum L.)[1,2] dictate a slow, non-accumulative breeding mode of the most important tuber crop. Transitioning potato breeding to a seed-propagated hybrid system based on diploid inbred lines has the potential to greatly accelerate its improvement[3]. Crucially, the development of inbred lines is impeded by manifold deleterious variants; explaining their nature and finding ways to eliminate them is the current focus of hybrid potato research[4-10]. However, most published diploid potato genomes are unphased, concealing crucial information on haplotype diversity and heterozygosity[11-13]. Here we develop a phased potato pangenome graph of 60 haplotypes from cultivated diploids and the ancestral wild species, and find evidence for the prevalence of transposable elements in generating structural variants. Compared with the linear reference, the graph pangenome represents a broader diversity (3,076 Mb versus 742 Mb). Notably, we observe enhanced heterozygosity in cultivated diploids compared with wild ones (14.0% versus 9.5%), indicating extensive hybridization during potato domestication. Using conservative criteria, we identify 19,625 putatively deleterious structural variants (dSVs) and reveal a biased accumulation of deleterious single nucleotide polymorphisms (dSNPs) around dSVs in coupling phase. Based on the graph pangenome, we computationally design ideal potato haplotypes with minimal dSNPs and dSVs. These advances provide critical insights into the genomic basis of clonal propagation and will guide breeders to develop a suite of promising inbred lines.},
}

@article {pmid39842315,
year = {2025},
author = {Zhao, Y and Xie, J and Yu, S and Wu, Q and Wang, Z and Shang, Y and Wang, Z and Zhang, J and Zhai, H and Huang, Z and Ding, Y and Wang, J},
title = {A novel method of species-specific molecular target mining and accurate discrimination of Bacillus cereus sensu lato.},
journal = {International journal of food microbiology},
volume = {431},
number = {},
pages = {111068},
doi = {10.1016/j.ijfoodmicro.2025.111068},
pmid = {39842315},
issn = {1879-3460},
abstract = {Bacillus cereus, a member of the Bacillus cereus sensu lato (B. cereus s.l.), is widely distributed in nature and can contaminate a variety of foods, leading to foodborne illnesses and substantial losses in the food industry. Although culture-based methods remain the gold standard for identifying B. cereus due to their high sensitivity under specific conditions, they are often complex and labor-intensive to implement. Furthermore, the high genetic similarity among certain members of the B. cereus s.l. makes it challenging to identify species-specific molecular targets, hindering the rapid and accurate differentiation of these bacteria. In this study, we introduce a novel method, comparative analysis based on whole genome slices (CAWGS), combined with the Basic Local Alignment Search Tool (BLAST) for efficient molecular target mining. Using CAWGS-BLAST and pan-genome analysis, we successfully identified new molecular targets for B. cereus, Bacillus thuringiensis, emetic B. cereus, Bacillus anthracis, Bacillus mycoides, Bacillus weihenstephanensis, and Bacillus megaterium. Based on these newly discovered targets, we developed a PCR-CRISPR/Cas12a method for detecting B. cereus s.l. and related species. Our research not only provides a rapid and accurate approach for discriminating B. cereus s.l. and related species, but also offers a universal and valuable reference for detecting foodborne pathogens, especially those with highly similar phenotypic and genetic characteristics.},
}

@article {pmid39838887,
year = {2025},
author = {Cohen, ZP and Perkin, LC and Raszick, TJ and Sim, SB and Geib, SM and Childers, AK and Sword, GA and Suh, CP},
title = {Pangenomics Links Boll Weevil Divergence With Ancient Mesoamerican Cotton Cultivation.},
journal = {Molecular ecology resources},
volume = {},
number = {},
pages = {e14054},
doi = {10.1111/1755-0998.14054},
pmid = {39838887},
issn = {1755-0998},
support = {16-352//Cotton Incorporated/ ; 3091//USDA CRIS/ ; -22000-038-00D//USDA CRIS/ ; },
abstract = {The boll weevil, Anthonomus grandis grandis Boheman, and thurberia weevil, Anthonomus grandis thurberiae Pierce, together comprise a species complex that ranges throughout Mexico, the southwestern regions of the United States and parts of South America. The boll weevil is a historically damaging and contemporaneously threatening pest to commercial upland cotton, Gossypium hirsutum L. (Malvales: Malvaceae), whereas the thurberia weevil is regarded as an innocuous non-pest subspecies that is mostly found on non-cultivated Thurber's or Arizona cotton, Gossypium thurberi L., throughout its native range in western Mexico and the southwestern United States. Recent independent analyses, using mitochondrial and whole-genome markers, have suggested the independent evolution of these lineages is more attributable to geographic isolation than biotic factors. We suggest a combination of drivers after employing comparative genomic, population genetic and pangenome methodologies to identify large and small polymorphisms. By leveraging genetic differences, we determined 39,310 diagnostic loci between the subspecies, find genes under selection, and model the subspecies' shared and unique evolutionary history. Interestingly, structural variations capture a large proportion of genes at the population level and demographic reconstruction suggests a split between approximately 3,320-16,300 before present (YBP), which coincides with cotton cultivation in Mesoamerica, approximately 3,000-5,000 YBP. Observed polymorphisms are enriched for reproductive, regulatory, and metabolic genes, which may be attributed to the subspecies split and coevolution with cultivated cotton. Our results demonstrate the utility of a holistic, comparative framework utilising small and large polymorphisms to reconstruct demography and identify genetic novelty via pangenomics.},
}

@article {pmid39838784,
year = {2025},
author = {Sun, T and Song, J and Luo, J and Jiang, Y and Tan, D and Zhou, L and Wu, W and Han, M and Hu, H and Tong, X and Lu, C and Dai, F},
title = {Dysfunction of a lepidopteran conserved gene, BmBLOC1S6, causes a translucent larval integument in the silkworm, Bombyx mori.},
journal = {Pest management science},
volume = {},
number = {},
pages = {},
doi = {10.1002/ps.8664},
pmid = {39838784},
issn = {1526-4998},
support = {//Funds of China Agriculture Research System of MOF and MARA (No. CARS-18-ZJ0102)/ ; //National Natural Science Foundation of China (Grant Nos. 32330102, U20A2058, 31830094, and 32272939)/ ; //Natural Science Foundation of Chongqing, China (Grant no. cstc2021jcyj-cxttX0005)/ ; },
abstract = {BACKGROUND: Diverse lepidopteran insects cause serious damage to plants, and their larvae possess a crucial epidermal barrier against environmental stimuli. Their ultraviolet (UV) resistance is enhanced by accumulating uric acid granules in the epidermis, suggesting that genes involved in this process may be potential targets for lepidopteran pest management.

RESULTS: The silkworm pan-genome dataset is a valuable source for studying genomic mutations and phenotype-genotype associations. Hoarfrost translucent (oh) is a recessive silkworm mutant with a translucent larval integument. Using comparative genomic analysis, we found that the oh mutant has an 828-bp deletion in the BmBLOC1S6 genome. BmBLOC1S6 encodes a BLOC-1 complex subunit and is conserved during lepidopteran evolution. Knockout of BmBLOC1S6 replicated the oh phenotype. Furthermore, BmBLOC1S6 knockout and oh larvae are more sensitive to UV irradiation compared to the wild-type. These results revealed that BmBLOC1S6 is essential in forming uric acid granules for silkworm epidermal UV resistance.

CONCLUSION: Our results showed that BmBLOC1S6 is responsible for the oh phenotype in silkworms and is conserved during lepidopteran evolution. This study may help us better clarify uric acid granules formation in the epidermis, explore their function in UV resistance and identify a potential molecular target for lepidopteran pest control. © 2025 Society of Chemical Industry.},
}

@article {pmid39836460,
year = {2025},
author = {Lao, HY and Wong, AYP and Ng, TT and Wong, RY and Yau, MC and Lam, JY and Siu, GK},
title = {Scrofimicrobium appendicitidis sp. nov., isolated from a patient with ruptured appendicitis.},
journal = {International journal of systematic and evolutionary microbiology},
volume = {75},
number = {1},
pages = {},
doi = {10.1099/ijsem.0.006633},
pmid = {39836460},
issn = {1466-5034},
mesh = {*Appendicitis/microbiology ; *RNA, Ribosomal, 16S/genetics ; *Phylogeny ; Humans ; *DNA, Bacterial/genetics ; *Base Composition ; *Bacterial Typing Techniques ; *Sequence Analysis, DNA ; Genome, Bacterial ; Retrospective Studies ; Actinomycetaceae/genetics/isolation & purification/classification ; Male ; },
abstract = {A clinical isolate, R131, was isolated from the peritoneal swab of a patient who suffered from ruptured appendicitis with abscess and gangrene in Hong Kong in 2018. Cells are facultatively anaerobic, non-motile, Gram-positive coccobacilli. Colonies were small, grey, semi-translucent, low convex and alpha-haemolytic. The bacterium grew on blood agar but not on Brain Heart Infusion (BHI) and Mueller-Hinton agars. It was negative for catalase, oxidase, indole and aesculin hydrolysis. The initial identification attempts via matrix-assisted laser desorption ionization-time of flight mass spectrometry and 16S rRNA gene sequencing yielded inconclusive results. The 16S rRNA gene analysis showed that R131 shared >99% nucleotide identity with certain uncultured Actinomycetales bacteria. In this retrospective investigation, a complete genome of R131 was constructed, disclosing a DNA G+C content of 64%. Phylogenetic analysis showed that the bacterium was mostly related to Scrofimicrobium canadense WB03_NA08, which was first described in 2020. However, its 16S rRNA gene shared only 94.15% nucleotide identity with that of S. canadense WB03_NA08. Notably, the orthoANI between R131 and S. canadense WB03_NA08 was 67.81%. A pan-genome analysis encompassing R131 and 4 Scrofimicrobium genomes showed 986 core gene clusters shared with the Scrofimicrobium species, along with 601 cloud genes. The average nucleotide identity comparisons within the pan-genome analysis ranged from 59.78 to 62.51% between R131 and the other Scrofimicrobium species. Correspondingly, the dDDH values ranged from 19.20 to 22.30%, while the POCP values spanned from 57.48 to 60.94%. Therefore, a novel species, Scrofimicrobium appendicitidis sp. nov., is proposed. The type strain is R131[T] (=JCM 36615[T]=LMG 33627[T]).},
}

*Appendicitis/microbiology
*RNA, Ribosomal, 16S/genetics
*Phylogeny
Humans
*DNA, Bacterial/genetics
*Base Composition
*Bacterial Typing Techniques
*Sequence Analysis, DNA
Genome, Bacterial
Retrospective Studies
Actinomycetaceae/genetics/isolation & purification/classification
Male

@article {pmid39833680,
year = {2025},
author = {Sbissi, I and Chouikhi, F and Ghodhbane-Gtari, F and Gtari, M},
title = {Ecogenomic insights into the resilience of keystone Blastococcus Species in extreme environments: a comprehensive analysis.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {51},
pmid = {39833680},
issn = {1471-2164},
mesh = {*Extreme Environments ; Genome, Bacterial ; Phylogeny ; Genomics/methods ; Ecosystem ; Adaptation, Physiological/genetics ; Metals, Heavy/toxicity ; Biodegradation, Environmental ; Soil Microbiology ; },
abstract = {BACKGROUND: The stone-dwelling genus Blastococcus plays a key role in ecosystems facing extreme conditions such as drought, salinity, alkalinity, and heavy metal contamination. Despite its ecological significance, little is known about the genomic factors underpinning its adaptability and resilience in such harsh environments. This study investigates the genomic basis of Blastococcus's adaptability within its specific microniches, offering insights into its potential for biotechnological applications.

RESULTS: Comprehensive pangenome analysis revealed that Blastococcus possesses a highly dynamic genetic composition, characterized by a small core genome and a large accessory genome, indicating significant genomic plasticity. Ecogenomic assessments highlighted the genus's capabilities in substrate degradation, nutrient transport, and stress tolerance, particularly on stone surfaces and archaeological sites. The strains also exhibited plant growth-promoting traits, enhanced heavy metal resistance, and the ability to degrade environmental pollutants, positioning Blastococcus as a candidate for sustainable agriculture and bioremediation. Interestingly, no correlation was found between the ecological or plant growth-promoting traits (PGPR) of the strains and their isolation source, suggesting that these traits are not linked to their specific environments.

CONCLUSIONS: This research highlights the ecological and biotechnological potential of Blastococcus species in ecosystem health, soil fertility improvement, and stress mitigation strategies. It calls for further studies on the adaptation mechanisms of the genus, emphasizing the need to validate these findings through wet lab experiments. This study enhances our understanding of microbial ecology in extreme environments and supports the use of Blastococcus in environmental management, particularly in soil remediation and sustainable agricultural practices.},
}

*Extreme Environments
Genome, Bacterial
Phylogeny
Genomics/methods
Ecosystem
Adaptation, Physiological/genetics
Metals, Heavy/toxicity
Biodegradation, Environmental
Soil Microbiology

@article {pmid39833199,
year = {2025},
author = {Sivarajan, V and Ganesh, AV and Subramani, P and Ganesapandi, P and Sivanandan, RN and Prakash, S and Manikandan, N and Dharmarajan, A and Arfuso, F and Warrier, S and Raj, M and Perumal, K},
title = {Prevalence and genomic insights of carbapenem resistant and ESBL producing Multidrug resistant Escherichia coli in urinary tract infections.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {2541},
pmid = {39833199},
issn = {2045-2322},
mesh = {*Urinary Tract Infections/microbiology/drug therapy ; Humans ; *Drug Resistance, Multiple, Bacterial/genetics ; *Escherichia coli/genetics/drug effects/isolation & purification ; *Escherichia coli Infections/microbiology/drug therapy/epidemiology ; *beta-Lactamases/genetics ; *Carbapenems/pharmacology ; Prevalence ; *Anti-Bacterial Agents/pharmacology ; Microbial Sensitivity Tests ; Whole Genome Sequencing/methods ; Female ; Male ; Middle Aged ; Adult ; Genome, Bacterial ; Aged ; Genomics/methods ; Phylogeny ; Young Adult ; Adolescent ; Child ; },
abstract = {Urinary tract infections are a common condition affecting people globally, with multidrug-resistant (MDR) Escherichia coli (E. coli) being a major causative agent. Antimicrobial susceptibility profiling was performed using the VITEK 2 automated system for 1254 E. coli isolates, revealing that 831(66.2%) isolates were determined as MDR E. coli. A significant resistance pattern was observed for nalidixic acid (86.04%), ampicillin (74.16%), ticarcillin (70.73%), cefalotin (65.23%), cefixime (62.68%), ciprofloxacin (55.18%), ceftriaxone (53.75%), amoxicillin-clavulanic acid (22.81%), ertapenem (7.18%), and fosfomycin (2.23%). Whole Genome Sequencing of Carbapenem-resistant E. coli (CREC)-CREC 3 (ST405), CREC 4 (ST448), and CREC 5 (ST167) was performed to determine genomic characteristics. CREC 3, CREC 4, and CREC 5 belong to the phylogroup D, B1, and A, respectively. The NDM-5 gene was common in all three isolates, with CTX-M-15 being present in CREC 3 and CREC 4. Virulence factors of CREC 3 (fliC, shuA), CREC 4 (spaS), CREC 5 (iucA, papH, papG, iucB, yigF), and plasmids (IncFIA, IncFIB) were identified to be significant. The use of pangenome analysis enhances our understanding of resistance traits of isolates ST167, ST405, and ST448, offering valuable insights into comparative genomics of uropathogenic MDR E. coli.},
}

*Urinary Tract Infections/microbiology/drug therapy
Humans
*Drug Resistance, Multiple, Bacterial/genetics
*Escherichia coli/genetics/drug effects/isolation & purification
*Escherichia coli Infections/microbiology/drug therapy/epidemiology
*beta-Lactamases/genetics
*Carbapenems/pharmacology
Prevalence
*Anti-Bacterial Agents/pharmacology
Microbial Sensitivity Tests
Whole Genome Sequencing/methods
Female
Male
Middle Aged
Adult
Genome, Bacterial
Aged
Genomics/methods
Phylogeny
Young Adult
Adolescent
Child