@article {pmid42320417,
year = {2026},
author = {Kutyna, DR and Pretorius, IS},
title = {Harvesting insights from recent advances in yeast genomics for predictable and precision wine fermentation.},
journal = {Current opinion in biotechnology},
volume = {100},
number = {},
pages = {103540},
doi = {10.1016/j.copbio.2026.103540},
pmid = {42320417},
issn = {1879-0429},
abstract = {Wine fermentation remains inherently variable because of the genetic and phenotypic diversity of Saccharomyces cerevisiae and non-Saccharomyces yeasts, microbial interactions, and climate-driven shifts in grape composition, challenging predictable and low-intervention winemaking. Recent population genomics advances, including telomere-to-telomere assemblies and pan-genome analyses of yeast genomes, have transformed the field by revealing structural variation, introgressions, hybridization, and gene content diversity underlying key enological traits. High-throughput functional genomics, quantitative trait locus mapping, multi-omics, and machine learning increasingly connect these features with fermentation kinetics, stress tolerance, and aroma biosynthesis. The near completion of the Synthetic Yeast Genome (Sc2.0) and its SCRaMbLE system further expands the experimental design space for rapid genome rearrangement and strain innovation. These advances have improved identification of candidate determinants of industrially relevant phenotypes, but robust genotype-to-phenotype prediction remains limited by polygenic architectures, epistasis, environmental dependence, and microbial context. Future progress will depend on integrating population genomics with functional validation, realistic phenotyping, and interpretable predictive frameworks to support rational yeast engineering and more consistent, sustainable winemaking.},
}

@article {pmid42323284,
year = {2026},
author = {Bouzek, HK and Zepeda-Rivera, MA and Srinivasan, S and Lee, EM and Strenk, SM and Jones, DS and McMahon, EF and Fiedler, TL and Kostovski, M and France, MT and Ravel, J and Fredricks, DN and Johnston, CD},
title = {A syntenic pangenome of Gardnerella reveals novel plasmids and phage, taxonomic boundaries, and species-level stratification of metabolic and virulence potential.},
journal = {Nature communications},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41467-026-74458-2},
pmid = {42323284},
issn = {2041-1723},
support = {DE027850//U.S. Department of Health & Human Services | NIH | National Institute of Dental and Craniofacial Research (NIDCR)/ ; Startup Funds//Fred Hutchinson Cancer Research Center (Hutchinson Center)/ ; },
abstract = {Gardnerella species are key drivers of bacterial vaginosis (BV), a prevalent condition affecting nearly one in three women of reproductive age and associated with adverse reproductive outcomes. Despite decades of study, progress in defining Gardnerella diversity has been hindered by inconsistent taxonomy and poor-quality genomic resources. Here we sequenced 392 Gardnerella isolates spanning asymptomatic and BV-associated microbiota and integrated this collection with all publicly available genomes to create a curated, high-quality reference set of 312 genomes. We resolved 21 genomic lineages encompassing 11 species and 15 subspecies using phylogenomics, average nucleotide identity (ANI), digital DNA-DNA hybridization (dDDH) and assigned each a provisional taxonomic name. Long-read assemblies enabled construction of a syntenic Gardnerella pangenome, revealing lineage-specific repertoires of virulence, metabolic, and defense, including variable sialidases (NanH), vaginolysin, and amino-acid biosynthetic pathways alongside conserved genomic organization. Comparative methylome profiling uncovered restriction-modification system diversity suggesting barriers to genetic exchange. Finally, we identified native cryptic plasmids in Gardnerella, overturning the assumption that the genus lacks plasmids. Together, these results establish a complete genomic and functional framework for Gardnerella, providing a reproducible foundation for mechanistic and translational studies of BV and a model for resolving taxonomy and functional stratification in other urogenital-associated bacteria.},
}

@article {pmid42323366,
year = {2026},
author = {Huang, H and Zhang, T and Sun, P and Chen, Y and Zhao, D and Zhang, X and Ma, H},
title = {A high-quality chromosome-level genome assembly of Ficus carica cultivar 'Green Peel'.},
journal = {Scientific data},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41597-026-07646-w},
pmid = {42323366},
issn = {2052-4463},
support = {Grant No. 1002-69199007//key research project for fig development of Weiyuan County, China./ ; },
abstract = {Fig (Ficus carica L.) is an early-domesticated fruit crop of high cultural and economic value. However, high-quality genome resources for evolutionary and genetic diversity studies remain limited. Here we report a high-quality, chromosome-level genome assembly for fig cv. 'Green Peel' generated with Oxford Nanopore long reads and Hi-C data, and polished with Illumina reads. The final assembly is 306.83 Mb and comprises 13 pseudo-chromosomes, with a contig N50 of 5.77 Mb. Read mapping supported the assembly, with mapping rate and genome coverage exceeding 99.5%, and BUSCO completeness reaching 98.1%. Annotation predicted 27,036 protein-coding genes with 97.3% BUSCO completeness, together with 1,303 transcription factors and 2,080 non-coding RNAs. Comparative analyses with Ficus pumila characterized gene family expansion and duplication modes and identified 131.43 Mb of structural variation. This dataset provides a valuable resource for trait mapping, genome-assisted breeding, and future fig pan-genome studies.},
}

@article {pmid42326372,
year = {2026},
author = {Islam, SI and Shahed, K and Parvin, MM and Sanjida, S},
title = {Hidden in the Pangenome? Machine Learning-Driven Discovery of Antimicrobial Potential in Corynebacterium glutamicum.},
journal = {Bioinformatics and biology insights},
volume = {20},
number = {},
pages = {11779322261461933},
pmid = {42326372},
issn = {1177-9322},
abstract = {Antimicrobial resistance poses an increasing global challenge, driving the urgent need for alternative strategies to identify novel therapeutic agents. Microbial natural products encoded by biosynthetic gene clusters (BGCs) remain among the most promising sources of bioactive compounds. Although Corynebacterium glutamicum is best known as an industrial producer of amino acids, its potential as a producer of secondary metabolites has not been comprehensively assessed, despite the availability of numerous high-quality genome sequences. In this study, we carried out a comparative pangenome analysis of 36 complete C. glutamicum genomes and systematically mined for BGCs to explore the species' biosynthetic repertoire. Our analysis revealed variation in BGC content among strains, with several isolates harboring more hybrid clusters than others, suggesting metabolic diversity across the species. In addition to conserved terpene biosynthetic pathways, we detected polyketide-associated clusters not previously reported in C. glutamicum, expanding its recognized metabolic potential. RiPP-like clusters, including Lactococcin-related variants, were also identified, highlighting an underexplored reservoir of antimicrobials. To prioritize candidates for future validation, Support Vector Machine, Random Forest, and k-Nearest Neighbor models were trained on Composition, Transition, and Distribution (CTD) physicochemical sequence features and applied to genome-mined small open reading frames. The models demonstrated strong predictive performance, with the Support Vector Machine achieving the highest accuracy (84.1%), F1 score (83.8%), and area under the ROC curve (AUC = 0.920). After removing duplicate sequence IDs and applying a high-confidence AMP probability threshold (≥0.95), 18 unique AMP-like candidates were identified as promising. Overall, this study presents C. glutamicum as a promising source of bioactive metabolite candidates and shows how pangenome-scale mining combined with machine learning can support antimicrobial peptide discovery while still requiring experimental validation of the predicted leads.},
}

@article {pmid42326405,
year = {2026},
author = {Aziz, T and Fizza, C and Zhao, L and Yang, Z and Alahmari, LA and Alshehri, F and Shami, A and Mansouri, OA},
title = {Genomic insights into probiotic potential and metabolic adapability of food derived Lactiplantibacillus plantarum and Pediococcus acidilactici.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1847858},
pmid = {42326405},
issn = {1664-302X},
abstract = {INTRODUCTION: Probiotic lactic acid bacteria derived from agro-food sources play a pivotal role in promoting human health and advancing functional food development, however the genomic determinants underlying their adaptive versatility and probiotic functionality remain insufficiently characterized.

METHODOLOGY: The current study employs a comparative genomics framework to evaluate the genetic diversity, metabolic plasticity, and evolutionary trajectories of Lactiplantibacillus plantarum (HMX2 and NMGL2) and Pediococcus acidilactici (BCB1H), aiming to elucidate the molecular determinants and functional mechanisms governing their probiotic efficacy. Various genomic analysis, including whole genome sequencing, genome annotation, average nucleotide identity (ANI), and Pan Genome analysis, was performed to assess the mechanism of adaptations and genomic variations.

RESULTS: NMGL2 exhibited the largest genome of 3.46 Mb among these strains, while having a total of 3,402 genes together with plasmids, which enhanced metabolic flexibility. A total of 59 genes were found which are likely linked with the functions of probiotic-related traits such as adhesion, immune modulation, and stress response. Although 59 genes were identified to be linked to probiotic characteristics like adhesion, immunomodulation, and stress resistance, the identified genomic features reflect the potential functionality and do not necessarily result in phenotypes.

DISCUSSION: The effectiveness of a probiotic is assessed based on more than just the availability of these genes; their regulation and expression are crucial. L. plantarum HMX2 and NMGL2 are found to be the same species but differ slightly at the genetic level, as indicated by the ANI between the two bacteria, which stands at 99.80%. On the other hand, the ANI between P. acidilactici BCB1H and L. plantarum is only around 68%, which is way less than 95% and thus indicates that they are not of different species. This shows that the two genera diverged at an early stage in their evolutionary path. Through Pan-Genome analysis, gene clusters were identified for varying levels of adaptability. The genetic features of L. plantarum NMGL2 suggest potential adaptability for industrial and probiotic use, though these predictions require experimental validation. The combined studies on transcriptomics and metablomics are required for the validation of functional potential in the genomics of these studies.},
}

@article {pmid42327276,
year = {2026},
author = {Rocha, J and Lou, RN and De Lima Adam, C and Hebbar, P and Ferguson, S and Bolognini, D and Killilea, A and Hoekzema, K and Guarracino, A and Deng, Y and Soranzo, N and Paten, B and Garrison, E and Pollen, A and Eichler, E and Rohlfs, R and Mitchell, M and Sudmant, PH},
title = {A Pan-pangenome illuminates complex structural variation and selection in humans, chimpanzees, and bonobos.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.06.06.730619},
pmid = {42327276},
issn = {2692-8205},
abstract = {Complete, haplotype-resolved genome assemblies have provided unprecedented insight into the evolution of structurally complex, rapidly evolving regions of human genomes; however, population-scale pangenome resources of our closest relatives, chimpanzees and bonobos (genus, Pan), are necessary to ascertain the origins and evolutionary context of these loci. Here, we sequence and assemble 58 haplotypes from four distinct Pan clades to high contiguity (median contig NG50=54 Mb), including eight near-T2T genomes. These genomes reveal previously intractable genetic variation increasing estimates of genome-wide genetic diversity 6-37% across populations compared to short-read estimates. We identify recurrent structural polymorphisms across species impacting genes associated with immune response and host-pathogen interaction and find that structural variants (SVs) are 170- to 260-fold more likely than single nucleotide variants (SNVs) to exhibit high-impact effects across species. Contrasting SV patterns across primates we find that transposable element mutation rates differ by as much as threefold between species. We show that human disease-associated short tandem repeat (TR) loci have uniquely expanded in humans sensitizing our species to these TR-expansion disorders. Physically phased haplotypes enable reconstruction of genome-wide genealogical histories, uncovering ancient, functional genetic variation maintained by balancing selection, as well as signatures of recent adaptation in chimpanzee subspecies. Several malaria-associated loci exhibit ancient structural polymorphism, including the African great ape-specific glycophorin (GYP) gene expansion. We characterize the sequence, structure, and composition of diverse glycophorin haplotypes in humans and chimpanzees. We identify independent malaria-protective GYPA-B fusion events in humans and novel chimpanzee glycophorin genes resulting from both ancient and recent fusion events demonstrating parallel adaptations to pathogen resistance across hominins. Together, our resource highlights the critical importance of nonhuman primate population-scale pangenomics for understanding the evolution of complex genome structures and the biodiversity of our endangered closest living relatives.},
}

@article {pmid42328694,
year = {2026},
author = {Lu, Y and Ma, R and Wang, B and Wu, J and Chong, Y and Gao, Z and Deng, W},
title = {Integrative Advances in Equine Genomics From Reference Assemblies to Evolutionary History and Key Traits.},
journal = {Evolutionary applications},
volume = {19},
number = {6},
pages = {e70283},
pmid = {42328694},
issn = {1752-4571},
abstract = {Horses are major domestic animals and cultural symbols that have accompanied humans for millennia. They underpin transport, agriculture, warfare and sport, and also provide a model for studying domestication, complex traits and adaptive evolution. Recent work in equine genomics has now generated a much richer picture of how these roles are grounded in the genome. This review brings together advances in several connected areas: the construction and refinement of reference assemblies; genomic reconstructions of origin, domestication and dispersal; global and regional patterns of genetic diversity; and the molecular basis of key traits such as athletic performance, coat colour, body size, environmental adaptation and inherited myopathies. The transition from EquCab1.0/2.0 to EquCab3.0 and a complete Y-chromosome sequence illustrates how long-read and Hi-C/T2T data improve genome completeness and the representation of complex regions. On this foundation, high-coverage resequencing of ancient and modern horses has clarified the geographical core of domestication in the Volga-Don region, the Bronze Age replacement of earlier domestic lineages and the long-term impact of human management on behaviour, conformation and mobility. Comparative analyses of mitochondrial DNA, Y-chromosomal haplotypes and autosomal runs of homozygosity further reveal a combination of diverse maternal lineages, highly constrained paternal lineages and breed-specific inbreeding histories. Against this background, studies of representative traits show how association signals, functional experiments and clinical evidence can be linked to practical tools for breeding and health management, for example through MSTN-guided performance profiling, EPAS1-based altitude adaptation and molecular tests for GYS1, SCN4A, PPIB and MYH1. We conclude by considering how telomere-to-telomere assemblies, pangenome resources, improved structural-variant detection and closer integration between population genomics and functional studies may support conservation, health surveillance and molecular breeding in diverse horse populations.},
}

@article {pmid42317557,
year = {2026},
author = {Uscanga Junco, A and Díaz-González, L and Taboada, B},
title = {K-FluDB: a novel K-mer-based database for enhanced genomic surveillance of Influenza A viruses.},
journal = {Bioinformatics advances},
volume = {6},
number = {1},
pages = {vbaf254},
pmid = {42317557},
issn = {2635-0041},
abstract = {MOTIVATION: Influenza A viruses frequently cause seasonal outbreaks and pandemics due to their genetic diversity and reassortment potential. Existing genomic surveillance tools face challenges with redundant databases, delaying subtype identification and obscuring reassortment dynamics. K-FluDB, a novel k-mer-based database, addresses these issues by enhancing subtype identification, capturing genomic diversity, and assisting in the detection of reassortment events critical for understanding viral evolution and improving outbreak proactive measures.

RESULTS: K-FluDB provides a comprehensive pangenome for Influenza A, including complete and subtype-specific subsequences from 50 subtype combinations across all 18 hemagglutinin (HA) and 11 neuraminidase (NA) subtypes. Achieving 99.64% compression, K-FluDB eliminates redundancy while preserving essential information. Validation with real-world datasets showed high recovery indices (up to 96.24%) and correct subtype prediction ratios (exceeding 99% for HA and NA). K-FluDB also assists in the detection of reassortment events.

Three versions of K-FluDB, optimized for read lengths of 75, 150, and 300 nucleotides, are freely available at https://zenodo.org/records/17203072, and the source code is available at https://github.com/usjunco/pangen.},
}

@article {pmid42319064,
year = {2026},
author = {Goh, YX and Hepp, S and Cummings, KJ and Wiedmann, M and Liao, J},
title = {Motile and non-motile Listeria species adopt distinct ecological and evolutionary strategies to achieve broad geographic ranges across soil ecosystems.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wrag158},
pmid = {42319064},
issn = {1751-7370},
abstract = {Broad geographic ranges often reflect ecological versatility and are associated with lower extinction risk. Motility is a key physiological and ecological trait in bacteria. However, how some motile and non-motile bacteria achieve broad geographic ranges remains poorly understood. Here, we analyzed the genomes of 141 Listeria welshimeri and 90 L. booriae isolates systematically obtained from soils, representing widespread motile and non-motile species, respectively. We show that L. welshimeri lacks clear phylogeographic structure, suggesting minimal geographic barriers to dispersal. Its wide distribution is likely associated with enhanced motility and effective host colonization that facilitate wildlife-driven dispersal, particularly by regional-terrestrial birds. This pattern is supported by positive selection on flagellar and chemotaxis genes, strong associations with wildlife movement patterns, and close genomic relatedness between soil and wild bird isolates. In contrast, L. booriae displays clade endemism and a strong distance-decay relationship, suggesting dispersal limitation. Despite lacking a dispersal advantage, L. booriae's wide distribution appears to be linked to genomic flexibility and metabolic versatility that support adaptation to diverse environmental conditions, especially those shaped by iron concentration and precipitation. This is evidenced by its large, open pangenome characterized by abundant and diverse metabolic pathways and broad substrates utilization capacity; pronounced positive selection on genes involved in inorganic ion, amino acid, and coenzyme transport and metabolism; and strong associations between gene richness and abiotic factors as well as bacterial community composition. These findings suggest distinct genomic foundations and ecological and evolutionary mechanisms underlying the success of motile and non-motile cosmopolitan bacteria in soil ecosystems.},
}

@article {pmid42312341,
year = {2026},
author = {Zakeri, M and Brown, NK and Gagie, T and Langmead, B},
title = {Movi 2: Fast and Space-Efficient Queries on Pangenomes.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btag362},
pmid = {42312341},
issn = {1367-4811},
abstract = {MOTIVATION: Space-efficient compressed indexing methods are critical for pangenomics and for avoiding reference bias. In the Movi study, we implemented the move-structure index, highlighting its locality-of-reference and speed. However, Movi had a high memory footprint compared to other compressed indexes.

RESULTS: Here we introduce Movi 2 and describe new methods that greatly reduce size and memory footprint of move structure-based indexes. The most compressed version of Movi 2 reduces the Movi index's space footprint more than fivefold. We also introduce sampling approaches that enable trade-offs between query and space efficiency. To demonstrate, we show that Movi 2 achieves advantageous time and space tradeoffs when applied to large pangenome collections, including both the first and second releases of the Human Pangenome Reference Consortium (HPRC) collection, the latter of which spans over 460 human haplotypes. We show that Movi 2 dominates prior methods on both speed and memory footprint, including both r-index-based and our previous move-structure-based method.

The methods we developed for Movi 2 are publicly available at https://github.com/mohsenzakeri/Movi.},
}

@article {pmid42313853,
year = {2026},
author = {Mukharjee, SK and Hasan, MF and Sikdar, B},
title = {Whole-genome characterization of halotolerant Enterobacter roggenkampii OSNO4 and its potential for climate-resilient agriculture.},
journal = {PloS one},
volume = {21},
number = {6},
pages = {e0351555},
doi = {10.1371/journal.pone.0351555},
pmid = {42313853},
issn = {1932-6203},
mesh = {*Enterobacter/genetics ; Rhizosphere ; *Genome, Bacterial ; Oryza/microbiology/growth & development ; *Agriculture/methods ; Phylogeny ; Salt Tolerance/genetics ; Soil Microbiology ; Whole Genome Sequencing ; Salinity ; Indoleacetic Acids/metabolism ; },
abstract = {Plant growth-promoting rhizobacteria (PGPR) represent an eco-friendly strategy to improve crop yield under abiotic stress conditions. This study aimed to perform a comprehensive genomic and functional profiling of a halotolerant rhizobacterium to evaluate its multi-trait plant growth-promoting (PGP) potential and its precise contribution to mitigating salinity stress for climate-resilient agriculture. In the present study, 24 (8.5%) rhizobacterial isolates showed phosphate-solubilizing activity out of 283 isolated bacteria from rice rhizosphere. From these, strain OSNO4 was selected for detailed evaluation. The isolate demonstrated phosphate solubilization (solubilization index: 1.22) and potassium solubilization, indole-3-acetic acid (IAA) production (38.34 µg/ml), nitrogen fixation, siderophore and ammonia production, protease activity, and biofilm formation in vitro. Additionally, it showed tolerance to salinity (10% NaCl), drought (20% PEG 6000), temperature (45 °C), and a broad pH range. Strain OSNO4 further suppressed the growth of phytopathogenic fungi Fusarium concentricum by 54.23%. Whole-genome sequencing analysis identified the strain as Enterobacter roggenkampii (ANI 98.2%, dDDH 85.7%), with a 4.67 Mb genome harboring total 4,546 predicted genes and diverse functional subsystems. Comprehensive genomic study further revealed the presence of genes linked to nutrient mobilization, phytohormone biosynthesis, abiotic stress tolerance, and antifungal activity. Six biosynthetic gene clusters, including siderophore-related and putatively novel clusters were also identified. Pan-genome analysis revealed an open genome structure with high flexibility and genetic variability. Under salinity stress, OSNO4 inoculation significantly improved rice seed germination (52.22% to 85.56% at 100 mM NaCl; 42.22% to 72.22% at 150 mM NaCl), root and shoot development, and biomass accumulation compared to uninoculated controls. The strain also showed broad antibiotic susceptibility and non-hemolytic phenotype, suggesting its biosafe nature. In summary, these data demonstrate that E. roggenkampii OSNO4 possesses a robust repertoire of genomic determinants and functional capabilities, establishing it as a highly potent bioinoculant for deployment in climate-resilient and sustainable agroecosystems.},
}

*Enterobacter/genetics
Rhizosphere
*Genome, Bacterial
Oryza/microbiology/growth & development
*Agriculture/methods
Phylogeny
Salt Tolerance/genetics
Soil Microbiology
Whole Genome Sequencing
Salinity
Indoleacetic Acids/metabolism

@article {pmid42314250,
year = {2026},
author = {Phaophu, P and Orsi, RH and Wirth, SE and Gray, AS and Wiedmann, M and Chaturongakul, S},
title = {Genomic insights into Salmonella Rissen from Thailand: Prophage substitution in phase 2 flagellar-encoding region and hotspot of multidrug resistance genes in the chromosome.},
journal = {International journal of food microbiology},
volume = {459},
number = {},
pages = {111903},
doi = {10.1016/j.ijfoodmicro.2026.111903},
pmid = {42314250},
issn = {1879-3460},
abstract = {Salmonella Rissen (6,7,14:f,g:-) has recently emerged in Thailand; a high prevalence of multidrug resistance (MDR) has been reported. S. Rissen is a monophasic serotype, lacking phase 1 or phase 2 flagellin, and its biphasic ancestor remains unknown. In this study, pangenome SNP analysis was performed on 119 Salmonella serotypes (i.e., 325 genomes) that share antigens with S. Rissen, including those with the 6,7,14 O antigen, f,g phase 1 flagellin antigen, or the absence of phase 2 antigen, as well as those in closely related clades. Although the biphasic ancestor of S. Rissen was not determined, all 109 Thai S. Rissen isolates belong to S. Rissen lineage A, which shares a most recent common ancestor (MRCA) with another monophasic serotype, S. Oranienburg lineage G; the antigenic formula (6,7,14:m,t:[z57]; [z57]), however, indicates that some rare S. Oranienburg isolates are biphasic. Thai S. Rissen isolates not only lack the phase 2 flagellin gene, fljB, but the entire fljAB-hin region is replaced by a SEN8-like prophage. However, unlike MDR Salmonella Typhimurium monophasic variant, 4,[5],12:i:- in which AMR genes replace the fljAB-hin region, AMR genes in S. Rissen were detected within the tnsD-silE region in the chromosome, suggesting an alternative AMR hotspot in S. Rissen. This tnsD-silE region was reported as a part of the Tn6777 transposon that can translocate from the S. Rissen chromosome to a plasmid, suggesting mobility of AMR genes in S. Rissen genomes. This study highlights the single emergence and clonal expansion of Thai MDR S. Rissen isolates and the plasticity of S. Rissen genomes.},
}

@article {pmid42316246,
year = {2026},
author = {Eskandar, P and Paten, B and Sirén, J},
title = {Lossless pangenome indexing using tag arrays.},
journal = {Algorithms for molecular biology : AMB},
volume = {},
number = {},
pages = {},
doi = {10.1186/s13015-026-00301-4},
pmid = {42316246},
issn = {1748-7188},
abstract = {Pangenome graphs represent the genomic variation by encoding multiple haplotypes within a unified graph structure. However, efficient and lossless indexing of such structures remains challenging due to the scale and complexity of pangenomic data. We present a practical and scalable indexing framework based on tag arrays, which annotate positions in the Burrows-Wheeler transform (BWT) with graph coordinates. Our method extends the FM-index with a run-length compressed tag structure that enables efficient retrieval of all unique graph locations where a query pattern appears. We introduce a novel construction algorithm that combines unique k-mers, graph-based extensions, and haplotype traversal to compute the tag array in a memory-efficient manner. To support large genomes, we process each chromosome independently and then merge the results into a unified index using properties of the multi-string BWT and r-index. Our evaluation on the HPRC graphs demonstrates that the tag array structure compresses effectively, scales well with added haplotypes, and preserves accurate mapping information across diverse regions of the genome. This indexing method enables lossless and haplotype-aware querying in complex pangenomes and offers a practical indexing layer to develop scalable aligners and downstream graph-based analysis tools. The index additionally supports efficient one-to-all coordinate translation, enabling any interval on a haplotype to be mapped to its corresponding intervals across all other haplotypes in the graph.},
}

@article {pmid42309578,
year = {2026},
author = {Raval, K and Shekh, S and Prajapati, B and Jangbari, N and Rana, A and Gupta, S and Joshi, C and Joshi, M},
title = {Understanding the probiotic potential of a healthy human vaginal flora, Lactobacillus gasseri K9: genomic and in vitro aspects.},
journal = {Journal, genetic engineering & biotechnology},
volume = {24},
number = {2},
pages = {100671},
pmid = {42309578},
issn = {2090-5920},
abstract = {Lactobacillus gasseri K9, isolated from a healthy vaginal sample, underwent detailed genomic and phenotypic evaluation. The strain demonstrated strong stress tolerance, adhesion, aggregation, and biofilm formation, while ensuring safety with no mucin degradation or hemolysis. Antimicrobial compounds, pathogen inhibition, and resilience in simulated gastrointestinal conditions highlight its potential role in maintaining vaginal homeostasis and functioning as a safe, effective probiotic candidate. The entire genome sequence of L. gasseri K9, with an emphasis on studying its probiotic potential and safety profile. The complete genome of L. gasseri K9, with a genome size of 1,872,894 base pairs, comprises 1,779 genes, exhibiting an average G + C content of 34.83%. Comprehensive genomic analysis identified genes associated with stress adaptation, carbohydrate utilization, cell adhesion, secondary metabolite biosynthesis, and other probiotic traits through multiple annotation platforms, including RAST, KEGG, COG, CAZyme, BAGEL4, and AntiSMASH. The detection of CRISPR arrays with broad phage-targeting patterns suggests that this strain possesses robust phage defence capabilities. Additionally, the absence of virulence factors and antibiotic resistance determinants, verified using CARD, ResFinder, and VFDB, underscores the safety profile of K9 as a promising probiotic candidate. Pangenome analysis of 278 L. gasseri genomes identified 12 distinctive sequences shared only by the K9 and Q9001 strains, setting them apart from all other isolates. Most of these sequences encoded hypothetical proteins, with one linked to a phage-related HK97-gp10 family protein. This study presents detailed genomic and functional characterization of L. gasseri K9, revealing unique genetic traits, strong probiotic functions, and a robust safety profile. Its role in maintaining vaginal health suggests strong potential for incorporation into probiotic formulations targeting women's wellness. Overall, these findings highlight K9 as a promising strain for next-generation vaginal probiotics.},
}

@article {pmid42309587,
year = {2026},
author = {Okuofu, SI and Osei, EK and Leech, J and Kenny, JG and O'Flaherty, V and McAuliffe, O},
title = {Comparative genomic analysis of poly-γ-glutamic acid producing Bacillus licheniformis strains isolated from dairy products.},
journal = {Journal, genetic engineering & biotechnology},
volume = {24},
number = {2},
pages = {100682},
pmid = {42309587},
issn = {2090-5920},
abstract = {Poly-γ-glutamic acid (γ-PGA) is a valuable biopolymer with diverse industrial applications, produced naturally by several Bacillus species. The dairy environment is an under-explored niche for identifying efficient, food-grade γ-PGA producers. In this study, four legacy dairy-derived Bacillus licheniformis strains: DPC3803, DPC6338, DPC6339, and DPC6340, producing high γ-PGA titres were examined using whole genome sequencing (WGS) and comparative genomic analysis to evaluate their suitability for future industrial applications. The genomes ranged from 4.19 to 4.29 Mb with an average GC content of 45.8-46.2%. Pangenome analysis of the four strains, together with 51 publicly available B. licheniformis genomes, identified 12,415 gene clusters, of which 18.9% and 81.1% were core and accessory genes respectively. Average nucleotide identity (ANI) analysis demonstrated >99% sequence identity among all 55B. licheniformis genomes, despite their isolation from diverse environments, indicating strong genomic conservation within the species. Experimental validation confirmed γ-PGA production by all four strains, with maximum titres (g/L) of 43.27 ± 1.49, 59.54 ± 4.33, 27.93 ± 1.87, and 47.74 ± 0.19 for DPC3803, DPC6338, DPC6339, and DPC6340, respectively. Genomic screening revealed multiple γ-PGA metabolism and CAZyme-encoding genes, as well as unique secondary metabolite clusters with potential antimicrobial activity. Although no plasmids or virulence factors were detected, twenty-one prophages were identified, sharing no significant homology with known cultivated phages, and a single β-lactamase gene suggested intrinsic resistance to β-lactams. These findings highlight the genomic and functional potential of these dairy-derived B. licheniformis as efficient, food-grade candidates for industrial γ-PGA production.},
}

@article {pmid42310362,
year = {2026},
author = {Jehma, N and Chaichana, N and Suwannasin, S and Dechathai, T and Singkhamanan, K and Wonglapsuwan, M and Pomwised, R and Surachat, K},
title = {Comparative genomics reveals population structure and functional differentiation in Limosilactobacillus fermentum.},
journal = {Scientific reports},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41598-026-56807-9},
pmid = {42310362},
issn = {2045-2322},
support = {B13F670076//the National Science, Research and Innovation Fund (NSRF) through the Program Management Unit for Human Resources and Institutional Development, Research and Innovation/ ; },
abstract = {Limosilactobacillus fermentum is a widely distributed lactic acid bacterium frequently detected in fermented foods and host-associated microbiota, yet its global genomic diversity and functional variability remain insufficiently characterized. Here, we performed a large-scale comparative genomic analysis of 336 high-quality L. fermentum genomes curated from public databases. Species identity was validated using average nucleotide identity (ANI), and population structure was examined using pairwise ANI comparisons together with Mash-based phylogenetic reconstruction. Clustering at ≥ 99% ANI resolved the dataset into 15 genomic clusters, with four dominant lineages comprising the majority of genomes. Pangenome reconstruction identified 5,853 gene clusters, including 1,325 core genes (22.6%) and a large accessory component dominated by low-frequency genes. Heap's law modeling (λ = 0.19) indicated a weakly open pangenome, suggesting ongoing gene acquisition as additional genomes are sampled. Functional annotation revealed that core genes were primarily associated with essential cellular processes, whereas accessory genes were enriched in carbohydrate metabolism, membrane-associated functions, and defense-related systems. Variation in carbohydrate-active enzymes (CAZymes), transport systems, and stress-response genes was observed across lineages, indicating strain-level functional diversity. Although genomes from human and food sources were broadly distributed across phylogenetic lineages, multivariate analysis showed that gene-content variation was more strongly associated with genomic lineage than with isolation source. These results provide a population genomic framework for understanding genomic diversity and functional potential in L. fermentum.},
}

@article {pmid42310524,
year = {2026},
author = {Mukharjee, SK and Hasan, MF and Sikdar, B},
title = {Comparative genomic insights into a plant-associated Enterobacter adelaidei strain isolated from the taro rhizosphere.},
journal = {BMC genomics},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12864-026-13081-3},
pmid = {42310524},
issn = {1471-2164},
abstract = {BACKGROUND: Enterobacter adelaidei, an extensively drug resistant strain, was recently described and isolated from hospital wastewater in Australia. However, its distribution in plant-associated environments has not been documented yet. This study presents a whole-genome-based characterization of E. adelaidei strain CELK12, isolated from the rhizosphere of taro (Colocasia esculenta L.) and its plant growth-promoting performance under saline stress conditions.

RESULTS: Genomic analyses confirmed the strain as E. adelaidei (ANI: 96.49%, dDDH: 71.90%). The genome of strain CELK12 (4.68 Mb, 53.5% GC content) was predicted to contain key genes involved in nutrient acquisition (gcd, pqqC, amtB), phytohormone biosynthesis (ipdC, trpE), iron transport (entB, feoB), and stress tolerance (otsA, katG, sodA, oxyR). These genomic features suggest the potential for rhizosphere competence and plant-beneficial activity of strain CELK12. Comparative genomics suggested a trend toward an open pan-genome among the selected strains (Heap's law α = 0.11) and strain-specific divergences in secondary metabolite production, consistent with possible environmental adaptation. Genomic and phenotypic assessments revealed that while CELK12 carries certain chromosomally encoded resistance genes, it lacks plasmids, shows no hemolytic activity, and exhibits broad phenotypic susceptibility to major antibiotic classes. The seed germination and pot investigations confirmed significant enhancement of rice growth under saline conditions (100-150 mM NaCl) following CELK12 treatment.

CONCLUSION: The findings of this study expand the known ecological range of E. adelaidei to include plant-associated niches and provide the first genomic predictions and experimental evidence of potential plant-beneficial traits within this specific lineage of the species.},
}

@article {pmid42311380,
year = {2026},
author = {Liang, L and Shang, Z and Liu, A and Lin, D and Wu, N and Jing, J and Yang, Z and Liu, W},
title = {Genomic characterization of a pathogenic Bacillus licheniformis strain LSDY01: deciphering its genetic diversity and virulence-associated traits.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1815181},
pmid = {42311380},
issn = {1664-302X},
abstract = {BACKGROUND: Bacillus licheniformis is an opportunistic pathogen in clinical settings. However, the emergence of clinical strains carrying horizontally acquired virulence determinants, including chromosomal genomic islands harboring yopX, a putative type IV secretion system (T4SS), and plasmids bearing toxin-antitoxin systems and additional virulence factors, poses a significant challenge to diagnosis and treatment. Moreover, the genetic basis of the pathogenicity of clinical isolates has not been comprehensively studied.

METHODS: A pathogenic B. licheniformis strain (LSDY01) isolated from a skin infection was subjected to whole-genome sequencing and comparative genomic analyses. Phylogenetic reconstruction, pan-genome analysis, and detailed characterization of plasmid and chromosomal virulence determinants were performed. Antimicrobial susceptibility testing was performed according to standardized guidelines. Biofilm formation assays were also conducted. The cytotoxic effect of LSDY01 on HEK293 cells was evaluated using a CCK-8 assay.

RESULTS: Strain LSDY01 belonged to B. licheniformis ST20, differing by only one allele from the prevalent ST3. Its closest relatives were the Daqu-derived strains CP143961.1 and CP143962.1. A unique horizontally acquired genomic island (~157 27 kb, GC 33.03%) and a putative type IV secretion system (T4SS) gene cluster were identified on the chromosome of this strain. A novel plasmid (pLSDY01), which is highly similar to environmental plasmids, harbors yopX, a toxin-antitoxin system, pilT, and a pistol ribozyme. LSDY01 was susceptible to imipenem and vancomycin but resistant to penicillin, erythromycin, and chloramphenicol. The CCK-8 assay revealed a non-significant trend toward reduced HEK293 cell viability after co-culture with LSDY01 (p = 0.0545 at 2 h of CCK-8 incubation).

CONCLUSION: Our findings suggest that horizontal gene transfer, including plasmid acquisition and potential phage integration, may have enabled B. licheniformis to evolve into a pathogen, highlighting the need to reassess the safety of traditionally non-pathogenic microbes.},
}

@article {pmid42296129,
year = {2026},
author = {Strysko, J and Hu, W and Mochankana, K and John-Thubuka, J and Zankere, T and Gopolang, B and Theiller, E and Jones, SM and Tembo, CV and Ntereke, TD and Gatonye, T and Lechiile, K and Keatholetswe, T and Bianco, C and Coffin, SE and McGann, C and Bittinger, K and Lautenbach, E and Mannathoko, N and Mokomane, M and Mosepele, M and Richard-Greenblatt, M and Nakstad, B and Goldfarb, DM and Planet, PJ and Moustafa, AM},
title = {Integrated epidemiologic investigation and genomic confirmation of a Klebsiella pneumoniae neonatal sepsis outbreak in Botswana.},
journal = {PLOS global public health},
volume = {6},
number = {6},
pages = {e0006468},
pmid = {42296129},
issn = {2767-3375},
abstract = {Klebsiella pneumoniae (Kpn) is a major cause of infant mortality worldwide, with most transmission occurring among hospitalized neonates in low- and middle-income countries where infections caused by multidrug-resistant Kpn (MDR-Kpn) are increasingly common. We hypothesized that integrating laboratory surveillance for neonatal colonization and infection, real-time epidemiologic investigations, and whole-genome sequencing (WGS) could identify transmission pathways to guide targeted infection prevention and control (IPC) strategies. We conducted Kpn surveillance in a 36-bed neonatal unit in Botswana over 12 months (2022-2023). WGS was performed on Kpn isolates from bloodstream infections (BSIs), and MDR-Kpn isolates collected from environmental sampling during outbreaks and twice-monthly colonization screenings (skin and perirectal swabs) using culture media selective for MDR-Kpn (CHROMagar Extended-spectrum beta-lactamase [ESBL]/SuperCarba). WGS data were analyzed using multilocus sequence typing (MLST), pangenome and reference-based single-nucleotide polymorphism (SNP) analyses, and Bayesian phylogenetics. We identified 55 Kpn BSIs during the 12-month surveillance period and the median prevalence of MDR-Kpn colonization was 28%. Kpn was recovered from multi-use intravenous (IV) fluid bags during a Kpn outbreak (41 BSIs, 10 deaths), which was controlled by implementing a 24-hour discard policy for IV medications. Among 270 Kpn isolates available (28 BSI, 232 colonizing, 10 environmental [six IV fluid, four sink drain]), WGS confirmed over half of BSI genomes (n = 17) and all six IV fluid isolates belonged to ST1414 and were closely related (<25 SNPs). The ST1414 clone was susceptible to third-generation cephalosporins and was therefore not detected during MDR-Kpn colonization screening. This study reinforces the value of integrating WGS with real-time epidemiologic investigations to understand transmission dynamics and guide IPC. Colonization surveillance focused solely on MDR-Kpn may overlook drug-susceptible but outbreak-prone strains.},
}

@article {pmid42297684,
year = {2026},
author = {Zhang, X and Smith, DR},
title = {Synteny detection, visualization, and its trending applications.},
journal = {Trends in plant science},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.tplants.2026.05.010},
pmid = {42297684},
issn = {1878-4372},
abstract = {Synteny detection analyses facilitate comparative genomics, especially when investigating gene duplications, genomic rearrangements, and ancient whole-genome duplication events. In recent years, major advancements have been seen in synteny detection and visualization. In this forum article, we explore the trending role that these tools play in gene-duplication detection, pangenome graph construction, and deep-learning-based cross-species transcript prediction.},
}

@article {pmid42304007,
year = {2026},
author = {Alam, SA and Karmakar, D and Khan, B and Mandal, R and Bhattacharya, S and Ahmed, I and Maruyama, F and Saha, P},
title = {Polyphasic taxonomic characterization of Brachybacterium netajii sp. nov., a metabolically versatile bacterium isolated from the river Ganges, India.},
journal = {Scientific reports},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41598-026-56775-0},
pmid = {42304007},
issn = {2045-2322},
abstract = {A comprehensive polyphasic taxonomic strategy was applied to the systematic characterization of strain DNPG3[T], which was isolated from the river Ganges, Hooghly, West Bengal, India. The Gram-positive, halotolerant, heavy-metal-tolerant strain exhibited the ability to degrade p-nitrophenol (PNP). Cellular fatty acid analysis revealed that the predominant components were anteiso-C15:0 (24.61%), C11:0 (21.06%), iso-C16:0 (11.89%), C16:0 (11.58%), and anteiso-C17:0 (11.24%). Notably, the presence of C11:0, C10:0 2-OH as major fatty acids differentiate strain DNPG3[T] from its closely related members of the genus Brachybacterium. The predominant respiratory quinone was identified as menaquinone-7 (MK-7). Analysis of 16S rRNA gene sequence indicated that B. zhongshanense strain JB[T] was the closest relative of DNPG3[T], sharing 97.08% sequence similarity. Genome-based ANI value calculated using the EzBioCloud server revealed that B. zhongshanense JCM 15471[T] was the closest genomic relative (85.49%). These values were further substantiated by digital DNA-DNA hybridization (dDDH) estimates calculated using the GGDC server. Taxonomic assignment using the GTDB database further indicated that strain DNPG3[T] constitutes a previously unrecognized species within the genus Brachybacterium. Genome analysis of strain DNPG3[T] identified eleven genomic islands, along with a rich repertoire of 194 carbohydrate-active enzyme (CAZyme) families, comprising 95 glycoside hydrolases and 53 glycosyltransferases. In addition, five biosynthetic gene clusters were detected. Collectively, these genomic features indicate the involvement of horizontal gene transfer events and highlighted the pronounced metabolic versatility of the strain, underscoring its potential for industrial enzyme production and secondary metabolite biosynthesis. Pan-genome analysis further indicates that the Brachybacterium pan-genome is open, reflecting substantial genetic diversity and ongoing gene acquisition within the genus. Comprehensive biochemical, physiological, chemotaxonomic, and phylogenetic analyses supported the assignment of strain DNPG3[T] to the genus Brachybacterium while clearly distinguishing it from all currently described species within the genus. Accordingly, strain DNPG3[T] was proposed to represent a novel species, for which the name Brachybacterium netajii sp. nov. is suggested. The type strain was DNPG3[T] (= MTCC13125[T]).},
}

@article {pmid42305012,
year = {2026},
author = {Ali, A and Waldbieser, GC and Youngblood, RC and Wheeler, PA and Scheffler, BE and Willis, S and Narum, SR and Thorgaard, GH and Salem, M and Palti, Y},
title = {De Novo Genome Assemblies of Four Rainbow Trout Genetic Lines Reveal Structural Variants in Pursuit of a Pangenome Reference.},
journal = {Molecular ecology resources},
volume = {26},
number = {5},
pages = {e70167},
pmid = {42305012},
issn = {1755-0998},
support = {8082-10600-002-000D//Agricultural Research Service/ ; },
mesh = {Animals ; *Oncorhynchus mykiss/genetics/classification ; *Genome ; *Genomic Structural Variation ; Sequence Analysis, DNA ; *Genetic Variation ; },
abstract = {Rainbow trout (Oncorhynchus mykiss) exhibit extensive genomic diversity shaped by domestication, life history and geographic origin. To advance the development of a comprehensive pangenome reference, we present new de novo genome assemblies of two genetically and ecologically distinct lines: Whale Rock (WR; wild, landlocked, Central California) and Keithley Creek (KC; wild, resident, interior Columbia Basin), along with the previously published assemblies of the Arlee (domesticated, Northern California) and Swanson (semi-domesticated, resident, Alaska) lines. All assemblies provide nearly complete coverage of known genes (BUSCO 95.8%-99.7%) and are similar in genome size (~2.3 Gb), with scaffold N50 values between 3.4 Mb (KC) and 52.4 Mb (Swanson). Comparative whole-genome alignments revealed high sequence conservation (97%-98% identity) among assemblies, but also evidence of extensive structural variation of at least 50 bp in length. Structural variant (SV) profiling identified tens of thousands of deletions, insertions and complex rearrangements largely in noncoding sequences. In an initial assessment of the utility of having multiple de novo genome assemblies for rainbow trout, we found that two strains (Arlee and Swanson; domesticated) share SVs enriched in genes linked with growth, reproduction and adaptation to domestication, such as GTP binding and ECM-receptor interaction. In comparison, the other two strains (WR and KC; wild origin) share SVs associated with reproductive timing, such as the GnRH signalling pathway. Both Arlee and WR also have unique SVs potentially related to their geographic origin and unique life history. Additionally, we identified SVs in key regions, such as a QTL for fillet yield on Omy17 and the maturation-associated six6/erβ-gphb5 locus on Omy25q, suggesting the importance of considering SVs when investigating the genomics of complex traits. Together, these assemblies and comparative analyses establish a foundation for a rainbow trout pangenome reference, illuminating how they can be utilized to reveal the structural genomic basis of domestication, adaptation, and other complex traits in O. mykiss.},
}

Animals
*Oncorhynchus mykiss/genetics/classification
*Genome
*Genomic Structural Variation
Sequence Analysis, DNA
*Genetic Variation

@article {pmid42308415,
year = {2026},
author = {Giebler, M and Luna, E and Nicolli, C and Martin, F and Pedrozo, R and Joglekar, P and Huerta, AI and Jia, Y and Leach, JE},
title = {Distinct Lineages of Pantoea ananatis Associated with Rice Differ in Toxin Biosynthesis Gene Content and Host Specialization.},
journal = {Phytopathology},
volume = {},
number = {},
pages = {},
doi = {10.1094/PHYTO-04-26-0138-R},
pmid = {42308415},
issn = {0031-949X},
abstract = {Pantoea ananatis has recently emerged as a causal agent of Pantoea leaf blight (PLB) and Pantoea panicle blight (PPB) of rice in the United States, raising concerns about its potential impact on rice production. Despite increasing reports of the disease, mechanisms underlying host specialization and virulence within this pathosystem remain poorly understood. Here, we combined comparative genomics and in-planta assays to investigate population structure and virulence determinants among rice-associated P. ananatis strains. Average nucleotide identity analysis of P. ananatis genomes resolved two lineages with contrasting host associations. One lineage, composed of strains recovered almost exclusively from rice, lacked the HiVir operon responsible for synthesis of the phosphonate toxin pantaphos. A second, broadly distributed lineage included P. ananatis isolated from diverse hosts, including rice, and many contained the HiVir operon. HiVir-mediated pantaphos production induced necrotic symptom development, but was not required for bacterial replication within rice tissue. Accordingly, strains lacking HiVir, including those from the rice-associated lineage and targeted mutants, exhibited reduced necrosis while achieving bacterial population sizes comparable to wild-type generalist strains during infection of rice. Conversely, host-range experiments showed that rice-associated strains colonized onion tissue less than generalist strains, consistent with evolutionary specialization for rice. Comparative pangenome analysis supported the separation of lineages and identified hundreds of lineage-specific genes that may underpin host associations. These findings demonstrate that P. ananatis populations associated with rice comprise distinct evolutionary lineages with differing genomic features and virulence strategies and reveal a decoupling between symptom development and bacterial proliferation during infection of rice.},
}

@article {pmid42294704,
year = {2026},
author = {He, Y and Wang, X and Li, S and Zhang, C and Xu, M and Zhou, Y and Sanford, RA and Liang, R and Zhu, Y and Yang, D and Dan, L and Mao, X and Zhang, L and Sun, W and Jiang, Y and Hu, Y and Jiang, Z and Li, Y and Song, W and Hu, N and Zhao, L and Dong, Y and Shi, L},
title = {Ecological plasticity of Halanaerobium microorganisms across terrestrial saline to hypersaline subsurface environments.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0138126},
doi = {10.1128/spectrum.01381-26},
pmid = {42294704},
issn = {2165-0497},
abstract = {UNLABELLED: Members of the genus Halanaerobium are widely distributed in hypersaline environments, including oil and gas reservoirs, and saline lake sediment. However, a comprehensive understanding of their physiological traits, metabolic capacities, adaptive strategies, and biogeography remains limited. In this study, a strictly anaerobic and halophilic strain, H. saccharolyticum_B KY39 was isolated from produced water in the Zhongyuan Oilfield, China. Strain KY39 grew at 20-45°C, 2-30% salinity, pH 5.3-9.0, and up to 50 MPa hydrostatic pressure. It could ferment various carbohydrates (e.g., glucose, xylose, sucrose, and maltose) or use mannitol and pyruvate as electron donors under Fe(III)-reducing conditions. Comparative genomic analyses of 31 high-quality Halanaerobium strains revealed an open pangenome. Genes involved in osmotic and pressure stress responses, including those related to osmoprotectant biosynthesis and ion transport, were highly conserved. The thiosulfate sulfurtransferase (TST) gene, responsible for converting thiosulfate to sulfite, was universally present. Notably, compared to the strains from saline lakes, those from oil and gas reservoirs possessed larger genomes and harbored a broader repertoire of genes related to peptidoglycan biosynthesis, nitrogen fixation, sulfur metabolism, biofilm formation, and carbohydrate uptake, suggesting enhanced metabolic flexibility and environmental adaptation. Moreover, a survey of the available metagenomes revealed that Halanaerobium species were globally distributed across diverse environments exhibiting a broader salinity range. In addition to oil and gas reservoirs and saline lakes, they also widely reside in soils, fermented foods, and marine ecosystems. Collectively, these findings advance the systematic understanding of ecological plasticity and metabolic versatility of Halanaerobium, shedding light on their ecological roles and potential industrial impacts.

IMPORTANCE: Members of the genus Halanaerobium are prominent inhabitants of surface and deep subsurface hypersaline environments, yet their ecological roles and adaptive strategies remain poorly understood. Here, through the isolation of a novel strain from the production fluid of an oil field combined with comparative genomic analyses across the genus, we revealed the metabolic versatility, stress tolerance, and global distribution of Halanaerobium. Our findings underscore the ecological plasticity, functional diversity, and niche differentiation within this genus, providing fundamental insights into its potential industrial and environmental applications.},
}

@article {pmid40856885,
year = {2025},
author = {Meng, X and Fu, Y and Qi, Y and Jin, Z and Li, P and Sang, Y},
title = {Genome-wide association studies in forestry.},
journal = {Molecular biology reports},
volume = {52},
number = {1},
pages = {848},
pmid = {40856885},
issn = {1573-4978},
support = {2024LZGC025;ZR2024QC117//Shandong Provincial Department of Science and Technolog/ ; 2024LZGC025;ZR2024QC117//Shandong Provincial Department of Science and Technolog/ ; },
abstract = {The extended generation cycles and high genomic heterozygosity of forest trees have long hindered investigations into the genetic basis of quantitative traits, impeding progress in molecular breeding applications. Recent advances in genome-wide association studies (GWAS), empowered by next-generation sequencing technologies, now offer unprecedented opportunities to dissect complex trait architectures and identify causal allelic variants in tree species. This review critically examines the evolving role of GWAS in forest tree genetics, emphasizing its achievements in mapping quantitative trait loci (QTLs) and characterizing functionally relevant alleles for breeding. We further analyze the unresolved challenge of “missing heritability” in tree GWAS and propose integrative approaches to mitigate this gap, including the development of high-throughput phenotyping platforms for capturing trait dynamics across environments, synergistic integration of multi-omics data (genomics, transcriptomics, epigenomics) via advanced computational models, and construction of pan-genome references to resolve structural variations in highly heterozygous genomes. Finally, we discuss the translational potential of GWAS-driven strategies in modern forestry, particularly for enhancing marker-assisted selection of climate-adaptive traits, optimizing wood properties, and shortening domestication timelines. By bridging methodological innovations with practical breeding applications, this synthesis aims to accelerate the translation of genetic discoveries into sustainable forest management practices.},
}

@article {pmid41553525,
year = {2026},
author = {Karthik, K and Anbazhagan, S and Chitra, MA and Sridhar, R},
title = {Isolation, whole genome sequencing, and comparative genomics of Corynebacterium pseudotuberculosis to identify biovar ovis specific biomarkers.},
journal = {Molecular biology reports},
volume = {53},
number = {1},
pages = {301},
pmid = {41553525},
issn = {1573-4978},
abstract = {BACKGROUND: Corynebacterium pseudotuberculosis, a gram-positive bacterium, causes caseous lymphadenitis in small ruminants (biovar ovis) and ulcerative lymphangitis in equines (biovar equi). Growing reports of C. pseudotuberculosis from various animals, including cattle, buffalo, pigs, deer, Iberian ibex, camel, llama, and alpaca. Since the host range is expanding, there is a need for biovar-specific identification of the organism. Hence, the present study was focused towards comparative genomics of C. pseudotuberculosis to identify biovar ovis specific markers. METHODS AND RESULTS: Corynebacterium pseudotuberculosis TN_CUL_1 was isolated from suspected cases of caseous lymphadenitis from small ruminants in an organized farm in Tamil Nadu, India. The C. pseudotuberculosis TN_CUL_1 strain was whole genome sequenced and was used for comparative genome analysis along with 157 C. pseudotuberculosis strains available in the NCBI genome database. Whole genome phylogeny showed a clear distinction between biovars equi and ovis, and the TN_CUL_1 strain was clustering in biovar ovis. Virulence gene pld was predicted in all the strains, while 9 strains isolated from buffalo had the tox gene coding for diphtheria toxin. Pangenome analysis indicated that the genome structure of C. pseudotuberculosis to be closed in nature as the pangenome curve attained a plateau. Biovar-specific genes like narT, narK, narY, narG, narX, moaC, moaA, mobA, and moeZ were predicted only in biovar equi, while yhaP was predicted only in biovar ovis strains. Further BLAST analysis indicated that the yhap gene coding for the ABC superfamily ATP binding cassette transporter binding protein was found only in biovar ovis strains. CONCLUSIONS: The study concludes that the yhap gene can be used as a biovar ovis-specific molecular marker.},
}

@article {pmid41843261,
year = {2026},
author = {Radhakrishnan, V and Prajna, L and Devarajan, B and Jeyakanthan, J},
title = {Whole-genome sequencing and analysis of Nocardia veterana isolates from keratitis patients.},
journal = {Molecular genetics and genomics : MGG},
volume = {301},
number = {1},
pages = {},
pmid = {41843261},
issn = {1617-4623},
abstract = {In this study, we conducted whole-genome sequencing and comparative genomic analysis of two Nocardia veterana isolates (JJAEH1 and JJAEH2) from severe corneal ulcers to elucidate their pathogenic potential, antimicrobial resistance determinants, and genomic features associated with steroid–antibiotic interactions in keratitis. Genome assemblies, annotated with RAST and Prokka, ranged from 7.2 to 7.5 Mb with a GC content of ~ 68.2%. Pan-genome analysis (Panaroo) revealed conserved virulence determinants, including fbpA, fbpB, and fbpC (fibronectin-binding mycolyltransferases), stp (serine/threonine phosphatase), type VII secretion system genes (eccA3, eccB3, espG1), and siderophore-associated iron acquisition genes (mbtA, viuB), indicating roles in host adherence, invasion, and immune evasion. Both isolates also harbored steroid-responsive genes (choD, kstD, kshA/B, fadD, hsaA–D) and two-component systems (senX3–regX3, pdtaS, arlR), linking metabolic adaptation to antibiotic tolerance. JJAEH1 exhibited broad susceptibility, whereas JJAEH2 was multidrug-resistant, carrying multiple efflux pumps (mdtL, mdtH). Heavy metal resistance determinants for mercury (merR) and arsenic (arsA, arsB, arsC, acr3) were present in both isolates, suggesting enhanced survival environments and co-selection of resistance traits. Average nucleotide identity analysis confirmed > 99.99% similarity to N. veterana. In vitro assays demonstrated reduced amikacin susceptibility in the presence of prednisolone, suggesting potential corticosteroid-associated modulation. Overall, we provide genomic and phenotypic insights into virulence, antimicrobial resistance, and steroid responsiveness in ocular N. veterana and identify a modest decrease in amikacin inhibition in the presence of prednisolone in vitro, supporting further functional investigation of steroid–antibiotic interactions in nocardial keratitis.},
}

@article {pmid41879963,
year = {2026},
author = {Kim, H and Lee, HH and Song, S and Haque, MA and Razzak, MA and Jang, MJ and Maki, K and Ku, S},
title = {Genome-Informed Characterization of Lactiplantibacillus plantarum ND88 with Inhibitory Activity against Representative Oral Pathogens.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {41879963},
issn = {1867-1314},
support = {VFIC23-1001//Texas A&M AgriLife Research VFIC/ ; 8000-0//USDA Hatch/ ; },
abstract = {Lactiplantibacillus plantarum ND88, a human-derived strain with putative probiotic-associated traits, was taxonomically confirmed by whole-genome sequencing and comparative genomic analysis. Average nucleotide identity (ANI) analysis showed that ND88 clustered within the L. plantarum species group, sharing > 98% identity with representative reference genomes. Comparative pangenome analysis of ND88 and 20 L. plantarum genomes revealed multiple ND88-specific and enriched orthogroups, indicating strain-level genomic diversification. Genome-informed Pfam domain annotation predicted several adhesion-associated features, including repeated MucBP domains and predicted surface-associated proteins carrying LPxTG motifs and secretion signals. Consistent with this, L. plantarum ND88 exhibited approximately 2.2-fold greater adhesion to intestinal epithelial cells compared with Lactocaseibacillus rhamnosus GG. The strain exhibited strong acid tolerance, maintaining approximately 98% survival at pH 3. Genome mining using BAGEL4 identified a plantaricin bacteriocin biosynthetic locus, providing a genetic basis for antimicrobial activity. Correspondingly, ND88 inhibited representative oral pathogens, reducing adhesion by 29.8–57.4% and growth by 47.7–97.1% in co-culture assays. Genome-based safety assessment indicated the absence of virulence-associated genes and acquired antimicrobial resistance determinants. Although the minimum inhibitory concentrations for gentamicin and kanamycin were above EFSA microbiological cut-off values, no genomic evidence of acquired resistance was detected. ND88 also showed no hemolytic activity, the absence of bile salt hydrolase activity, and low D-lactate production (0.0068 g/L), comparable to GRAS-certified L. plantarum strains. These results demonstrate that ND88 is a genetically safe strain with experimentally supported probiotic-associated traits.},
}

@article {pmid41886233,
year = {2026},
author = {Che, Y and Mao, Y and Li, M and Liu, X and Li, H and Yan, G and Gao, H and Bai, X and Sun, Z and Liu, X and Wang, D},
title = {Vaginal Probiotic Potential of the Nomadic Species Limosilactobacacillus fermentum Under Dysbiotic Vaginal Conditions: Population Genomic Insights and Anti-Pathogenic Efficacy of a Vaginal Isolate VL9.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {41886233},
issn = {1867-1314},
support = {32570220//National Natural Science Foundation of China/ ; 2025ZD01900100//Prevention and Control of Emerging and Major Infectious Diseases-National Science and Technology Major Project/ ; NPRC-32//National Science and Technology Infrastructure of China/ ; },
abstract = {Vaginal disorders are prevalent health concerns primarily driven by vaginal dysbiosis, yet antibiotic treatment often leads to recurrence and disruption of the vaginal microbiota. Probiotic therapy is promising, but current development focuses mainly on host-adapted species, which are reported to be sensitive to dynamic vaginal pH and nutrient. To broaden the candidate repertoire, we investigated whether Limosilactobacillus fermentum, a “nomadic” species that transitions between hosts and environments, could serve as a vaginal probiotic. We conducted a population-scale genomic evaluation of the vaginal probiotic potential of L. fermentum (211 public genomes and 2 vaginal isolates) and confirmed its nomadic genomic features: an open pangenome, larger genome size and GC content, and a lack of geographic- or source-specific clustering in the phylogenetic tree. Functional annotation identified 35 core genes associated with vaginal probiotic traits, 9 KEGG pathways enriched in metabolism and 51 CAZyme subfamilies. Virulence and antibiotic resistance genes were rare. A representative strain, VL9, isolated from a healthy vagina, was validated in vitro, exhibiting robust growth across pH 3–7, stable lactic acid production (13.0 g/L in nutrient-rich medium and 5.4 g/L in oligotrophic medium), high cell surface hydrophobicity (> 95%), and broad inhibition against 14 of 15 pathogens, with > 98% growth inhibition at 104–106 CFU/mL against Candida albicans. VL9 also exhibited low MICs to 11 antibiotics (≤ 4 µg/mL) and non-hemolytic activity. Our findings provide insight into broadening candidate species for vaginal probiotics and position VL9 as a potential strain for further validation.},
}

@article {pmid41940992,
year = {2026},
author = {Vijayakumar, S and Ramaiah, S},
title = {WGS-based in silico analysis of clinically-associated Klebsiella pneumoniae genomes: insights into antimicrobial resistance, virulence determinants, and plasmid dynamics.},
journal = {Molecular genetics and genomics : MGG},
volume = {301},
number = {1},
pages = {},
pmid = {41940992},
issn = {1617-4623},
support = {IRIS ID: 2021-11889//Indian Council of Medical Research/ ; },
abstract = {Klebsiella pneumoniae (K. pneumoniae) is a leading cause of nosocomial infections and is increasingly linked to multidrug resistance and hypervirulence. Comprehensive genomic characterization is essential for understanding the emergence of multidrug resistant and hypervirulent K. pneumoniae strains. Therefore, this study comprehensively investigated the resistome, virulome, and plasmidome profile of 310 clinical K. pneumoniae genomes to elucidate genetic determinants of virulence and antimicrobial resistance (AMR). Multi-locus sequence typing identified 86 sequence types, with ST11 being the predominant lineage associated with KL64 and KL47 capsular types. Resistome analysis detected widespread β-lactam resistance genes, with most genomes carrying extended-spectrum β-lactamases (ESBLs). Carbapenemases namely KPC and NDM were detected in 31% and 15% of genomes respectively. The co-occurrence of multiple ESBLs (CTX-M, SHV, and TEM) within the same genome was observed in nearly half of the genomes (146/310), suggesting a strong genetic determinant of resistance to third-generation cephalosporins. ST23 genomes showed an increased abundance of siderophore-associated virulence genes, including aerobactin, yersiniabactin, and colibactin. Plasmidome profiling revealed that several resistance determinants were found on conjugative plasmids encoding β-lactamase and aminoglycoside resistance genes which underscores their potential for horizontal dissemination. The open pan-genome exhibited substantial diversity, with accessory genome enriched in mobilome-associated genes (14.6%) compared to core genome (0.1%). Overall, these results reveal the extensive genomic plasticity of K. pneumoniae and widespread distribution of resistance and virulence determinants, largely mediated by mobile genetic elements. These findings are pivotal for guiding future genomic surveillance and to support the development of targeted therapeutic approaches to combat AMR.},
}

@article {pmid41998453,
year = {2026},
author = {Harini, AC and Sundaresan, AK and Ramakrishnan, J},
title = {Klebsiella pneumoniae in the global AMR: resistance mechanisms and genomic adaptation.},
journal = {World journal of microbiology & biotechnology},
volume = {42},
number = {5},
pages = {},
pmid = {41998453},
issn = {1573-0972},
abstract = {Antimicrobial Resistance (AMR) represents a defining crisis of modern healthcare, severely limiting therapeutic options and driving a global increase in clinical mortality. Central to this crisis is Klebsiella pneumoniae, a ubiquitous gut commensal that has evolved into a formidable opportunistic pathogen through its remarkable ability to transition from a harmless organism to a hypervirulent, Multidrug-Resistant (MDR) threat. This review examines that pathogenic transition, emphasizing the dangerous convergence of virulence and resistance traits particularly within carbapenem-resistant lineages. The bacterium leverages an expansive “open” pangenome and immense genetic plasticity to act as a primary trafficker of AMR genes. We detail the molecular mechanisms underlying resistance across nearly all antibiotic classes including β-lactams, aminoglycosides, and last-resort polymyxins driven by enzymatic degradation, target modification, and sophisticated efflux systems. Beyond clinical antibiotic pressure, the review explores how non-antibiotic drivers, such as environmental stressors, biocide exposure, and heavy metals, accelerate AMR evolution through cross-resistance and novel epigenetic adaptations. The rapid dissemination of these resistance determinants is facilitated by a robust toolkit of Horizontal Gene Transfer (HGT), including transposons, integrons, plasmid replicons, and bacteriophage-mediated transduction. Finally, this review evaluates the current therapeutic landscape, addressing the challenges of the drug development pipeline while highlighting emerging interventions such as novel β-lactam/β-lactamase inhibitor combinations, phage therapy, and anti-virulence strategies. Understanding this interplay between genomic evolution and ecological drivers is critical for designing a unified stewardship framework and effective interventions to curb the global AMR crisis.},
}

@article {pmid42036542,
year = {2026},
author = {Permpoonpattana, P and Islam, SI and Khang, LTP and Dangsawat, O and Sangsawad, P and Yeh, SD and Phetduang, K and Therdtatha, P and Onsanit, S and Linh, NV},
title = {Comprehensive characterization and genome-resolved insights into the probiotic potential of Bacillus sp. KNSH39 isolated from Litopenaeus vannamei intestine.},
journal = {World journal of microbiology & biotechnology},
volume = {42},
number = {5},
pages = {},
pmid = {42036542},
issn = {1573-0972},
abstract = {Probiotic Bacillus species are being investigated as sustainable interventions to enhance health and disease resilience in aquaculture. However, the functional basis, biosafety profile, and genomic determinants of probiotic suitability in shrimp gut-associated Bacillus strains remain insufficiently characterized. In this study, a Bacillus strain (KNSH39) isolated from the intestine of Pacific white shrimp (Litopenaeus vannamei) was evaluated using integrated phenotypic, functional, and genome-resolved approaches. Classical assays assessed morphology, sporulation, antibiotic susceptibility, gastrointestinal tolerance, storage stability, and antibacterial activity of cell-free supernatant under thermal and pH stress. Hybrid whole-genome sequencing using Oxford Nanopore Technologies and Illumina platforms enabled high-quality assembly, followed by comprehensive functional annotation, mobilome analysis, biosynthetic gene cluster prediction, and comparative genomics. KNSH39 exhibited strong sporulation capacity (98.04%), a non-hemolytic phenotype, high tolerance to acidic and bile conditions, and formulation-dependent storage stability, with gel-bead encapsulation markedly improving viability. Cell-free supernatant inhibited Streptococcus agalactiae and Aeromonas hydrophila in a concentration-, time-, temperature-, and pH-dependent manner, retaining activity after heating to 120 °C. Genome analysis revealed a 5.49 Mb Bacillus cereus–group genome with complete central metabolic pathways, extensive quorum sensing systems, diverse secondary metabolite biosynthetic gene clusters, and an open pangenome structure. Collectively, these findings suggest that KNSH39 strain presents as a promising aquaculture probiotic candidate, exhibiting thermally stable antibacterial potential and well-defined genomic attributes.},
}

@article {pmid42284716,
year = {2026},
author = {Lin, X and Guo, S and Yang, R and Xu, W and Cheng, D and Wang, Z and Li, W and Segbo, S and Zhou, P and Huang, X and Ni, Z and Shi, T and Gao, Z},
title = {Pan-genome analysis of the P-type ATPase gene family in Prunus mume and functional characterization of PmAHA3 in organic acid accumulation.},
journal = {Plant physiology and biochemistry : PPB},
volume = {237},
number = {},
pages = {111457},
doi = {10.1016/j.plaphy.2026.111457},
pmid = {42284716},
issn = {1873-2690},
abstract = {Organic acid accumulation is a key determinant of fruit flavor and processing quality in Prunus mume, yet its underlying molecular mechanisms remain poorly understood. P-type ATPases are membrane proteins that drive the active transport of ions and molecules via ATP hydrolysis and play important roles in organic acid accumulation However, their genome-wide features and functions in P. mume remain poorly understood. Here, 49 P-type ATPase genes were identified from the P. mume pan-genome, including 29 core, 6 near-core, 11 dispensable, and 3 private genes, and classified into six subfamilies. Dispersed and whole-genome duplication were the major force driving gene family expansion, and most genes experienced strong negative selection. Expression profiling identified the P3A-type gene PmAHA3 as highly expressed in fruit, with vacuolar membrane localization. Both transient RNAi silencing in fruit and CRISPR/Cas9 knockout in callus significantly reduced the contents of malic and citric acid, demonstrating their roles in organic acid accumulation. These results provide insight into the evolution and function of P-type ATPases, offering potential targets for improving fruit quality.},
}

@article {pmid42286102,
year = {2026},
author = {Li, C and Zhao, P},
title = {Pan-genome cloning and expression analysis of S-RNase homologous gene in SI and SC of different tomato species.},
journal = {Scientific reports},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41598-026-57781-y},
pmid = {42286102},
issn = {2045-2322},
support = {NSBSJJ2018032//Initial Scientific Research Fund for Dr in Nanchang Normal University/ ; GJJ181081//Science and Technology Research Project of Jiangxi Provincial Department of Education/ ; },
abstract = {Flowering plants encode polymorphic ribonucleases (S-RNases) that determine the self-incompatibility (SI) phenotype of the style. The pan-genome cloning and expression analysis of the S-RNase homologous genes in SI and self-compatibility (SC) lines of different tomato species have not been reported. In this study, partial sequences of cDNA and DNA of the S-RNase homologous gene (designated ZS) were obtained from S. pimpinellifolium, S. Lycopersicum, S. habrochaites and S. chilense which included SI lines and SC lines. Tissue-specific expression of the S-RNase gene was detected using semi-quantitative RT-PCR and quantitative real-time PCR. We selected 6 ZS genes (two come from the SI lines and four come from SC lines) which come from different tomato species mentioned in this paper to research. ZS genes were exclusively in styles and there were significant differences in expression level of the different tomato species. The expression level of the ZS genes in the styles of the SI tomato clade S. chilense was higher than that in the SC tomato clades S. pimpinellifolium and S. lycopersicum. And, the SC tomato clade S. habrochaites, in which the expression level of the ZS genes was even higher than that in the SI tomato clade S. chilense. The outcomes presented in this research provide the basis for future deeper investigation of the molecular mechanism of SI in tomato.},
}

@article {pmid42286142,
year = {2026},
author = {Chen, S and Liu, X and Qu, S and Song, Y and Chai, K and Liu, H and Zhang, Y and Xia, Z and Li, X and Wang, J and Zhang, M and Li, H and Chen, GB and Maliepaard, C and Zhang, X},
title = {A k-mer-based genome-wide association study approach empowering gene mining in polyploids.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {42286142},
issn = {1546-1718},
abstract = {Genome-wide association studies in complex polyploids are hindered by genotyping ambiguity and allele dosage complexity. Here we present KMERIA, a k-mer-based framework specifically designed to address these challenges, enabling efficient genotyping and robust association mapping in complex polyploid genomes. Rigorous benchmarking with simulated and empirical datasets demonstrates that KMERIA surpasses existing methods in accuracy and statistical power. By applying KMERIA to 290 wild sugarcane (Saccharum spontaneum) accessions and integrating a 15-accession graph pangenome to capture structural variations, we identified new genes regulating sucrose biosynthesis (SsMGT) and tillering (for example, SsERF14, SsNGA5, SsNAC, SsARF8, SsLOG and SsSCR). These findings elucidate the genetic architecture of yield-related traits and provide actionable targets for sugarcane breeding. Collectively, KMERIA bridges a critical methodological gap in polyploid genomics, while our graph-pangenome integration provides a powerful framework for deciphering genotype-phenotype relationships in crops with complex architectures.},
}

@article {pmid42287231,
year = {2026},
author = {Bundurus, IA and Ștef, L and Gundogdu, O and Pet, I and Corcionivoschi, N and Balta, I},
title = {Genomic Features of Campylobacter jejuni and Campylobacter coli Poultry Isolates from the Western Part of Romania.},
journal = {Foodborne pathogens and disease},
volume = {},
number = {},
pages = {15353141261460746},
doi = {10.1177/15353141261460746},
pmid = {42287231},
issn = {1556-7125},
abstract = {Campylobacter jejuni and Campylobacter coli are leading causes of foodborne gastroenteritis worldwide, with poultry representing the primary reservoir for human infection. Understanding species-specific differences in virulence-associated features, antimicrobial resistance genes, and population structure is essential for assessing public health risks and guiding surveillance strategies. A total of 26 Campylobacter isolates (22 C. coli and 4 C. jejuni) were recovered in 2023 from poultry caeca collected from farms in north-western, central-western, and south-western Romania. Species identification and detection of the hcp gene, a marker of the type VI secretion system (T6SS), were performed using multiplex PCR. Multilocus sequence typing (MLST) based on seven housekeeping genes was performed to evaluate genetic diversity and population structure. The hcp gene was detected exclusively in C. jejuni isolates, indicating that it was detected only in C. jejuni within this collection of the primary T6SS component. Both species shared a broad set of core virulence genes related to motility, colonization, quorum sensing, adhesion, and surface polysaccharide biosynthesis, while notable differences were observed in accessory virulence gene profiles. Genes associated with antibiotic resistance, including the tetracycline resistance gene tet(O) and multiple efflux-related determinants, were frequently detected in both species. MLST analysis revealed high genetic diversity, with most isolates not assignable to previously defined sequence types, consistent with an open pan-genome and substantial genomic plasticity. These findings feature clear differences between C. jejuni and C. coli in the distribution of virulence markers, while validating the widespread presence of antimicrobial resistance genes in poultry-associated isolates. This study highlights the adaptive potential of Campylobacter and underscores the need to advance molecular surveillance to monitor virulence and antimicrobial resistance risks relevant to animal and human health.},
}

@article {pmid42287752,
year = {2026},
author = {Chen, Z and Cui, M},
title = {Genomic insights into antimicrobial resistance and isolation source classification of Cronobacter sakazakii from infant and toddler food in the United States.},
journal = {Letters in applied microbiology},
volume = {},
number = {},
pages = {},
doi = {10.1093/lambio/ovag054},
pmid = {42287752},
issn = {1472-765X},
abstract = {Cronobacter sakazakii is an opportunistic foodborne pathogen associated with severe infections in infants, linked to powdered infant formula and related products. We conducted genomic profiling of C. sakazakii (n = 209) from infant and toddler food in the United States, comprising all publicly available genomes for this source, through the integration of antimicrobial resistance (AMR), plasmid replicon, phylogenetic, and pan-genome analyses. We further applied a machine learning (ML)-driven isolation source classification approach based on pan-genome features to distinguish food and clinical isolates. AMR analysis revealed a conserved resistome dominated by three β-lactam resistance genes (blaCSA, blaCSA-1, and blaCSA-2). Independent co-occurrence and pairwise association analyses of AMR genes and plasmid replicons indicated sparse and gene-specific relationships, suggesting that observed AMR patterns were more consistent with conserved resistance determinants than extensive plasmid-mediated dissemination. Phylogenetic analysis identified two major clades, while pan-genome assessment demonstrated an open genome dominated by accessory genes. Using gene presence/absence profiles, a random forest classifier achieved high accuracy in distinguishing food and clinical isolates, highlighting the classification power of pan-genome signatures within the dataset. These findings provide insights into the genomic structure of food-associated C. sakazakii and the utility of integrating comparative genomics with ML for food safety surveillance.},
}

@article {pmid42288159,
year = {2026},
author = {Zhuang, W and Pan, P and Zhang, H and Chen, K and Guan, J and Yu, S and Fan, H and Xu, C and Liao, M and Zhang, J},
title = {TraC promotes complement evasion of Salmonella enterica serovar Choleraesuis by recruiting host C4b-binding protein.},
journal = {Microbial pathogenesis},
volume = {218},
number = {},
pages = {108616},
doi = {10.1016/j.micpath.2026.108616},
pmid = {42288159},
issn = {1096-1208},
abstract = {Salmonella enterica serovar Choleraesuis (S. Choleraesuis) is a highly invasive zoonotic pathogen responsible for severe systemic infections, in which the complement system constitutes a major innate defense against circulating bacteria. However, the molecular basis underlying resistance of S. Choleraesuis to complement-mediated killing remains poorly understood. Here, whole-genome sequencing and pan-genome comparative analyses of S. Choleraesuis isolates exhibiting distinct serum-resistance phenotypes identified five candidate genes associated with enhanced serum survival. Among them, traC emerged as the most critical determinant. In S. Choleraesuis, deletion of traC reduced serum resistance by 73%, impaired adhesion and invasion to HeLa cell by 55% and 71%, respectively, and decreased intracellular persistence in RAW264.7 cells by 24-55%. In a murine infection model, loss of traC markedly attenuated systemic dissemination, resulting in significant reduction of bacterial loads in blood (80%), liver (32%) and spleen (63%). Genetic complementation of traC restored these phenotypes to near wild-type levels. Mechanistically, TraC promoted recruitment of the host complement regulator C4b-binding protein (C4BP), which may facilitate factor I-mediated C3b degradation, resulting in reduced C3b deposition on the bacterial surface and enhanced bacterial survival under serum exposure. Co-immunoprecipitation and GST pull-down assays further supported an interaction between TraC and C4BP, likely involving the N-terminal region of TraC. Furthermore, ectopic expression of traC in low-invasive S. Choleraesuis was sufficient to enhance serum resistance and suppress complement deposition. Collectively, these findings suggest that TraC contributes to complement evasion in invasive S. Choleraesuis and may facilitate bacterial adaptation during bloodstream infection by modulating host complement regulation.},
}

@article {pmid42288821,
year = {2026},
author = {Qumar, S and Hamad, M and AbuOdeh, R and Khoder, G and Ahmed, N},
title = {Comprehensive genomic insights into lineages, virulence, and antibiotic resistance profiles of Campylobacter jejuni entailing a global One Health scenario.},
journal = {Gut pathogens},
volume = {},
number = {},
pages = {},
doi = {10.1186/s13099-026-00848-y},
pmid = {42288821},
issn = {1757-4749},
abstract = {BACKGROUND: Campylobacter species are among the leading causes of bacterial gastroenteritis worldwide, with poultry recognized as a major reservoir for several life-threatening foodborne and zoonotic infections. The overuse and possible misuse of antimicrobials in the livestock sector in different countries of the world have contributed to the emergence of multidrug-resistant Campylobacter jejuni strains with significant public health concerns. To better understand the evolution, host adaptation, and antimicrobial resistance (AMR) of C. jejuni, we performed a global comparative genomic analysis of 1,125 high-quality genomes from human and chicken hosts, including five newly sequenced isolates representing broiler chicken samples.

RESULTS: Pangenome analysis of 1,125 C. jejuni genomes identified 4,489 orthologous gene clusters, of which 1,360 constitute the conserved core genome. The findings indicate a weakly open pangenome approaching saturation, suggesting limited gene acquisition. Phylogenomic analysis revealed three major clades with limited geographic clustering, consistent with global dissemination and evolutionary divergence. Human isolates were distributed across all clades, whereas chicken isolates were primarily restricted to clade one. Sequence typing identified 290 STs across 30 clonal complexes, with ST-48 enriched in chickens while ST-50 predominated in humans, reflecting potential host adaptation and epidemiological structuring. All five in-house isolates were multidrug-resistant, producing extended-spectrum β-lactamases (ESBLs) that conferred β-lactam resistance. Additionally, three isolates exhibited resistance to macrolides and tetracycline, further underscoring their broad resistance phenotype. Genome-wide AMR profiling of 1,125 C. jejuni isolates identified 31 well-characterized resistance genes, including those encoding RND and MATE efflux systems, penicillin-binding proteins, and metallo- and serine-beta-lactamase families, underscoring their intrinsic role in the core resistome. The most common resistance mutations were gyrA p.T86I (60.3%) and 23S r2075A>G (4%), conferring resistance to fluoroquinolones and clarithromycin. Analysis of the 1,125 genomes, including the five new isolates, revealed 126 key virulence genes, with cytolethal distending toxin (cdtA, cdtB, and cdtC) and capsule biosynthesis clusters present in over 85% and 93% of the isolates, respectively.

CONCLUSION: These findings provide comprehensive insights into the evolution, transmission dynamics, host adaptation, antimicrobial resistance, and pathogenic potential of C. jejuni. Poultry serves as a critical reservoir contributing to the emergence and dissemination of high-risk, pathogenic, and drug-resistant lineages, underscoring the importance of monitoring and controlling AMR in livestock to protect public health.},
}

@article {pmid42291119,
year = {2026},
author = {Park, J and Jang, KB and Kang, MG and Kyung, J and Yoon, J and Ryu, S and Kim, Y},
title = {Comparative pangenome analysis of methanogenic archaea from diverse ecosystems reveals potential targets for methane mitigation in rumen microbiome.},
journal = {Journal of animal science and technology},
volume = {68},
number = {3},
pages = {935-953},
pmid = {42291119},
issn = {2055-0391},
abstract = {Rumen methanogenesis is a major biological contributor to methane emissions in ruminants, yet the extent to which functional markers align with taxonomic relationships and how genome content varies across habitats, remains poorly resolved. In this study, we integrated broad phylogenetic frameworks with pangenome-resolved analysis to characterize methanogenic archaea from diverse ecosystems, including seawater, freshwater, sewage, rumen, human gut, soil, and cockroach sources. By combining these insights with pangenome reconstruction and KEGG-based pathway mapping of methanogenesis, we reveal key evolutionary and functional patterns. Notably, phylogenies based on 16S rRNA and mcrA genes showed limited concordance: only two clades exhibited overlap between trees, with most clustering patterns lacking environmental specificity. This discrepancy reflects the deep conservation of 16S rRNA compared with the evolutionary plasticity of mcr genes, shaped by lateral gene transfer, gene loss, and pathway modularity. The pangenome comprised of 8,695 orthogroups across 71 genomes, with core and soft-core genes enriched in translation, amino acid metabolism, and coenzyme biosynthesis, while the shell contained many poorly annotated orthogroups, highlighting annotation gaps in archaeal genomes. KEGG analysis revealed habitat-specific signatures: rumen methanogens were notably depleted in genes of the acetyl-CoA pathway, whereas human gut methanogens lacked key cofactor biosynthesis modules, including those for coenzymes M, B, F420, and methanofuran. From rumen-derived shotgun metagenomes, we identified 53 methane-producing, 4 canonical methanogenic, 10 potential competitor, and 1 methanotrophic metagenome-assembled genomes based on functional gene content. Competitor candidates included nitrate-reducing and Wood-Ljungdahl pathway-utilizing acetogens, suggesting hydrogen redirection under high-hydrogen or inhibitor conditions. These findings support a functional marker strategy that integrates 16S rRNA with pathway-specific genes and a pangenome framework to enhance ecological interpretations of methanogens and to prioritize potential targets for methane mitigation in ruminants.},
}

@article {pmid42293541,
year = {2026},
author = {Calderon, G and Tamang, J and Woodfin, S and Prah, I and Hurdle, J and Xu, Y},
title = {Systematic analysis of the type VII secretion system in Streptococcus gallolyticus subsp. gallolyticus reveals genomic diversity and functional associations.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1844499},
pmid = {42293541},
issn = {1664-302X},
abstract = {Streptococcus gallolyticus subsp. gallolyticus (Sgg) is an opportunistic pathobiont associated with bacteremia, infective endocarditis, and colorectal cancer. However, the genomic diversity of this subspecies and the distribution of key virulence determinants, particularly the type VII secretion system (T7SS), remain poorly characterized. Here, we performed genomic analyses of 76 Sgg strains from diverse geographic and host origins. Core- and pan-genome analyses, multi locus sequence typing, and phylogenetic reconstruction revealed dominant sequence types (STs) that correlate with geographic origin or source of isolation. Furthermore, systematic characterization of the T7SS locus identified five new T7SS subtypes and demonstrated a strong association between T7SS subtype and ST. We further expanded the known repertoire of T7SS LXG domain-containing polymorphic toxins (LXG toxins) in Sgg substantially through genome-wide searches. Distinct distribution patterns were observed for the LXG toxins across the strains. Lastly, our data indicated that T7SS subtype was significantly associated with biofilm formation capacity of Sgg strains. Together, these findings advance our understanding of Sgg genomic diversity, reveal substantial lineage-associated variation in T7SS architecture and effector repertoires, and suggest a previously unrecognized connection between T7SS and biofilm formation in Sgg.},
}

@article {pmid42294060,
year = {2026},
author = {Purnhagen, K and Bartsch, D and Eckermann, K and Hubar-Kołodziejczyk, A and Lämke, J and Pallarz, S and Wesseler, J},
title = {Detection, identification and quantification of NGTs in EU authorization procedures - No solution without legislative change.},
journal = {Open research Europe},
volume = {6},
number = {},
pages = {168},
pmid = {42294060},
issn = {2732-5121},
abstract = {For the purposes of GMO authorisation, applicants are required to submit validated methods for the detection, identification and quantification (DIQ). For classical transgenic organisms, this requirement has proven workable. For products derived from New Genomic Techniques (NGTs), specifically those introducing small insertions and deletions (InDels) without foreign genetic material, it has not. NGT-induced genomic changes are frequently indistinguishable from naturally occurring mutations, making identification legally required but technically unachievable with currently available analytical tools. This open letter examines whether recently proposed DIQ methodologies, including genomic fingerprinting approaches based on single nucleotide variant (SNV) profiling, can bridge this gap. We find that while such approaches advance detection capabilities, they fall short of the identification and quantification standards demanded by EU law, for reasons such as the absence of universal pangenome datasets, the complexity of polyploid crop genomes, the loss of fingerprint integrity through elite line crossing, and the dependence of recombination rates on multiple species-specific factors. The mismatch between legal requirements and scientific feasibility has consequences for authorisation procedures, supply chain compliance, organic farming integrity, and international trade. We conclude that no purely technical solution is forthcoming and that legislative change is necessary. Aligning the EU's evidentiary standards with technical reality is a precondition for a functional and enforceable GMO authorisation system.},
}

@article {pmid42294646,
year = {2026},
author = {Lu, Y-F and Zuo, G-H and Zhi, X-Y},
title = {A structural backbone with sequestered plasticity organizes the Escherichia coli pangenome.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0020726},
doi = {10.1128/msystems.00207-26},
pmid = {42294646},
issn = {2379-5077},
abstract = {UNLABELLED: The exponential growth of microbial genomic data has made computational scalability the primary bottleneck in pangenome analysis because traditional alignment-based methods have quadratic complexity. We developed CVNet, an alignment-free orthology inference framework that uses composition vectors and Markov clustering. CVNet achieves near-linear scalability and high accuracy, enabling pangenome analysis across thousands of genomes. Applying it to 1,200 complete Escherichia coli genomes, we moved beyond the "bag-of-genes" approach to investigate the pangenome's spatial architecture. By constructing a genome-wide core gene synteny network from CVNet orthogroups, we revealed that core genes form a modular (Q = 0.9851) and asymmetric structural backbone, strongly biased toward the replication origin (oriC; KS test, D = 0.9133). Accessory genes and genomic islands are non-randomly sequestered within specific integration hotspots, with over 99% located between core genes connected by extremely weak syntenic links. These findings establish a structural backbone and sequestered plasticity model, demonstrating how E. coli maintains chromosomal integrity through a rigid scaffold that physically compartmentalizes genetic plasticity. This study thus presents CVNet as a scalable computational solution and introduces a spatial paradigm for understanding how bacterial genomes balance evolutionary stability with adaptive flexibility.

IMPORTANCE: Pangenome analysis has been constrained by alignment-based tools that do not scale and a "bag of genes" perspective that ignores chromosomal organization. We present CVNet, an alignment-free framework that enables near-linear scalability for orthology inference across thousands of genomes. Applying CVNet to 1,200 complete E. coli genomes, we discover that the chromosome is organized by a rigid core gene backbone, with accessory genes sequestered into discrete integration hotspots. This structural backbone and sequestered plasticity model reveals bacterial genomes as spatially organized systems in which stability and flexibility are physically compartmentalized, thereby establishing a framework for topological pangenomics.},
}

@article {pmid42026459,
year = {2026},
author = {Holman, DE and Klein, A and Keyster, M},
title = {Whole-genome characterization and analysis of Pantoea agglomerans R6: a genomic insight into its pathogenicity and resistance as a potential opportunistic plant pathogen.},
journal = {BMC genomics},
volume = {27},
number = {1},
pages = {},
pmid = {42026459},
issn = {1471-2164},
abstract = {UNLABELLED: Pantoea agglomerans is a Gram-negative bacterium increasingly recognised as an opportunistic pathogen, yet the molecular basis underpinning its host-interaction capacity remains poorly understood. Here, we report the whole-genome sequencing and integrative characterisation of P. agglomerans strain R6, isolated from Lactuca serriola. The 4.7 Mb draft genome (GC content 55.6%) encodes 4,349 genes, including secretion system components, siderophore clusters, adhesins, and multidrug efflux pumps. Comparative genomic analysis against previously characterised Pantoea strains revealed an open pan-genome shaped by horizontal gene transfer, with multiple genomic islands harbouring putative virulence- and resistance-associated loci. Notably, homologues of type VI secretion system components, iron acquisition systems, and stress response pathways suggest adaptive potential during host colonisation. Complementary phenotypic assays supported these genomic predictions, demonstrating swarming motility, biofilm formation, extracellular polysaccharide production, and enzymatic activities associated with host interaction in related strains. While R6 displayed susceptibility to β-lactams, its genomic repertoire indicates potential for adaptive resilience under selective pressure. This integrative genomic and phenotypic characterisation identifies candidate molecular features associated with opportunistic behaviour and highlights the genomic potential of R6, rather than experimentally validated causal determinants of pathogenicity.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12864-026-12875-9.},
}

@article {pmid42274483,
year = {2026},
author = {Shi, J and Lu, Y and Sheng, Z and Liu, H and Li, K and Chong, Y and Gao, Z and Deng, W and Wu, D},
title = {Pangenomics for Agricultural Breeding: Construction Strategies, Evidence Integration, and Translational Constraints.},
journal = {Biology},
volume = {15},
number = {11},
pages = {},
pmid = {42274483},
issn = {2079-7737},
support = {32302707//National Natural Science Foundation of China/ ; 202202AE090005//Major Science and Technology Projects in Yunnan Province/ ; 202302AE090015//Major Science and Technology Projects in Yunnan Province/ ; 202301AU070117//Yunnan Province Basic Research Program Project/ ; XDYC-CYCX-2022-0029//"Xingdian Talent" Industry Innovation Talent Program in Yunnan Province/ ; },
abstract = {Pangenomics has become an important framework for representing genetic diversity beyond a single linear reference genome. In agricultural species, it improves access to structural variants (SVs), copy number variations (CNVs), presence/absence variations (PAVs), and non-reference regulatory or coding sequences that may contribute to domestication, adaptation, and breeding traits. This review summarizes recent progress in long-read sequencing, telomere-to-telomere (T2T) assembly, and graph-based genome analysis, with emphasis on both livestock and crop systems. We first define the conceptual boundary between pangenome representations and reference-based variant catalogs. We then compare three major technical routes: variant integration, reference-guided iterative graph construction, and reference-free graph construction. Their performance is evaluated in terms of accuracy, scalability, coordinate consistency, reference bias, computational demand, annotation transfer, and suitability for downstream breeding questions. We further discuss how pangenome resources support hidden variant discovery, QTL and GWAS interpretation, environmental adaptation analysis, and multi-omics-based candidate prioritization. Importantly, we highlight unresolved limitations, including graph complexity, pipeline-dependent SV calls, incomplete functional annotation, weak cross-study comparability, and the difficulty of distinguishing causal variants from linked or neutral variation. This review therefore treats pangenome studies as connected but non-equivalent evidence: resource-building studies establish representational breadth, method papers define technical feasibility, and trait-focused studies provide varying levels of biological support. Apparent inconsistencies among studies are interpreted as signals of differences in sampling, genome complexity, validation depth, and graph construction strategy rather than as simple disagreements.},
}

@article {pmid42275059,
year = {2026},
author = {Nickel, J and Fullmer, S and Tørresen, OK and Ferrari, G and Laine, JT and Romundset, A and Skage, M and Tooming-Klunderud, A and Foote, AD and Jakobsen, KS},
title = {Chromosome-level genome assembly of a Norwegian threespine stickleback (Gasterosteus aculeatus) improves mapping for ancient DNA and QTL associated with parallel loss of pelvic spines.},
journal = {The Journal of heredity},
volume = {},
number = {},
pages = {},
doi = {10.1093/jhered/esag047},
pmid = {42275059},
issn = {1465-7333},
abstract = {The threespine stickleback represents a model system for studying parallel evolution, due to the repeated phenotypic adaptation of ancestral marine/anadromous populations to freshwater. Consequently, the genomic architecture underpinning these phenotypic traits has been extensively studied, and an increasing number of genomic resources are available. These include high quality chromosomal reference genome assemblies for Pacific marine and freshwater sticklebacks. However, these reference genomes may bias mapping of short-read data from Atlantic stickleback, and do not fully resolve some repeat-rich regions. Here, we present a chromosome-level reference genome (fGasAcu404) generated from an Atlantic anadromous stickleback using PacBio HiFi and Hi-C data. The assembly improves representation of repeat-rich regions, including on chromosome VII, where the Pitx1 locus and upstream PelA enhancer (Quantitative Trait Loci underpinning repeated loss of the pelvic girdle and spines) are located. Syntenic comparisons and mapping of short reads from well-studied spined and spineless stickleback indicate these loci are incorporated into the new assembly. We evaluate the utility of this reference for paleogenomic analyses by mapping ancient (>10,000 years BP) Norwegian stickleback DNA and assessing inversion karyotypes. We find marginal mapping gains and the ability to robustly infer homozygous ancestral karyotypes at three inversions in two ancient genomes which have predominantly marine-adaptive ancestry. However, karyotype is more ambiguous in an ancient genome with predominantly freshwater ancestry, reflecting the need for further genomic resources for this system. This new reference represents an important step towards the construction of a pangenome that better encompasses genetic variation among ancient and contemporary threespine stickleback populations across their range.},
}

@article {pmid42275491,
year = {2026},
author = {Hsieh, P and Soisangwan, N and Gordon, DS and Javidh, A and Harvey, WT and Porubsky, D and Hoekzema, K and Baker, C and Munson, KM and Kinipi, C and Leavesley, M and Brucato, N and Cox, MP and Ricaut, FX and Romero, IG and Eichler, EE},
title = {A global map for introgressed structural variation and selection in humans.},
journal = {Science (New York, N.Y.)},
volume = {392},
number = {6803},
pages = {eadz7518},
doi = {10.1126/science.adz7518},
pmid = {42275491},
issn = {1095-9203},
mesh = {Humans ; Animals ; *Selection, Genetic ; Neanderthals/genetics ; *Genome, Human ; Centromere/genetics ; *Hominidae/genetics ; Papua New Guinea ; *Genetic Introgression ; *Genomic Structural Variation ; Chromosome Mapping ; Evolution, Molecular ; },
abstract = {Genetic introgression from Neanderthals and Denisovans shaped modern human genomes; however, introgressed structural variants (SVs ≥ 50 base pairs) remain challenging to discover. We integrated high-quality phased assemblies from four new Papua New Guinea (PNG) haploid genomes with 94 published assemblies of diverse ancestry to infer an introgressed SV map. Introgressed SVs are enriched in genes (47%), including critical genomic disorder regions, and are most abundant in PNG genomes. We identified 11 centromeres likely derived from archaic hominins, adding unexplored diversity to centromere genomics. Pangenome genotyping of these 98 assemblies across 1363 samples revealed 16 adaptive SVs, many associated with immune-related genes and expression, in the PNG genomes. We hypothesize that archaic SVs contributed to reproductive success, underscoring introgression as a major force in human adaptive evolution.},
}

Humans
Animals
*Selection, Genetic
Neanderthals/genetics
*Genome, Human
Centromere/genetics
*Hominidae/genetics
Papua New Guinea
*Genetic Introgression
*Genomic Structural Variation
Chromosome Mapping
Evolution, Molecular

@article {pmid42277643,
year = {2026},
author = {Rahimian, M and Aghazadeh-Soltan-Ahmadi, M},
title = {Evolutionary interplay: virulence, endolysin-like hydrolases, and defense correlations in the Erwinia amylovora pangenome.},
journal = {BMC microbiology},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12866-026-05295-y},
pmid = {42277643},
issn = {1471-2180},
abstract = {Erwinia amylovora, the causative agent of fire blight, poses a significant threat to global pome fruit production. This study presents a comprehensive genomic analysis of 317 E. amylovora strains and 227 Erwinia phages to elucidate virulence evolution, phage-host dynamics, and the genomic signatures of the co-evolutionary arms race. Our analysis suggests that a substantial portion of E. amylovora's virulence factors (VFs) share evolutionary origins with diverse plant, human, and animal pathogens, underscoring widespread horizontal gene transfer. We identified bacterial phage hydrolases‑like proteins that share phylogenetic and domain-level similarities with phage endolysins. These observations are consistent with the possibility that some bacterial hydrolases originated from phage-derived ancestors, although functional repurposing remains to be experimentally validated. Crucially, our analysis identifies systematic, non-random associations between bacterial defense systems (e.g., RM, CRISPR-Cas, TA) and mobile anti-defense genes. Statistical correlations show strong patterns of co-occurrence and mutual exclusivity, which are consistent with an ongoing phage-bacteria arms race. These patterns provide a genomic basis for generating hypotheses about co-evolutionary dynamics. These findings may advance our understanding of E. amylovora pathogenicity and phage interactions, offering foundational insights for developing targeted phage-based biocontrol strategies against this devastating plant pathogen. Experimental validation of the predicted virulence factors and defense correlations is warranted to confirm their biological roles.},
}

@article {pmid42282480,
year = {2026},
author = {Zhang, X and Deng, T and Wang, H and Sun, H},
title = {Genomic insights into alpine plant adaptation.},
journal = {Plant diversity},
volume = {48},
number = {3},
pages = {439-450},
pmid = {42282480},
issn = {2468-2659},
abstract = {Alpine plants persist in some of the harshest terrestrial environments, where low temperatures, high ultraviolet radiation, and short growing seasons impose strong selective pressures. Recent advances in genome sequencing and comparative genomics are unraveling the multifaceted mechanisms that enable their adaptation and diversification under these conditions. In this review, we synthesize current progress on how genetic variation at different levels, including single nucleotide polymorphisms (SNPs), structural variants, whole-genome duplication, gene family evolution, and transposable elements, contribute to high-elevation adaptations in alpine plants. SNP-based studies have provided critical insights into adaptive differentiation along environmental gradients as well as molecular convergence underlying high-elevation adaptation, while analyses of structural variations and transposable elements reveal their potential roles in shaping phenotypic diversity and environmental responsiveness. Despite these advances, major challenges remain in linking genomic variation to functional adaptation, reflecting limitations in sampling, comparative frameworks, and functional validation. This review emphasizes the promise of integrative multi-omics, pangenome reconstruction, and functional assays to bridge these gaps, and highlights how genomic insights can guide the conservation of alpine biodiversity under accelerating climate change.},
}

@article {pmid42282663,
year = {2026},
author = {Torres-Morales, J and Dewhirst, F and Kauffman, KM and Mark Welch, J and Borisy, G},
title = {Site-specialization of human oral Porphyromonas species.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.64898/2026.06.02.729646},
pmid = {42282663},
issn = {2692-8205},
abstract = {Site-specificity within the human oral cavity reflects adaptation mechanisms such as genome divergence and metabolic specialization. Members of the genus Porphyromonas are distributed across oral sites in health and disease, yet the specific distribution of taxa and the functional basis of their site-specificity remain poorly understood. We analyzed 1,242 metagenomes from nine oral sites in healthy individuals and 24 subgingival plaque samples from individuals with periodontitis. Competitive mapping to a dereplicated genus-level pangenome of 84 reference genomes, combined with phylogenomic, gene-level detection, and functional profiling, revealed distinct site-specific distribution patterns, ecotype differentiation, and metabolic specialization across Porphyromonas taxa. Porphyromonas pasteri was the most abundant and widespread taxon in healthy subjects, comprising two ecotypes--one mucosal, one plaque-associated. Porphyromonas gingivalis was rare in healthy subjects but present in periodontal disease, although detected in only half of periodontitis samples. P. gingivalis exhibited the broadest metabolic repertoire, suggestive of a survival strategy adaptive to disparate conditions. In contrast, Porphyromonas catoniae, restricted to healthy dental plaque, lacked biosynthetic pathways for cobalamin, biotin, and serine, implying nutritional dependency on other taxa or the host. Porphyromonas endodontalis, detected in subgingival plaque across both health and disease, also lacked several metabolic pathways. A 44 kb conjugative element identified in P. gingivalis was detected across healthy and periodontitis subgingival plaque microbiomes independently of the P. gingivalis chromosome, indicating horizontal transfer. These findings reveal genomic divergence and complex metabolic specialization among Porphyromonas taxa, refining our understanding of their role in the ecological structure of the human oral microbiome.},
}

@article {pmid42283460,
year = {2026},
author = {Tothero, GK and Keffer, JL and Emerson, D and Fleming, EJ and Chan, CS},
title = {Distinguishing Leptothrix and Sphaerotilus genera by an integrated genomic-phenotypic analysis supported by new Leptothrix genomes.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0176825},
doi = {10.1128/msystems.01768-25},
pmid = {42283460},
issn = {2379-5077},
abstract = {The Sphaerotilus-Leptothrix group of bacteria includes one of the first described microorganisms, Leptothrix ochracea, an uncultured type strain, plus isolates of Leptothrix and Sphaerotilus. This group is unified by the ability to form sheaths and oxidize metals, although L. ochracea exhibits obvious ecological, morphological, and functional differences from the rest of Sphaerotilus-Leptothrix. Recently, there have been calls to combine the group into one genus, Sphaerotilus; however, these studies lacked adequate genomic representation of L. ochracea. Here, we present a comprehensive comparative genomic analysis of the Sphaerotilus-Leptothrix group, including expanded representation of L. ochracea, a closely related novel species, Leptothrix toolikensis, and two new isolates (Leptothrix mechoopdaensis). Analysis of 38 genomes resolves three phylogenetic and functional groups: the ochracea-type Leptothrix (Group 1), the mobilis-type Leptothrix (Group 2), and Sphaerotilus (Group 3). Group 1 genomes form a separate genus based on average nucleotide identity and alignment fraction. The genomes clearly diverge from the rest of Sphaerotilus-Leptothrix in phylogeny, size, and metabolic potential. Group 1 genomes are much smaller (2.59-3.04 Mb) than those of Groups 2 (4.55-6.06 Mb) and 3 (3.94-5.07 Mb), while encoding more metal oxidases and fewer carbohydrate-active enzymes. Group 2 clusters with Group 3 phylogenetically and is similar in organic carbon metabolisms but maintains more metal oxidation genes. Group 2 members lack homogeneity in phenotype and genotype, suggesting that additional isolates and genomes are needed for confident classification. However, Group 1 genomes (L. ochracea and L. toolikensis) show clear divergence, precluding their inclusion in Sphaerotilus and supporting the retention of the genus Leptothrix.IMPORTANCEResearchers have long noted differences in metal oxidation, morphology, and ecology among Sphaerotilus-Leptothrix, but longstanding confusion over phylogeny and genus boundaries led to inconsistent taxonomic classification between the two genera. This confusion stems from previous work that used isolates that are unavailable or lost distinguishing traits in culture, and from limited genomic data. Furthermore, the Leptothrix type strain L. ochracea has never been isolated. This study provides molecular evidence that substantiates calls to reassign some Leptothrix members to the genus Sphaerotilus but adds to an emerging body of evidence that Group 1 L. ochracea and now L. toolikensis represent a functionally distinct lineage. While genomic similarity metrics left taxonomic divisions unclear, integrating metabolic potential with phylogeny resolved genus boundaries based on clear functional groupings. This polyphasic approach for delineating genera clarifies longstanding taxonomic confusion and refines our understanding of functional diversity both across and within Sphaerotilus-Leptothrix lineages.},
}

@article {pmid42283717,
year = {2026},
author = {Cirak, B and Kreitlow, A and Borowiak, M and Hoffmann, C and Lämmler, C and Ewers, C and Malorny, B and Plötz, M and Abdulmawjood, A},
title = {Discovery of genomically distinct Arcanobacterium isolates from companion animals: a candidate for novel species status.},
journal = {International journal of systematic and evolutionary microbiology},
volume = {76},
number = {6},
pages = {},
doi = {10.1099/ijsem.0.007191},
pmid = {42283717},
issn = {1466-5034},
mesh = {Animals ; *Phylogeny ; *Arcanobacterium/classification/genetics/isolation & purification ; DNA, Bacterial/genetics ; RNA, Ribosomal, 16S/genetics ; Bacterial Typing Techniques ; Sequence Analysis, DNA ; *Genome, Bacterial ; *Pets/microbiology ; Nucleic Acid Hybridization ; Multigene Family ; Phenotype ; },
abstract = {The genus Arcanobacterium has expanded rapidly, with an increasing number of species described from domestic and wildlife hosts, underscoring the need for clearer delineation of species boundaries. In this study, 12 isolates initially presumed to belong to Arcanobacterium canis were examined using comparative phenotypic and genomic approaches to clarify their taxonomic position. The isolates showed partial phenotypic similarity to the type strain A. canis DSM 25104ᵀ, including consistent haemolysis, but differed in several enzymatic reactions and carbohydrate utilization patterns. Matrix-assisted laser desorption/ionization time-of-flight MS identified all isolates at the genus level, with only one displaying spectral similarity to A. canis. Phylogenetic analysis of five gene targets revealed that although the isolates shared sequence similarity with the type strain A. canis DSM 25104ᵀ, they consistently formed a separate clade. Core-genome phylogeny likewise placed the isolates on an independent branch. Pangenome analysis identified 2,178 gene clusters (58.8% core genes) and demonstrated that the cytolysin-like gene present in the type strain A. canis DSM 25104ᵀ is completely absent from all 12 isolates. Digital DNA-DNA hybridization and average nucleotide identity values fell below accepted species-level thresholds, indicating that the isolates represent a genomically distinct lineage within Arcanobacterium. Because chemotaxonomic analyses required for formal species description were not performed, the taxonomic status of this lineage remains unresolved. Nevertheless, the present findings refine species boundaries within Arcanobacterium and provide a robust foundation for future taxonomic and comparative genomic studies.},
}

Animals
*Phylogeny
*Arcanobacterium/classification/genetics/isolation & purification
DNA, Bacterial/genetics
RNA, Ribosomal, 16S/genetics
Bacterial Typing Techniques
Sequence Analysis, DNA
*Genome, Bacterial
*Pets/microbiology
Nucleic Acid Hybridization
Multigene Family
Phenotype

@article {pmid42283788,
year = {2026},
author = {Heydarov, RN and Romanova, KA and Ushtanit, AI and Mikhailovich, VM},
title = {The genomic landscape of Klebsiella pneumoniae in Russia.},
journal = {World journal of microbiology & biotechnology},
volume = {42},
number = {7},
pages = {},
pmid = {42283788},
issn = {1573-0972},
support = {25-24-00721//Russian Science Foundation/ ; 25-24-00721//Russian Science Foundation/ ; 25-24-00721//Russian Science Foundation/ ; 25-24-00721//Russian Science Foundation/ ; },
mesh = {*Klebsiella pneumoniae/genetics/isolation & purification/drug effects/pathogenicity/classification ; Plasmids/genetics ; *Genome, Bacterial/genetics ; beta-Lactamases/genetics ; Russia/epidemiology ; *Klebsiella Infections/microbiology/epidemiology ; Bacterial Proteins/genetics ; Virulence Factors/genetics ; Humans ; Whole Genome Sequencing ; Drug Resistance, Multiple, Bacterial/genetics ; Anti-Bacterial Agents/pharmacology ; Genomics ; Virulence/genetics ; CRISPR-Cas Systems ; },
abstract = {Klebsiella pneumoniae is a critical priority pathogen known for its extensive antimicrobial resistance (AMR) and capacity to cause severe infections. The traditional dichotomy between multidrug-resistant (MDR) and hypervirulent strains is rapidly eroding, driving the emergence of highly lethal convergent phenotypes. While global surveillance heavily emphasizes KPC-producing lineages, the specific genomic architecture driving this convergence in the Russian Federation remains insufficiently resolved. In this study, we analyzed population structure represented in a curated dataset 264 K. pneumoniae genomes, comprising 18 newly sequenced clinical isolates and 246 public assemblies from 2015 to 2024, using whole-genome sequencing, pangenome reconstruction, resistome, virulence factors and plasmidome profiling, and CRISPR-Cas typing. Our analysis revealed that high-risk sequence types ST395 (56.1%) and ST147 (8.7%) dominate the regional landscape. Carbapenemase genes were detected in 76.5% of isolates, primarily driven by blaOXA-48 on IncL/M plasmids within ST395 and blaNDM variants in ST147. Crucially, 46.2% of isolates harbored convergent plasmids, predominantly large, mosaic IncFIB/IncHI1B cointegrates, that simultaneously encode hypervirulence determinants like the aerobactin synthesis locus alongside resistance genes including blaNDM-1 and blaCTX-M-15. Additionally, we identified a heavy enrichment of plasmid-borne Type IV-A3 CRISPR-Cas systems in the dominant ST395 clone. The regional dominance of ST395 and ST147, coupled with the extensive horizontal integration of both resistance and virulence, represents a formidable public health threat. These findings underscore the critical need for localized genomic surveillance to effectively monitor evolving convergent pathogens and guide tailored antimicrobial stewardship.},
}

*Klebsiella pneumoniae/genetics/isolation & purification/drug effects/pathogenicity/classification
Plasmids/genetics
*Genome, Bacterial/genetics
beta-Lactamases/genetics
Russia/epidemiology
*Klebsiella Infections/microbiology/epidemiology
Bacterial Proteins/genetics
Virulence Factors/genetics
Humans
Whole Genome Sequencing
Drug Resistance, Multiple, Bacterial/genetics
Anti-Bacterial Agents/pharmacology
Genomics
Virulence/genetics
CRISPR-Cas Systems

@article {pmid42284160,
year = {2026},
author = {Wu, F and Deng, K and Lin, X and Wen, X and Zhu, Y and Peng, S and Cai, K and Cai, S and Wu, Q and Zheng, X and Yu, Z and Mo, N and Zhu, H and Zheng, Y and Huang, J and Zheng, Y and Fox, EGP},
title = {Time-resolved comparative genomics of 'Candidatus Carsonella ruddii' across psyllid lineages reveals a conserved core genome and contrasting secondary symbiont dynamics.},
journal = {Microbial genomics},
volume = {12},
number = {6},
pages = {},
doi = {10.1099/mgen.0.001727},
pmid = {42284160},
issn = {2057-5858},
mesh = {Animals ; *Symbiosis/genetics ; *Genome, Bacterial ; Phylogeny ; RNA, Ribosomal, 16S/genetics ; *Hemiptera/microbiology/classification ; Genomics ; },
abstract = {Psyllids harbour the obligate nutritional symbiont 'Candidatus Carsonella ruddii' (CaCr), yet complete CaCr genomes remain unevenly sampled across Psylloidea, limiting both comparative analysis and temporal inference. Here, seven complete CaCr genomes (165-174 kb) were assembled and annotated from psyllid hosts representing four families, including lineages for which genome-grade resources had previously been unavailable. We integrated whole-genome phylogenomics, pangenome analysis, fossil-calibrated relaxed-clock dating and quantitative PCR (based on 16S rRNA) screening of secondary symbionts. Across hosts, CaCr retained an extremely reduced, AT-rich (>82%) and gene-dense (>90% coding) genome architecture with a conserved core of 155 genes, while the accessory fraction was limited and lineage-specific. Most variable genes belonged to amino-acid metabolism or proteins of unknown function, suggesting differential erosion of peripheral functions around a stable translational and informational core. Phylogenomically, CaCr diversification broadly tracked deep host diversification, although the CaCr lineage from Diaphorina citri grouped with Triozidae-associated lineages rather than with other sampled Psyllidae. Using two host fossil-informed soft calibrations, we estimated that major CaCr divergences occurred mainly from the Paleogene to the Miocene, with crown diversification of Cacopsylla-associated CaCr at 15.95-18.99 Ma. In contrast to the stability of the primary symbiosis, secondary symbionts showed patchy host distributions: Wolbachia- and Arsenophonus-like lineages occurred in multiple hosts, 'Candidatus Profftella armatura' was restricted to D. citri, and no secondary symbiont was detected in Cacopsylla chinensis. These results provide a time-resolved comparative framework for CaCr evolution in psyllids and underscore the different evolutionary stability of primary and facultative associates.},
}

Animals
*Symbiosis/genetics
*Genome, Bacterial
Phylogeny
RNA, Ribosomal, 16S/genetics
*Hemiptera/microbiology/classification
Genomics

@article {pmid42259962,
year = {2026},
author = {Olowo-Okere, A and Skiebe, E and Wilharm, G},
title = {Genomic and phylogenomic analyses reveal extensive diversity among soil-derived Acinetobacter baumannii isolates from Nigeria.},
journal = {Scientific reports},
volume = {16},
number = {1},
pages = {},
pmid = {42259962},
issn = {2045-2322},
abstract = {This study reports the genomic characterization of 24 representative Acinetobacter baumannii isolates recovered from soil across ecologically distinct sites in Nigeria's Federal Capital Territory. From the 43 soil samples analyzed, 101 Acinetobacter spp. were recovered, predominantly A. baumannii (39/101; 38.61%). Analysis of the 24 A. baumannii isolates revealed extensive genetic diversity, including 20 distinct Pasteur and 19 Oxford sequence types (STs), of which 15 and 13, respectively, were novel. Additionally, we detected 20 capsular (KL) and seven outer core lipooligosaccharide (OCL) locus types. In silico prediction revealed that most isolates did not harbour clinically relevant antibiotic resistance genes and were unrelated to known international clonal complexes. However, one isolate (A23-4) belonged to the international clone 8 (IC8) lineage and harboured a class 1 integron-associated MDR cassette containing ant(3″)-Ia, dfrA1, and sul2, flanked by insertion sequences ISAIw4, ISVsa3, and IS1006. Further analyses identified 4,975 pangenome gene clusters and a polyphyletic distribution of the A. baumannii isolates across multiple distinct evolutionary lineages. The studied soil samples harbour a highly diverse and largely antimicrobial-susceptible population of A. baumannii rich in novel lineages. However, the detection of a MDR ST10/IC8 clone highlights the value of genomic surveillance in identifying potentially high-risk strains within environmental reservoirs.},
}

@article {pmid42262111,
year = {2026},
author = {Cheng, X and Liu, H and Qiu, X and Wu, W and Hu, H and Xu, P and Tang, H},
title = {Systemic trade-offs between core and accessory genomes govern stress adaptation in Rhodococcus erythropolis.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0013726},
doi = {10.1128/msystems.00137-26},
pmid = {42262111},
issn = {2379-5077},
abstract = {The genus Rhodococcus is a premier biotechnological chassis for organic pollutant bioremediation and natural product biosynthesis, yet the systemic genetic basis of its stress resilience remains poorly defined. Here, we elucidate adaptive strategies in Rhodococcus erythropolis by integrating pangenomics with multi-omics and phenotypic analyses. We refined R. erythropolis taxonomy using average nucleotide identity across 671 genomes and constructed a high-quality pangenome that exhibits an open architecture, with continuous expansion of the accessory cloud genome via horizontal gene transfer to enable environmental adaptation. Using R. erythropolis strain XP as a representative model, we confirmed broad physiological robustness, including tolerance to multiple heavy metals [Ni(II), Zn(II), Pb(II), Cu(II), and Cr(VI); minimum inhibitory concentrations, 2-7 mM], wide pH ranges (5-11), and high salinity (1.5 M NaCl). Integration of comparative transcriptomics with weighted gene co-expression network analysis revealed the transcriptional basis of this resilience. A key growth-regulatory module (ME1), dominated by evolutionarily conserved core genes (68.8%), including essential cell division components, was identified. Under severe stress, this core module is strongly downregulated, coinciding with stress-induced filamentation. These results expose a fundamental evolutionary trade-off: repression of vertical propagation via core functions enables preferential deployment of accessory cloud genes that confer resistance. Collectively, this study links pangenome plasticity to physiological trade-offs and provides a conceptual framework for optimizing R. erythropolis in industrial applications.IMPORTANCEMicroorganisms must continually balance rapid growth with survival under stress, yet the genomic architecture underlying this trade-off remains unclear. By analyzing 671 genomes to refine the taxonomy of the biotechnologically important bacterium Rhodococcus erythropolis and integrating multi-omics data, we demonstrate that this physiological balance is mirrored by an evolutionary division of labor. The conserved core genome predominantly governs growth, whereas the horizontally acquired accessory cloud genome drives stress resistance. Under severe stress, the bacterium downregulates core cell division machinery to prioritize resources for activating its accessory defense repertoire. This work establishes a direct link between pangenome evolution and cellular fitness, offering theoretical guidance for engineering robust microbial chassis.},
}

@article {pmid42265603,
year = {2026},
author = {Zhao, Y and Lu, YF and Hai, X and Zhi, XY},
title = {LSGFA: domain-based infraspecific large-scale prokaryotic genomic orthologous gene inference.},
journal = {BMC bioinformatics},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12859-026-06506-z},
pmid = {42265603},
issn = {1471-2105},
support = {32060003//National Natural Science Foundation of China/ ; },
abstract = {BACKGROUND: Orthologous gene inference is a crucial technical challenge in evolutionary biology. It typically depends on sequence similarity searches and employs a graph clustering method to infer homologous gene families. However, the all-vs-all sequence similarity search is time-consuming for large-scale genome datasets. In this work, we present LSGFA, a method that detects subgraphs based on the similarity of protein domain architectures and then performs graph clustering within each subgraph, corresponding to sequences that share similar compositions of protein domains.

RESULTS: LSGFA carries out four steps in the analysis workflow: protein domain annotation, initial clustering based on Pfam domain architecture, SSN-based clustering, and detection of pan-genomic patterns. Benchmarking against five state-of-the-art tools (OrthoFinder, Roary, PanTA, Panaroo, and PGAP2) across multiple datasets demonstrates that LSGFA achieves a balanced trade-off between computational efficiency and biological accuracy. It takes less time than OrthoFinder while identifying more core genes than high-speed heuristic tools, and its orthogroup inference results show strong consistency with OrthoFinder.

CONCLUSIONS: Due to the high proportion of proteins with known domain architectures in prokaryotes, LSGFA is particularly well-suited for prokaryotic genomes, where it significantly reduces computational time while yielding accurate homologous gene inference.},
}

@article {pmid42270222,
year = {2026},
author = {Ren, J and Xu, Y and Wang, Z and He, W},
title = {Pangenome-based interpretable machine learning framework for predicting antimicrobial resistance in foodborne Escherichia coli.},
journal = {Food research international (Ottawa, Ont.)},
volume = {239},
number = {},
pages = {119492},
doi = {10.1016/j.foodres.2026.119492},
pmid = {42270222},
issn = {1873-7145},
abstract = {Antimicrobial resistance (AMR) in foodborne Escherichia coli (E. coli) remains a significant public health concern. Predicting AMR from whole-genome sequencing data has become a critical component of modern surveillance. However, conventional approaches relying solely on known resistance genes often fail to capture the broader genomic context associated with resistance. In this study, we developed interpretable machine learning models using pangenome-derived accessory genes from 655 foodborne E. coli isolates. These models achieved robust predictive performance across five antibiotics. SHAP analysis revealed that the models relied on genomic features beyond canonical resistance determinants, including markers of mobile genetic elements and stress response mechanisms. Furthermore, the disinfectant resistance gene qacEΔ1 emerged as a consistently important predictive feature across different antibiotic models. This suggests qacEΔ1 as a reliable positional marker for the physical linkage of resistance genes on integron platforms, representing a genomic context associated with potential co-selection pressures in food production environments. Overall, this study demonstrates the feasibility of the pangenome-based framework to provide interpretable predictions and capture potential genomic signals linked to the dissemination of resistance.},
}

@article {pmid42270740,
year = {2026},
author = {Masum, MHU and Chamonara, K and Uddin, MS and Hossain, I and Roy, SC and Hossain, MI and Hosen, MR and Siddiqua, A and Al Mukarrom, A},
title = {Comprehensive genomic analysis of avian Escherichia coli from Noakhali uncovers multidrug resistance, metal resistance, and zoonotic signatures.},
journal = {Scientific reports},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41598-026-54331-4},
pmid = {42270740},
issn = {2045-2322},
abstract = {Colibacillosis caused by avian pathogenic Escherichia coli (APEC) results in significant poultry losses and financial constraints globally, particularly in Bangladesh, emphasizing the urgent need for effective surveillance and control strategies. The present study employed whole-genome sequencing (WGS) of E. coli isolates from avian hosts and their surroundings to obtain genomic and evolutionary insights. Subsequently, the strains exhibited high genome completeness (> 99%) and coarse consistency scores (> 98) for genome assembly metrics. Further, genome annotation profiles showed a broad range of antimicrobial resistance (AMR) determinants, including resistance-nodulation-division (RND), major facilitator superfamily (MFS), and small multidrug resistance (SMR) multidrug efflux pumps. The coexistence of such AMR determinants within mobile genetic elements (MGEs) indicates a pattern of horizontal gene transfer and a possible dissemination pathway for the multidrug resistance phenotype. Several virulence-associated gene (VAG) clusters in the genomes suggest potential virulence profiles. A significant number of genes conferring heavy metal resistance and detoxification were identified in the genomes, including arsenic, copper, magnesium, tellurite, and zinc resistance, indicating extensive metal stress tolerance in the strains. Subsequent pangenome and phylogeny analyses uncovered significant similarities between strains derived from avian and human clinical isolates, suggesting a potential for zoonotic transmission. The findings highlight genetic association and potential public health implications of APEC and environmental E. coli (EEC) strains from poultry.},
}

@article {pmid42270823,
year = {2026},
author = {Biswas, R and Anbarasu, A},
title = {In silico genomic analysis of resistome, virulome, and mobilome of β-lactamase-producing Klebsiella pneumoniae.},
journal = {Scientific reports},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41598-026-56520-7},
pmid = {42270823},
issn = {2045-2322},
abstract = {Klebsiella pneumoniae (K. pneumoniae) is a major multidrug-resistant pathogen associated with nosocomial infections, particularly among immunocompromised patients, and contributes significantly to global morbidity and mortality. This study provides a comprehensive genomic analysis of β-lactamase-producing K. pneumoniae isolates. Whole-genome sequences of clinical isolates were retrieved from the National Center for Biotechnology Information-Sequence Read Archive (NCBI-SRA) repository and systematically analyzed to characterize antimicrobial resistance (AMR) genes, virulence factors, mobile genetic elements, and defense systems. Clonal diversity was assessed using multilocus sequence typing and capsule typing. Pan-genome analysis revealed pronounced heterogeneity, with ST15 as the predominant sequence type. The presence of a large accessory genome indicates substantial genomic plasticity. In total, 244 unique AMR genes were identified, predominantly encoding β-lactamases and efflux pumps. Genes conferring resistance to penams, aminoglycosides, tetracyclines, and fluoroquinolones were also highly represented. Over 6203 insertion sequence (IS) elements were detected, mainly from the IS3 family. Integron-associated resistance genes were frequently observed, particularly those conferring resistance to β-lactams and aminoglycosides. Collectively, these findings highlight K. pneumoniae's rapid genetic diversification and high potential for resistance, which are intrinsically linked to the complex dynamics of its resistome, virulome, and mobilome. This reinforces the urgent need for alternative therapeutic strategies, antimicrobial stewardship, and enhanced genomic surveillance to curb the increasing threat of AMR.},
}

@article {pmid42273045,
year = {2026},
author = {Azour, A and Matar, GM and Bilen, M},
title = {Colibactin (pks) carriage in Escherichia coli is associated with lineage restriction, reduced plasmid burden, and lower antimicrobial resistance.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1842853},
pmid = {42273045},
issn = {1664-302X},
abstract = {The colibactin pks genomic island of Escherichia coli is a chromosomally integrated secondary metabolite locus implicated in host-microbe interactions and colorectal carcinogenesis. Although pks distribution has been linked to specific E. coli lineages, its relationship with plasmid burden, antimicrobial resistance (AMR), and genome-wide accessory gene structure remains incompletely resolved at population scale. Here, we analyzed 9,700 curated E. coli genomes from BV-BRC and identified 498 genomes carrying complete or near-complete canonical pks loci. pks-positive genomes were strongly enriched in phylogroup B2 and concentrated within a limited number of sequence types, including ST73, ST95, ST127, and ST12. Compared with pks-negative genomes, pks-positive genomes carried fewer AMR genes and fewer plasmid replicons. This pattern persisted in phylogroup B2-controlled comparisons, although sequence-type structure remained an important potential contributor. Synteny and flanking-region analyses showed strong conservation of the internal clb gene cluster together with recurrent conservation of the surrounding chromosomal neighborhood, consistent with positional stability of canonical pks loci. Pangenome reconstruction of B2-matched genomes revealed that pks-positive genomes had a smaller total pangenome and accessory gene compartment, but a larger core genome, than pks-negative genomes. Together, these findings indicate that canonical pks carriage marks a lineage-restricted and genomically conserved E. coli subpopulation associated with reduced plasmid and AMR burden. These associations support a model in which colibactin-positive lineages differ from multidrug-resistant plasmid-rich lineages in their accessory genome architecture, although experimental studies remain required to define the underlying mechanisms.},
}

@article {pmid42273220,
year = {2026},
author = {Xu, J and Chen, J and Long, J and Xue, T and Zhang, X},
title = {Pan-genome analysis and abiotic stress expression of the SWEET gene family in Brassica napus.},
journal = {Frontiers in plant science},
volume = {17},
number = {},
pages = {1846550},
pmid = {42273220},
issn = {1664-462X},
abstract = {The SWEET (Sugars Will Eventually be Exported Transporters) gene family plays crucial roles in sugar transport, plant development, and abiotic stress responses. However, its pan-genomic characteristics and practical breeding potential in Brassica napus remain unclear. In this study, we systematically identified 96 BnSWEET genes across eight rapeseed genomes, revealing extensive presence/absence variations (PAVs) and clear classification into four subfamilies (Groups I-IV). Evolutionary analyses highlighted diverse selection pressures, with specific members (e.g., BnSWEET37) exhibiting strong signatures of positive selection (Ka/Ks > 1.0), while others were conserved under purifying selection. Haplotype analysis revealed that elite alleles of BnSWEET5 are significantly associated with seed oil content, silique length, and germination vigor. Furthermore, Weighted Gene Co-expression Network Analysis (WGCNA) identified BnSWEET47 as a core regulatory hub coordinating sugar partitioning and secondary metabolism. Transcriptomic profiling and RT-qPCR validation confirmed that BnSWEET genes, particularly those representing specific structural and evolutionary variants (e.g., the PAV-specific BnSWEET26), exhibit highly heterogeneous and tissue-specific temporal expression patterns under multiple abiotic stresses. Overall, this study elucidates the evolutionary and functional divergence of the BnSWEET family and proposes a practical breeding pathway-utilizing the identified elite haplotypes and key PAV variants for precision germplasm screening-to optimize source-sink balance and enhance abiotic stress resilience in B. napus.},
}

@article {pmid42258184,
year = {2026},
author = {Bisht, N and Mayilraj, S and Kaur, N and Kumar, S},
title = {Uncovering the Biosynthetic Potential of Amycolatopsis: New Insights into Glycopeptide Antibiotic and Polyketide Gene Clusters.},
journal = {Journal of applied microbiology},
volume = {},
number = {},
pages = {},
doi = {10.1093/jambio/lxag134},
pmid = {42258184},
issn = {1365-2672},
abstract = {BACKGROUND: : Amycolatopsis species are renowned producers of a vast array of biologically active molecules, including Glycopeptide antibiotics (GPAs), polyketides, siderophores, and terpenes. Despite their clinical significance, the full biosynthetic genetic capacity and evolutionary diversification of Amycolatopsis remain unexplored.

METHODS AND RESULTS: We analyzed 16 Amycolatopsis strains, including six newly sequenced in this work, six from our previously published datasets, and four retrieved from NCBI. Phylogenetic, pangenome, and antiSMASH-based genome-mining analyses were performed to identify secondary metabolite gene clusters, with a focus on NRPS, PKS, terpenes, and siderophores. Conserved glycopeptide gene clusters found across Cluster A strains, encoding core NRPSs, P450 oxygenases, and tailoring enzymes with variations consistent with the structural GPA types. Analysis showed conserved but distinct GPA BGC organization corresponding to the type I, II, and III subclasses, as well as their genetic, structural, and functional diversifications. A. azurea DSM 43854T produced A35512B rather than azureomycins, while A. alba DSM 44262T produced vancomycin. Six previously unreported Cluster A strains were found to encode putative GPA gene clusters, and LC-MS profiling predicted GPA production of nogabecin from A. keratiniphila subsp. keratiniphila DSM 44409T and A33512B from A. thailandensis JCM 16380T. GPA biosynthetic capacity was largely restricted to Cluster A, but in Cluster C, in the case of A. balhimycina DSM 44591T. Type II PKS, siderophore, and terpene gene clusters were also explored for these strains.

CONCLUSIONS: This study provides a comparative genomic overview of Amycolatopsis Cluster A, highlighting GPA diversity and revealing broader potential for secondary metabolites.},
}

@article {pmid42026455,
year = {2026},
author = {Sizana, LC and Thekisoe, O and Molale-Tom, L and Van Wyk, D and Ramatla, T and Lekota, KE},
title = {Genomic characterization of Pseudomonas aeruginosa clonal lineage ST162 isolated from bovine-milk in South Africa.},
journal = {BMC microbiology},
volume = {26},
number = {1},
pages = {},
pmid = {42026455},
issn = {1471-2180},
support = {CSUR23030681021//National Research Foundation/ ; },
abstract = {BACKGROUND: Pseudomonas aeruginosa is an opportunistic pathogen that can colonize a wide range of habitats. This pathogen is associated with bovine mastitis; however, its genomic characteristics in a veterinary context remain poorly defined.

METHODS: We present the first comprehensive genomic analysis of P. aeruginosa isolates obtained from bovine milk in the Dr Kenneth Kaunda District, North West Province, South Africa. Bovine milk-derived isolates (n = 10) were analysed using whole-genome sequencing, resistome profiling and pangenome analysis.

RESULTS: The 10 South African isolates shared a highly conserved resistome, harbouring antimicrobial resistance genes (ARGs) associated with β-lactams (bla_OXA−396, blaPAO), aminoglycosides (aph(3’)-IIb_1, aadA6_1), tetracyclines (tet(G)), and sulfonamides (sul1_5). The ppkA gene, a regulator of T6SS and biofilm dynamics, was absent in the sequenced genomes 4RF, 8RF, and 13RF13LH. The pchH gene, involved in pyochelin transport, was detected only in strains 11RH10LH and 1RF, indicating variability in specific virulence regulators and iron acquisition genes. Based on pangenomics analysis using hierarchical clustering, all 10 South African isolates belonged to sequence type ST162 and formed a tight monophyletic clade, clustering closely with human-derived ST162 strains from the United States and Australia. All genomes containing plasmid AF876 were associated with the presence of the crpP gene encoding a ciprofloxacin-modifying enzyme. PHAGE_JBD25, PHAGE_F10, PHAGE_ phi297, and PHAGE_ Pf1 were consistently identified as common, intact prophages, indicating a conserved prophage repertoire shared among the isolates.

CONCLUSIONS: These findings highlight the importance of genomic surveillance in veterinary pathogens and offer valuable insights into the evolution and dissemination of P. aeruginosa within dairy environments. The detection of ST162 in both animal and human-associated strains suggests potential zoonotic transmission routes and raises concerns regarding the persistence, dissemination, and evolution of this lineage within livestock production environments.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12866-026-05053-0.},
}

@article {pmid42026457,
year = {2026},
author = {Wu, H and Lu, Y and Xie, K and Liu, C and Zhou, C and Wang, D and Zhang, K and Li, Y and Sun, L and Shi, C and Peng, H and Zhang, J and Gu, W},
title = {A novel Sinomonas strain and Its genus-wide genomic insights into plant growth-promoting potential.},
journal = {BMC microbiology},
volume = {26},
number = {1},
pages = {},
pmid = {42026457},
issn = {1471-2180},
support = {2023YFD1702200//This work was supported financially by the National Key Technology Research and Development Program of China/ ; 2024A1515011125//the Guangdong Basic and Applied Basic Research Foundation/ ; 2025B03J0001//the Science and Technology Program of Guangzhou/ ; 2023-WPY-00-004//the Guangdong Strategic Special Fund for Rural Revitalization/ ; 2023-WPY-00-005//the Guangdong Strategic Special Fund for Rural Revitalization/ ; XT202508//the Low carbon agriculture and carbon neutralization Research Center/ ; XT202220//the Low carbon agriculture and carbon neutralization Research Center/ ; R2023PY-JX019//Special Fund for Scientific Innovation Strategy Construction of High-level Academy of Agriculture Science/ ; R2020PY-JG012//Special Fund for Scientific Innovation Strategy Construction of High-level Academy of Agriculture Science/ ; R2021YJ-QG007//Special fund for the introduction or training of scientific and technological talents of Guangdong Academy of Agricultural Sciences/ ; R2021YJ-YB1003//Special fund for the introduction or training of scientific and technological talents of Guangdong Academy of Agricultural Sciences/ ; 2025ZQQZ-G23//the State Key Laboratory of Swine and Poultry Breeding Industry/ ; 2023B0202010027//the Key-Area Research and Development Program of Guangdong Province/ ; 2024CXTD17//Modern Agricultural Industrial Technology System of Guangdong Province/ ; 2023SDZG08//the Open Competition Program of the Top Nine Critical Priorities of Agricultural Science and Technology Innovation for the 14th Five-Year Plan of Guangdong Province/ ; 2024TS-3-3//the Special Fund for Rural Revitalization Strategy of Guangdong/ ; 2022-440000-43010104-9463//the Guangdong Strategic Specical Fund of Rural Revitalization/ ; },
abstract = {BACKGROUND: Beneficial plant-associated microorganisms are key drivers of sustainable agriculture. However, their discovery and practical application remain insufficiently explored. Here, we present the first comprehensive comparative genomic analysis of a newly identified Sinomonas strain together with all publicly available genomes to assess its agronomic potential.

RESULTS: Our results demonstrate that Sinomonas has an open pangenome and harbors multiple pathways for IAA biosynthesis, including a rare pathway found in only a limited number of bacterial taxa. The genus also contains genes involved in the synthesis of cytokinin analogues. In addition, genomic annotation identified ten genes putatively associated with phosphorus solubilization. A total of sixteen distinct biosynthetic gene clusters were identified, covering pathways for the biosynthesis of stenothricin, dactylocycline, aborycin, reveromycin, michiganin A, ikarugamycin, and peucechelin, all of which are compounds with reported antibacterial activity. In addition, Sinomonas carries multiple genes potentially involved in improving plant stress tolerance, including genes related to the biosynthesis of spermidine, 2,3-butanediol, acetoin, betaine, proline, and trehalose.

CONCLUSION: Overall, these findings highlight the functional diversity of the Sinomonas genome and provide preliminary insights into its potential agricultural applications.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1186/s12866-026-05072-x.},
}

@article {pmid42256219,
year = {2026},
author = {Yang, Y and Shi, X and Chen, J and Wang, L and Wu, Z and Yao, W and Xu, L and Zhang, Y and Liu, Z and Wu, B},
title = {Identification and phylogenetic analysis of seven Brucella abortus strains in Zhejiang, China.},
journal = {Frontiers in cellular and infection microbiology},
volume = {16},
number = {},
pages = {1758965},
pmid = {42256219},
issn = {2235-2988},
abstract = {INTRODUCTION: Brucella abortus poses a serious zoonotic threat in China, however its genomic epidemiology in Zhejiang Province remains largely uncharacterized. This study addresses this knowledge gap by conducting the first integrated genomic analysis of seven B. abortus isolates obtained from patients and cows in the region.

METHODS: The phenotypic, genotypic, and phylogenomic characters of the isolates were illustrated by BCSP-31 and AMOS-PCR, MLST, ANI, cgSNP, and Pan-Genome analysis.

RESULTS: All seven isolates were identified as B. abortus via AMOS-PCR and belonged to a single sequence type (ST2) based on MLST, a classification further corroborated by an average nucleotide identity (ANI) of 99.99% to the reference strain B. abortus 544. Pan-genome analysis disclosed a highly conserved genome comprising 3,084 core genes and a minimal accessory genome of only 10 shell genes, alongside the prediction of 68 virulence-associated factors and one AMR gene, mprF. Core genome SNP phylogeny indicated that the Zhejiang strains form a monophyletic cluster with Russian references and trifurcate into three distinct subclades. Each subclade demonstrates specific phylogenetic connections to strains from separate northern Chinese provinces.

DISCUSSION: As the first study to integrate phenotypic, genotypic, and phylogenomic data for B. abortus in this region, our work substantially expands the understanding of its local population structure and provides a critical evidence base for proactive genomic surveillance, thereby informing targeted public health interventions against brucellosis.},
}

@article {pmid42250117,
year = {2026},
author = {Zainal Fithri, HH and Samsulrizal, NH and Mansor, NN and Hamzah, N and Abu Halim, NH and Ridzuan, MSM and Abdullah, A and Abdul Rahim, NAS and Abdul Hamid, AA},
title = {Unveiling Complete Genome of Streptococcus agalactiae from Malaysian Aquaculture: A Closer Look at Molecular Characteristics and Phylogenomic.},
journal = {Marine biotechnology (New York, N.Y.)},
volume = {28},
number = {3},
pages = {},
pmid = {42250117},
issn = {1436-2236},
support = {P21300040170502//12th Malaysia Plan budget: R&D of Fish Health Programs in Aquaculture/ ; },
abstract = {Streptococcus agalactiae (Group B Streptococcus, GBS) is a significant pathogen in aquaculture worldwide and is responsible for high mortality in farmed fish. Despite its regional impact, complete genome data from Malaysian isolates remain scarce. In this study, we report the first complete genome of a Malaysian S. agalactiae isolate, SA2BKE, derived from infected tilapia. Using Oxford Nanopore long-read sequencing, we assembled a 2.03 Mb circular complete genome of S. agalactiae. The functional annotation revealed 1,970 protein-coding genes and 108 RNA genes. Several antimicrobial resistance genes, including tet(M), mreA, and mprF, are associated with resistance to tetracyclines, macrolides, and peptides, respectively. Notably, there are 15 virulence-associated proteins involved in cell wall/membrane/envelope biogenesis. Multilocus sequence typing (MLST) identified SA2BKE as sequence type ST283, which has the potential to infect both fish and humans. Comparative phylogenomic analysis revealed 215 global strains positioned SA2BKE within a clade of other ST283 isolates from Asia and South America, suggesting potential transregional transmission. Pan-genome analysis identified 555 core genes shared among the analysed genomes, highlighting substantial genomic diversity within the species. Additionally, 14 mobile genetic element-associated regions were detected in SA2BKE, indicating potential genome plasticity and horizontal gene transfer events. These findings expand the genomic reference data for S. agalactiae isolates from Malaysia, contributing to regional surveillance efforts across Southeast Asia and supporting integrated disease management strategies in aquaculture.},
}

@article {pmid42251052,
year = {2026},
author = {Mantena, S and Edahiro, R and Okada, Y and Akbari, A and Raychaudhuri, S},
title = {A multi-ethnic reference map of T cell receptor germline diversity reveals evidence of natural selection on alpha chain genes.},
journal = {Nature communications},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41467-026-73730-9},
pmid = {42251052},
issn = {2041-1723},
support = {R01AR063759, P01AI148102, U01HG012009, R56HG013083, and T32GM144273//U.S. Department of Health & Human Services | National Institutes of Health (NIH)/ ; JP25tm0424233, JP25gm7110002, JP24gm1810012, JP24ek0210207//Japan Agency for Medical Research and Development (AMED)/ ; },
abstract = {T cell receptors (TCR) orchestrate adaptive immunity, yet the complex, repetitive architecture of the TCR loci has impeded systematic characterization of human genetic variation in the genes encoding the TCR. Using public long-read sequencing data from the Human Pangenome Reference Consortium and All of Us consortia spanning 2719 donors, we build a near-complete map of common alleles in TCR V, D, and J genes, revealing amino acid variation at almost every position within V genes. We observe allele frequency differences between populations for many individual TCR genes. We present evidence of natural selection on TCR genes, including signals of balancing selection and positive selection in the alpha chain locus. We find TCR allelic polymorphism alters core functional properties of T cells, including thymic fate commitment and cell-surface receptor abundance. Collectively, these findings position inherited variation in TCR genes as a key axis of immunological diversity that may shape interindividual differences in immune responses.},
}

@article {pmid42252506,
year = {2026},
author = {Galtier, A and Warinner, C and Velsko, IM},
title = {Ancient species diversity and niche adaptation in Tannerella and Porphyromonas revealed through pangenomics.},
journal = {Genome biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/gbe/evag136},
pmid = {42252506},
issn = {1759-6653},
abstract = {De novo assembly of ancient and modern bacterial metagenomes can shed light on evolution and ecology of bacterial species that are challenging to culture. Tannerella and Porphyromonas are bacterial genera linked to periodontal disease, and understanding their evolution may reveal insights into their role in oral disease development. We performed pangenomic and phylogenetic analyses on a global set of isolates and metagenome-assembled genomes of the genera Tannerella (n=238) and Porphyromonas (n=976), including 66 genomes from ancient dental calculus samples (up to 14,800 years old), and modern oral samples from present-day living populations. We identify a novel species of oral Tannerella in modern and ancient humans, which we call Ca. Tannerella abscondita, that is related to and often mistaken for Tannerella forsythia but differs in its virulence repertoire. We reveal distinct niche tropism in Tannerella species and Porphyromonas pasteri, but not Porphyromonas gingivalis. There is limited phylogeographic structuring, and virulence genes are homogeneously distributed across continents and oral niches. Saliva-derived strains of T. forsythia and P. gingivalis from Oceania and T. serpentiformis and P. pasteri from Asia show enrichment of pseudogenes related to ecological niche transitions. A phylogenetic analysis of the P. gingivalis major fimbrial protein gene fimA reveals the genes cluster by genotypes, and that no ancient genes are found in genotypes I and Ib. Using de novo assembly for bacterial pangenomics improves the representation of oral genera found in reference databases and enhances our ability to study the evolutionary history of these taxa.},
}

@article {pmid42253453,
year = {2026},
author = {Orlova, EA and Bechtold, NP and Grigoriev, YN and Shoeva, OY and Glagoleva, AY and Kukoeva, TV},
title = {Development of a molecular marker for the Run8 gene for the selection of barley genotypes resistant to smut.},
journal = {Vavilovskii zhurnal genetiki i selektsii},
volume = {30},
number = {3},
pages = {372-380},
doi = {10.18699/vjgb-26-41},
pmid = {42253453},
issn = {2500-0462},
abstract = {Loose smut of barley, caused by the basidiomycete Ustilago nuda (Jens.) Roster, occurs in all regions of the world where this crop is grown. This seed-borne disease causes significant losses in grain production. Selection for resistance to loose smut based on the use of donors with resistance genes is an ecologically and economically safe way to constrain the negative impact of the pathogen on barley. The introduction of molecular genetic approaches into the breeding process makes it possible to control the transfer of resistance genes to hybrid material. The Run8 gene controls resistance to many isolates of loose smut, including in the West Siberian region of Russia. The objective of the current study is to develop a molecular marker for Run8 for the selection of barley genotypes resistant to loose smut from hybrid populations. By comparing the nucleotide sequences of the Run8 gene available from the barley pangenome database, an insertion/deletion of six nucleotide pairs in the coding region of the gene was identified. Based on the identified polymorphism, a molecular marker Hor7050 was developed, which allows differentiating the alleles of Run8. The developed marker was tested on hybrid lines (F5-F6) obtained from crossing cultivar Elf, which is a donor of resistance to loose smut and carries, according to the originators, the Run8 gene, with cultivar Tanai, which has practical resistance to the pathogen. Using the developed marker, 18 hybrids carrying Run8 of Elf were selected from 84 hybrids; however, the phytopathological assessment showed that eight of the selected lines were susceptible to the disease. To clarify the genotype of 18 selected lines, an additional analysis was carried out using the microsatellite marker EBmac0541 linked to Run6. A relationship was established between the presence of the allele of this marker from Elf and resistance to the disease. It is possible that Elf, in addition to Run8, carries Run6, which is effective against race 1 of the causative agent of loose smut. Additional studies are required to clarify the presence of Run6 in the Elf variety. In addition to resistance, the selected lines were characterized by productivity traits. According to the two-year analysis, three productive resistant lines were identified, with Run8 - 32, 65 and 79, significantly exceeding the control Elf in yield. The selected lines were transferred to breeding nurseries for their further evaluation by economically important traits.},
}

@article {pmid42254503,
year = {2026},
author = {Liu, Z and Li, Z and Zhang, J and Brown, CT and Wang, L},
title = {Interpretable learning algorithms enable pathogenic potential assessment and virulence-associated gene discovery of Vibrio parahaemolyticus.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1832130},
pmid = {42254503},
issn = {1664-302X},
abstract = {The presence of Vibrio parahaemolyticus (Vp) at various stages of seafood production has adversely affected public health and threatened the sustainability of the industry. Driven by the advancement of next-generation-sequencing technologies and public health data sharing initiative, an increasing volume of public Vp genomic data with metadata has become available, which serve as the foundation for building learning models to accurately differentiate isolation sources and further uncover gene-level determinants of pathogenic potential. The primary goal of this study was to develop and validate machine learning (ML) and deep learning (DL) algorithms to differentiate Vp strains from different isolation sources (clinical vs. environmental isolates) using pangenome assemblies and achieved robust and precise pathogenic potential prediction of Vp. The secondary goal of this study was to obtain critical biological insights revealing pathogenic potential-associated genes contributing to the isolation source difference from these established learning models. Based on the results, the developed learning models demonstrated strong performance, achieving an AUC greater than 0.95 in distinguishing clinical and environmental isolates using pangenome signals. Besides, the gene feature weight analysis from RF revealed the importance of specific accessory genes during Vp evolution including but not limited to functional unknown cloud genes, vspR, sctC5, and tdh1, which provides biological insights as potential future research directions. These findings essentially highlight critical importance of accessory and cloud genes in differentiating clinical and environmental isolates, and provide new insights into how recently acquired genes may contribute to pathogenic evolution of Vp. Additionally, the framework demonstrated in this study provides a cost-effective intelligent strategy by leveraging large public genomic datasets to support surveillance and risk assessment of seafood-associated pathogens.},
}

@article {pmid42249918,
year = {2026},
author = {Jeong, H and Choi, H and Park, YS},
title = {Comparative genomics reveals immunomodulatory and anti-obesity traits of Lactococcus lactis subsp. lactis.},
journal = {Applied microbiology and biotechnology},
volume = {},
number = {},
pages = {},
doi = {10.1007/s00253-026-13892-0},
pmid = {42249918},
issn = {1432-0614},
support = {RS-2025-24523283//National Research Foundation of Korea/ ; },
abstract = {Lactococcus lactis subsp. lactis strains have been widely recognized for their probiotic potential, including their immunomodulatory and anti-obesity effects. This study aims to determine the genomic basis of the health-promoting properties of L. lactis subsp. lactis CAB701 and WiKim0124 using whole-genome sequencing and comparative genomic analysis. Taxonomic classification using average nucleotide identity and digital DNA-DNA hybridization confirms both strains as L. lactis subsp. lactis. Genome alignment reveals high synteny among CAB701, WiKim0124, and the reference strains, with minor structural variations. Functional annotation identifies genes associated with carbohydrate metabolism, biofilm formation, and immune modulation. Pan-genome analysis shows a substantial proportion of strain-specific genes, suggesting niche-specific adaptation. Notably, L. lactis subsp. lactis CAB701 and WiKim0124 harbor unique biosynthetic gene clusters for nisin Z and sactipeptides, which may contribute to their antimicrobial and immunomodulatory functions. Additionally, genes involved in short-chain fatty acid metabolism are identified, highlighting their potential role in metabolic regulation. These findings provide valuable insights into the functional genetics of L. lactis subsp. lactis and their applicability as probiotics for immune modulation and obesity management. KEY POINTS: • Comparative genomics revealed strain-specific immune- and metabolism-linked genes • CAB701 and WiKim0124 uniquely harbor nisin Z and sactipeptide biosynthetic clusters • Genomic features support L. lactis application as functional probiotics.},
}

@article {pmid42245112,
year = {2026},
author = {Kumar, A and Muthuramalingam, P and Verma, L and Kumar, R and Kumar, N and Misra, J and Ravi, K and Shin, H and Ramesh, M},
title = {Modern genomic and omics-based technologies for millet breeding and genetic improvement.},
journal = {Frontiers in plant science},
volume = {17},
number = {},
pages = {1782766},
pmid = {42245112},
issn = {1664-462X},
abstract = {Millets are a diverse group of small seeded grasses that have long served as vital staple foods and forage crops across a wide range of agro-ecological regions. Known for their exceptional adaptability to marginal and resource poor environments, millets have historically supported farming communities in arid and semi-arid regions. Despite these advantages, they remain underutilized in modern agriculture due to limited genomic resources, harsh growing conditions, and insufficient technological support for their improvement. However, growing concerns over climate change, malnutrition and the need for sustainable agriculture have renewed global scientific interest in millet research and breeding. Recent breakthroughs in molecular biology such as marker-assisted selection (MAS), Genome-wide association studies (GWAS), genomic selection (GS), genetic engineering, omics technologies, speed breeding, and machine learning (ML) have significantly transformed the landscape of millet improvement. Advances in MAS, high-throughput genotyping, transcriptomics, proteomics, metabolomics, and phenomics have enabled more profound insights into the genetic architecture of key agronomic traits. These tools have facilitated the identification of genes, regulatory networks, and metabolic pathways governing drought tolerance, nutrient use efficiency, disease resistance and other essential stress responses. The integration of next-generation sequencing and comparative genomics has further expanded millet research through the development of reference genomes, pangenomes, and comprehensive germplasm characterizations. Pangenomic approaches, in particular, have uncovered structural variations and novel alleles that contribute to phenotypic diversity, offering valuable targets for breeding climate-resilient cultivars. High-resolution phenomic platforms have enhanced the precision of trait evaluation, enabling rapid screening of large populations under diverse environmental conditions. Additionally, genome editing technologies, especially CRISPR/Cas systems and multiplex CRISPR/Cas, have opened new avenues for precise genetic improvement by enabling targeted gene modification to enhance stress resilience and yield traits. Therefore, these integrated omics-driven and molecular breeding strategies are reshaping the millet improvement. With modern biotechnological innovations, researchers are now better equipped to develop high-yielding, nutrient-rich and climate-resilient millet cultivars. These advancements position millets as strategic crops that can strengthen global food and nutritional security while promoting sustainable agricultural systems in the face of mounting environmental challenges.},
}

@article {pmid42245389,
year = {2026},
author = {Murugavel, K and Karthikeyan, G and Raveendran, M and Sendhilvel, V and Sudha, A and Karthiba, L},
title = {Omics-based insights into endophytic Bacillus subtilis (TN FL 158) for blister blight management in Camellia sinensis.},
journal = {3 Biotech},
volume = {16},
number = {6},
pages = {246},
pmid = {42245389},
issn = {2190-572X},
abstract = {UNLABELLED: Blister blight of tea (Camellia sinensis), caused by Exobasidium vexans, is one of the most destructive foliar diseases in South India, with an incidence of up to 68% and yield losses approaching 50%. In the present study, an endophytic bacterial isolate, Bacillus subtilis (TN FL 158), obtained from the flower of C. sinensis, was evaluated for its in vitro antagonistic potential against E. vexans along with genome mining, metabolite profiling and host transcriptome analysis. Scanning electron microscopy indicated the association of bacterial cells with treated leaf and twig tissues following foliar application. The strain suppressed basidiospore germination by 93.39% (5.56% germination compared to 84% in the control) and exhibited siderophore production along with cellulase, protease and amylase activities. Whole genome sequencing yielded a 3.96 Mb genome with a GC content of 43.68%, comprising 3,765 protein-coding genes and several biosynthetic gene clusters associated with antimicrobial secondary metabolites such as fengycin, surfactin, iturin, bacilysin, subtilosin A, pulcherriminic acid and bacillibactin. Comparative genomic analysis revealed 84 singleton genes and an open pan-genome structure. Gas chromatography-mass spectrometry detected several non-volatile metabolites and volatile organic compounds in the bacterial culture. Transcriptome profiling of tea plants treated with B. subtilis (TN FL 158) and challenged with E. vexans indicated differential expression patterns of defense-related genes. Collectively, these findings suggest that B. subtilis (TN FL 158) may represent a promising candidate for further evaluation as a potential biocontrol agent for blister blight management in Camellia sinensis.

SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s13205-026-04829-5.},
}

@article {pmid42249289,
year = {2026},
author = {Zhou, ZL and Wu, Q and Liu, ZW and Wang, WB},
title = {Comparative genomics and epidemic success of Mycobacterium tuberculosis lineage 4 in eastern China.},
journal = {BMC genomics},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12864-026-13035-9},
pmid = {42249289},
issn = {1471-2164},
support = {2026PDWSYCQN-15//Healthcare Talents Youth Program of Shanghai Pudong New Area/ ; ZD2021CY001//Shanghai Municipal Science and Technology Major Project/ ; GWVI-11.1-03//Shanghai New Three-year Action Plan for Public Health/ ; 82073612//National Natural Science Foundation of China/ ; },
abstract = {BACKGROUND: Mycobacterium tuberculosis (Mtb) lineage 4 (L4) remains as a crucial component of the pathogen. Genetic factors potentiate the spread of Mtb, while the genomic feature and epidemic success at individual level of L4 strains have not been fully illustrated, especially in China. Therefore, the current study aimed to obtain additional understanding on the pan-genome architecture and transmission of the pathogen.

RESULTS: The results first revealed a low proportion of soft-core genes (28.66%) and high genetic diversity for Mtb L4 strains in eastern China. The pan-genome size increased with added genomes following an exponential growth trend, with no obvious plateau observed. Additionally, our results suggested a greater gene loss rate (mean: 0.0112) compared to gene gain rate (mean: 0.0039), suggesting its important roles in the course of adaptive evolution for L4 strains. Pan-genome was enriched in 120 KEGG pathways, of which the majority was metabolism (75.57%). Furthermore, we identified significant associations between the bacterial success and 5 genes (espK, ilvD, mazF7, aftD, ilvA), the presence of which suggested high transmissibility of L4 strains.

CONCLUSION: This study highlights an open and dynamic pan-genome structure of Mtb L4 strains in eastern China. The local strains are undergoing massive changes in gene families that shape its gene repertoires, thereby potentially conferring the adaptive potential to environment and bacterial transmission. Collectively, our findings allow for deeper insights into the pan-genome composition, phylogenetic relationship, evolutionary dynamic, and epidemic success of Mtb L4 strains.},
}

@article {pmid42249699,
year = {2026},
author = {Alexandrov, N and Blair, L and Wang, T and Lowe, D and Sayer, DC},
title = {HLA-DR Haplotype Diversity Revealed by Pangenome Sequence Analysis.},
journal = {HLA},
volume = {107},
number = {6},
pages = {e70757},
doi = {10.1111/tan.70757},
pmid = {42249699},
issn = {2059-2310},
abstract = {The HLA-DR region of the MHC, spanning HLA-DRB1 to HLA-DRA, is currently characterised by five unique haplotypes (named DR1, DR51, DR52, DR53 and DR8). All haplotypes have HLA-DRB1, HLA-DRB9 and HLA-DRA. The DR1 haplotype also has HLA-DRB6, the DR52 haplotype, HLA-DRB3 and HLA-DRB2, and DR53 also has HLA-DRB4, HLA-DRB7 and HLA-DRB8. The DR8 haplotype has no additional loci. HLA-DRB3, HLA-DRB4 and HLA-DRB5 are expressed genes, and HLA-DRB2, HLA-DRB6, HLA-DRB7 and HLA-DRB8 are pseudogenes. Whilst the genetic content of each haplotype is known, a detailed genomic comparison of these haplotypes has not been reported. To address this issue, we have performed multi-sequence alignments of the complete HLA-DRA to HLA-DRB1 region on 94 phased genome assemblies from the Pangenome Project. Our analysis reveals extensive structural variation and significant size differences between haplotypes characterised by large insertions and deletions. We also describe two new pseudogenes, locally named HLA-DRBTF1 and HLA-DRBTF2. HLA-DRBTF1 was present on DR1 and DR53 haplotypes, and HLA-DRBTF2 was found on all haplotypes with haplotype-specific short and long variants. Our analysis enables us to propose an updated, simplified map of the HLA-DR region, demonstrating the comparative arrangement of genes and pseudogenes between HLA-DR haplotypes.},
}

@article {pmid42240372,
year = {2026},
author = {Lamichhane, B and Kabir, A and Adams, AA and Burns, L and Johnson, B and Sponseller, B and Helmy, YA},
title = {Genomic diversity of multidrug-resistant Rhodococcus equi: novel sequence types, pangenome architecture, and phylogenomic evolution.},
journal = {Applied and environmental microbiology},
volume = {},
number = {},
pages = {e0248625},
doi = {10.1128/aem.02486-25},
pmid = {42240372},
issn = {1098-5336},
abstract = {UNLABELLED: Rhodococcus equi is a major cause of life-threatening pneumonia in foals under 6 months of age and an opportunistic pathogen in immunocompromised humans. Although common in soil and equine farm environments, its evolutionary dynamics, virulence architecture, and pathways of antimicrobial resistance (AMR) emergence remain poorly understood. This study integrated phenotypic characterization and whole-genome sequencing of 46 R. equi isolates from horses submitted for necropsy (n = 45) and equine fecal samples (n = 1) in Kentucky between January 2022 and December 2023 to define their resistance landscape, virulence potential, and population structure. A high burden of multidrug-resistant (MDR) strains was identified (32.6%), including resistance to rifamycin, macrolides, tetracyclines, sulfonamides, and cephalosporins. Nearly all isolates (97.8%) formed robust biofilms, survived intracellularly in macrophages, and carried key virulence determinants (vapA, vapH, iupT). Genomic analysis identified 22 multilocus sequence types (MLSTs), including 20 previously unreported novel sequence types (STs), indicating substantial lineage expansion. Pangenome analysis revealed a large accessory genome and limited core gene conservation; phylogenomic analysis revealed clustering with isolates from humans and other animal hosts, suggesting shared evolutionary ancestry and potential cross-species transmission. These findings highlight R. equi as a One Health concern at the animal-environment-human interface. The discovery of numerous novel STs, together with widespread MDR phenotypes and conserved virulence determinants, underscores the need for strengthened antimicrobial stewardship, enhanced genomic surveillance, and development of alternative therapeutic strategies. This study provides critical insights into the epidemiology, AMR emergence, and evolutionary dynamics of R. equi circulating within equine farm systems and its implications for both equine and human health.

IMPORTANCE: Rhodococcus equi is a bacterium commonly found in soil and around horse farms. While it is part of the natural environment, it can cause serious diseases, including life-threatening pneumonia in young foals and severe infections in people with weakened immune systems. Despite its importance, much remains unknown about how this pathogen spreads, evolves, and develops resistance to antibiotics. In this study, we combined laboratory testing with genome sequencing of R. equi obtained from necropsied horses to better understand how these bacteria resist antibiotics and form protective biofilms that make infections difficult to treat. Our genomic analyses revealed many previously unrecognized genetic lineages and showed that horse-associated strains share close evolutionary links with isolates from humans and other animals. Together, these findings highlight R. equi as an emerging concern and a potential public health risk, underscoring the importance of responsible antimicrobial use and expanded genomic surveillance to safeguard equine and human health.},
}

@article {pmid42241084,
year = {2026},
author = {Rodriguez, S and Rey-Varela, D and Blanco-Hortas, A and Martinez, C and Martínez, P and Travers, MA and Barja, JL and Dubert, J},
title = {Deciphering the pangenome of the shellfish pathogen Vibrio europaeus: evolutionary history and functional impact of core and accessory genes in aquaculture.},
journal = {Microbial genomics},
volume = {12},
number = {6},
pages = {},
doi = {10.1099/mgen.0.001682},
pmid = {42241084},
issn = {2057-5858},
abstract = {Vibrio europaeus is an important pathogen in shellfish aquaculture, yet its genomic diversity remains poorly understood. Here, we present the first comprehensive analysis of the V. europaeus pangenome, integrating genomic data from all strains available to date (n=39) sequenced specifically for this study. These were isolated from different aquaculture facilities (shellfish hatcheries) associated with mass mollusc mortalities from different geographical locations, years and host species. Our findings revealed an open pangenome with 61% of the genes associated with the accessory genome that contribute to environmental and host adaptations. Phylogenomic analyses of the core-genome (39% of the pangenome size) allowed us to evaluate the evolutionary history and intraspecific diversity of V. europaeus and revealed that Spanish strains displayed a much lower genetic variability than French, Chilean or American strains, probably due to a monophyletic radiation event. Functional annotation of core and accessory genes revealed the key virulence factors of the species, while it also disclosed that these are located mainly in the core genes. The high number of anti-phage defence systems encoded in the accessory genome explained almost all the variability of the species. The results provide important insights into the evolutionary history and ecological versatility of V. europaeus, with potential implications for diagnostics, epidemiological surveillance and disease management strategies in aquaculture.},
}

@article {pmid42243268,
year = {2026},
author = {Desai, D and Sharma, T and Gandham, N and Khopkar-Kale, P and Bharti, N and Kasibhatla, SM and Sonavane, U and Banerjee, R},
title = {Genomic characterization of multidrug-resistant Klebsiella pneumoniae clinical isolates from India.},
journal = {Scientific reports},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41598-026-54711-w},
pmid = {42243268},
issn = {2045-2322},
abstract = {Klebsiella pneumoniae is an emerging global threat driven by rising antimicrobial resistance and the spread of hypervirulent lineages. To investigate its evolving genomic landscape in India, we characterized two clinical K. pneumoniae isolates, NG_299 and NG_300, obtained from a tertiary care hospital in Pune and analyzed them in the context of Indian and global isolate collections. Comprehensive phenotypic and genomic analyses were performed using antimicrobial susceptibility testing, Illumina NovaSeq whole-genome sequencing and PCR-based confirmation of resistance and virulence markers. Both isolates exhibited multidrug resistance, remaining susceptible to only a limited subset of tested antibiotics. NG_299 (ST231) was susceptible to amikacin, colistin, and trimethoprim/sulfamethoxazole, whereas NG_300 (ST20) was found to be susceptible only to colistin and trimethoprim/sulfamethoxazole. Genomic profiling revealed thirty-two resistance determinants in NG_299 and fifty-two in NG_300, both of which produce extended-spectrum β-lactamases. Carbapenem resistance was linked to metallo-β-lactamase activity and the presence of AmpC was confirmed by antimicrobial susceptibility testing and PCR in NG_300. Pan-genome resistome analysis of global isolates identified conserved core genes (CRP, PhoP, rpoB) and a sparse occurrence of AMR genes (NDM, CTX-M, KPC, OXA, mcr) associated with horizontal gene transfer. Notably, NDM and CTX-M were present in both study isolates, with OXA variants detected in NG_299. Distinct missense mutations within shared resistance genes highlighted independent evolutionary trajectories. Both isolates carried virulence factors associated with adhesion, biofilm formation, iron acquisition, and secretion systems, including siderophores. Plasmid analysis identified IncF replicons in both isolates and blaNDM-5 on an IncFII plasmid in NG_299. These findings document the circulation of multidrug-resistant K. pneumoniae in Pune and underscore the urgent need for strengthened genomic surveillance.},
}

@article {pmid42243869,
year = {2026},
author = {Jin, J and Zhang, A and Shen, B and Li, X and Landis, JB and Chen, C and Yuan, Y and Li, L and Yang, L and Qu, S and Li, Y and Zhang, X and Liu, M and Sun, Y and Fan, D and Hao, Q},
title = {The T2T genome assembly of Ziziphus jujuba 'Huizao' and pan-genome analyses provide insights into fruit texture diversity in jujube.},
journal = {Molecular horticulture},
volume = {6},
number = {1},
pages = {},
pmid = {42243869},
issn = {2730-9401},
support = {32160684//National Natural Science Foundation of China/ ; },
}

@article {pmid42244773,
year = {2026},
author = {Espinoza, JL and Dupont, CL and Phillips, A},
title = {Leviathan: A fast, memory-efficient, and scalable taxonomic and pathway profiler for (pan)genome-resolved metagenomics and metatranscriptomics.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.07.14.664802},
pmid = {42244773},
issn = {2692-8205},
abstract = {Functional profiling of metagenomes and metatranscriptomes is essential for understanding microbial community capabilities, yet current methods require computationally expensive translated-search alignments that scale poorly to the large genome-resolved reference databases now common in the field. We introduce Leviathan, an open-source software package for integrated taxonomic and functional profiling that operates at both genome and pangenome resolution. Leviathan combines Sylph for ultra fast alignment-free taxonomic profiling with Salmon for pseudo-alignment-based read quantification in DNA-space against genome-resolved gene catalogs, bypassing the translated-search step that dominates runtime in existing approaches. For each (pan)genome, Leviathan functional profiling produces dual metrics: pathway abundance from aggregated gene-level quantification and pathway coverage from graph-based assessment of enzymatic step completeness. On CAMI-I and CAMI-II datasets, Leviathan achieved up to 74-fold faster runtimes and 14-fold lower memory usage compared to HUMAnN, while improving genome-level assignment accuracy by up to 12% and pangenome-level accuracy by up to 5%. We demonstrate Leviathan's applicability through two case studies: a marine plastisphere metagenomics dataset where differential coverage analysis revealed metabolic shifts between early and mature biofilm communities and a dental caries metatranscriptomics dataset where pangenome-resolved co-expression network analysis identified organism-specific transcriptional patterns diagnostic of health and disease states. Leviathan is available at https://github.com/jolespin/leviathan.},
}

@article {pmid42233644,
year = {2026},
author = {Dubin, CA and Zhao, C and Pollard, KS and Oskotsky, T and Golob, JL and Sirota, M},
title = {Expanding vaginal microbiome pangenomes via a custom MIDAS database reveals Lactobacillus crispatus accessory genes associated with cervical dysplasia.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0149825},
doi = {10.1128/msystems.01498-25},
pmid = {42233644},
issn = {2379-5077},
abstract = {The vaginal microbiome plays a central role in reproductive health. Vaginal microbiome dysbiosis is associated with many adverse reproductive health outcomes, but most studies have focused on associations at the species level. The potential contribution of intraspecies microbial variation, especially gene content differences across bacterial strains, remains underexplored in reproductive health contexts. The Metagenomic Intra-Species Diversity Analysis (MIDAS) framework enables such analyses, but depends on comprehensive reference databases. We constructed a MIDAS-compatible pangenome database from over 18,000 genomes in the Vaginal Microbiome Genome Collection (VMGC). Compared to the Genome Taxonomy Database (GTDB)-derived reference, the VMGC-derived database expanded the pangenomes of prevalent vaginal species, better capturing vaginal-specific intraspecies diversity. Applying this database to vaginal samples from a cervical dysplasia cohort, we identified 13 Lactobacillus crispatus accessory genes significantly associated with cervical dysplasia, including a HicAB toxin-antitoxin system, three transcriptional regulators, and three phage-derived genes. These findings highlight the utility of body site-specific reference resources and shotgun metagenomic sequencing for uncovering intraspecies microbial variation relevant to reproductive health.IMPORTANCEThe vaginal microbiome plays a critical role in reproductive health, and different bacteria from the same species can carry different genes that influence how the strains interact with the host and other microbes. These strain-level differences are often overlooked when microbiomes are analyzed only at the species level. Existing genomic reference databases are heavily biased toward gut and environmental bacteria, leaving the genetic diversity of vaginal microbes understudied. We built a specialized reference database from over 18,000 vaginal bacterial genomes that better reflects this diversity. We then applied this resource to quantify gene-level variation in vaginal samples from a cervical dysplasia cohort. Focusing on Lactobacillus crispatus, a prevalent and often beneficial vaginal species, we identified 13 genes that were more common in women with cervical dysplasia than in controls. This work demonstrates that body site-specific genomic resources are essential for uncovering strain-level bacterial differences relevant to reproductive health.},
}

@article {pmid42233679,
year = {2026},
author = {Cui, Y and Li, X and Li, X and Wang, J and Jin, H and Shi, K and Yan, J},
title = {Comparative genomics reveals Dehalogenimonas genome dynamics and evolutionary trajectories toward organohalide respiration.},
journal = {Applied and environmental microbiology},
volume = {},
number = {},
pages = {e0057926},
doi = {10.1128/aem.00579-26},
pmid = {42233679},
issn = {1098-5336},
abstract = {Dehalogenimonas spp. specialize in organohalide respiration, a metabolism that features reductive dehalogenase (RDase) as the key catalyst, yet their evolutionary history and adaptation to halogenated substrates are largely unknown. Here, we surveyed the respiratory gene modules in Dehalogenimonas and constructed a pangenome for this genus. Comparative analyses revealed a genus-wide trend of genome streamlining, marked by contraction of gene families for general cellular functions, alongside preferential expansion of RDase-coding rdhA genes. Pairwise collinearity analysis showed poorly conserved gene order, indicating extensive genome rearrangements during the diversification of Dehalogenimonas lineages. Despite such genomic plasticity, all Dehalogenimonas rdhA genes assigned a definitive function are organized into operons positioned immediately adjacent to a two-component regulatory system, indicating that their transcription is tightly coupled to environmental signal sensing. We also identified an ssrA-associated genomic island carrying the signature dcpA, providing strong evidence for a role of mobile genetic elements in facilitating the spread of dihaloelimination potential across Dehalogenimonas. Selection pressure analyses further indicated that dcpA has been shaped by episodic positive selection at specific codon sites, indicative of adaptive fine-tuning, whereas purifying selection across many codon sites removes deleterious mutations and preserves core RDase catalytic function. Collectively, these streamlined, mosaic genomes provide an integrated evolutionary view of metabolic specialization in Dehalogenimonas.IMPORTANCEOrganohalide-respiring bacteria (OHRB) contribute to the cleanup of persistent halogenated contaminants in subsurface environments. Members affiliated with the genus Dehalogenimonas represent a distinct OHRB phylotype and have attracted growing attention for their ability to detoxify a broad range of organohalides, including the carcinogen vinyl chloride. Compared with other well-characterized OHRB, the genome architecture and evolutionary history of Dehalogenimonas spp. remain poorly resolved at the genus scale. Here, we address this knowledge gap by establishing the first comparative genomic framework for Dehalogenimonas. Our analyses reveal genome streamlining associated with specialization in organohalide respiration across the genus. We also identify conserved mechanisms that govern the acquisition and transcriptional control of Dehalogenimonas reductive dehalogenase genes. Together, this work sheds light on how Dehalogenimonas lineages evolve, acquire, and regulate essential respiratory components, providing a foundation to better understand their divergence and guide the deployment of these keystone OHRB in bioremediation practices.},
}

@article {pmid42236495,
year = {2026},
author = {Qi, Y and Guo, S and Liu, Z and Wu, J and Sheng, H and Chen, L and Popyvanov, D and Li, Y and Fu, Y and Sun, H and Nagy, LG and Xiao, S},
title = {Pan-genome based on chromosome sequences of wild and cultivated Agaricus bisporus.},
journal = {Scientific data},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41597-026-07459-x},
pmid = {42236495},
issn = {2052-4463},
support = {No. U20A204//National Natural Science Foundation of China (National Science Foundation of China)/ ; },
abstract = {Agaricus bisporus, one of the most widely cultivated mushrooms around the world, plays an important role in economy and agriculture. In this study, by employing long-reads generated by PacBio and Nanopore sequencing, we assembled six novel high-quality genomes (of which three are telomere-to-telomere assemblies) with sizes 29.6 ~ 30.8 Mb and N50 lengths of 2.5 ~ 2.6 Mb. Combined with public genome data of nine strains, we successfully established a pan-genome of A. bisporus, comprising a total of 14,626 clusters of protein coding genes, of which 50.70%, 7.45%, 24.74% and 17.01% are defined as core, soft core, dispensable, and private clusters, respectively. A total of 5,646 non- redundant structural variants (SVs) were identified among wild and cultivated strains and the genes associated with SV were mapped. This work provides valuable whole-genome sequences and genomic resources across wild and cultivated strains of the most widely cultivated mushroom species for functional analyses of genomes.},
}

@article {pmid42226049,
year = {2026},
author = {Wang, M and Shao, C and Vílchez, JI and He, D and Chen, L and Zhang, JL and Zhang, H},
title = {Restriction-modification systems and prophages drive genomic diversification in Priestia megaterium.},
journal = {Biology direct},
volume = {21},
number = {1},
pages = {},
pmid = {42226049},
issn = {1745-6150},
support = {32470308//National Natural Science Foundation of China/ ; },
abstract = {Bacteria are frequently stressed by bacteriophages. Priestia megaterium is a bacterium of both agricultural and biotechnological importance, yet it has been unclear how the interplay between phage-imposed stress and bacterial immunity shapes the genome evolution and stability in P. megaterium. Through comparative genomics and methylome profiling, herein we show that restriction-modification (RM) systems are the dominant and ubiquitous barrier to lysogeny in P. megaterium. Intact prophages disproportionately carry anti-restriction genes, including multiple DNA methyltransferases and anti-restriction proteins, revealing the molecular strategies required to overcome the strong RM-mediated selective pressure inherent to this species. Prophage-derived genes are significantly enriched within the unique pangenome fraction and include auxiliary metabolic genes absent in host genomes. Moreover, prophage content strongly predicts phylogenetic structure in P. megaterium. Together, our findings demonstrate how defensive constraints, phage counter-adaptations, and horizontal acquisition jointly drive genomic diversification of P. megaterium.},
}

@article {pmid42226345,
year = {2026},
author = {Yang, T and Liu, N and Huang, L and Guo, J and Xue, X and Wang, M and Zhang, X and Quan, C and Feng, E and Tan, J and Zhang, Z and You, Y and Xia, Y and Huai, D and Chen, Y and Yan, L and Liu, K and Jiang, H and Lei, Y and Liao, B},
title = {High-quality genome of elite peanut cultivar ZH05 reveals subgenome asymmetry, pan-genome diversity, and breeding insights.},
journal = {Journal of integrative plant biology},
volume = {},
number = {},
pages = {},
doi = {10.1111/jipb.70308},
pmid = {42226345},
issn = {1744-7909},
abstract = {Peanut (Arachis hypogaea) is an allotetraploid legume crop of agricultural and economic importance worldwide. Despite advances in peanut genomics, the integration of genetic diversity with multi-omics landscapes remains limited, and a comprehensive understanding of subgenome asymmetry is still lacking. Here, we present a high-quality genome assembly of an elite peanut cultivar Zhonghua 5 (ZH05; 2,622.85 Mb with 73,718 predicted genes) and construct a species-specific pan-genome based on 1,286 accessions, uncovering 849.82 Mb of non-reference sequences and 18,484 novel genes. Over 23 million genetic variants and extensive gene PAVs substantially expand the landscape of genetic diversity in peanut. Integrative multi-omics (transcriptome, DNA methylation, chromatin accessibility, and three-dimensional genome architecture), combined with population genomics analyses, reveal pronounced and multi-layered subgenome asymmetry. Specifically, SubA shows higher chromatin accessibility and overall gene expression, whereas SubB displays more transposable elements, elevated DNA methylation, more genes under selection during domestication, and stronger three-dimensional chromatin interactions with more stable topologically associating domains. Furthermore, genetic dissection using a recombinant inbred line population identified several major stable QTLs for seed size, whose pyramiding contributes to ZH05's superior yield performance. Collectively, this study establishes an integrated genomic framework for peanut, illuminates asymmetric subgenome evolution across sequence, epigenetic, and chromatin architecture, and provides valuable resources for accelerating molecular breeding and crop improvement.},
}

@article {pmid42228388,
year = {2026},
author = {Wu, H and Liu, L and Li, S and Zhang, P and Xing, Z and Huang, Q and Kuang, D and Liu, W and Chen, C and Xia, Q},
title = {Whole-genome analysis of a novel Pandoraea sputorum lineage causing high-mortality bloodstream infections.},
journal = {Microbial genomics},
volume = {12},
number = {6},
pages = {},
pmid = {42228388},
issn = {2057-5858},
abstract = {Background. Pandoraea sputorum is an emerging multidrug-resistant pathogen primarily associated with cystic fibrosis. Bloodstream infections (BSIs) are rare but linked to high mortality. The genomic characteristics and evolutionary history of P. sputorum lineages causing BSIs remain poorly understood.Methods. We performed whole-genome sequencing on 18 P. sputorum isolates recovered from patients with BSIs in China between June 2022 and March 2024. Phylogenetic relationships were determined by core-genome SNP analysis, and the pan-genome was characterized using Roary. Antimicrobial resistance and virulence genes were identified using the CARD and VFDB databases. Evolutionary timescales were estimated using Bayesian molecular clock analysis.Results. The case fatality rate among patients was 27.8% (5 out of 18). Common clinical manifestations included fever (83.3%, 15 out of 18), productive cough (77.8%, 14 out of 18) and dyspnoea (61.1%, 11 out of 18). All isolates formed a distinct monophyletic lineage, genetically distant (>2,000 SNPs) from known P. sputorum strains but with minimal intra-lineage diversity (15-98 SNPs), indicating recent clonal expansion. The pan-genome was highly conserved, with core genes comprising 94.6% of the gene repertoire. All strains harboured core genome-encoded ceoB (efflux pump) and OXA-155 (β-lactamase) genes, conferring resistance to multiple antimicrobials but remaining susceptible to imipenem. Bayesian analysis estimated the origin of this lineage in 2004 (95% highest posterior density: 2003.2-2005.8), with major diversification occurring between 2007 and 2018.Conclusion. We identified a novel, recently emerged and highly clonal lineage of P. sputorum associated with high-mortality BSIs. Its stable reservoir of core genome-encoded resistance mechanisms poses a significant therapeutic challenge. This lineage represents an emerging multidrug-resistant threat to public health, necessitating enhanced surveillance and infection control measures.},
}

@article {pmid42231155,
year = {2026},
author = {Wang, M and Wang, J and Wang, C and Liu, C and Chen, J and Liang, Y and Liu, J and Yang, C and Yin, Z and Zhou, C and Mu, H and Du, Y},
title = {Pan-genome insights into genetic diversity, evolutionary dynamics, and pathogenic traits of Staphylococcus agnetis.},
journal = {BMC genomics},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12864-026-13008-y},
pmid = {42231155},
issn = {1471-2164},
support = {TJYXZDXK-3-026C//Tianjin Key Medical Discipline (Specialty) Construction Project/ ; A202304//Chinese Pharmacists Association Commissioned research project/ ; },
abstract = {BACKGROUND STAPHYLOCOCCUS AGNETIS: is an emerging pathogen primarily associated with bovine mastitis and avian lameness. Despite increasing reports of its occurrence across animal hosts, its genomic diversity and the distribution of antimicrobial resistance (AMR) and virulence-associated genes remain insufficiently characterized. RESULTS: The species S. agnetis possesses an open pan-genome, dominated by cloud gene families enriched in defense mechanisms and genomic plasticity, consistent with gene flux. Evolutionary reconstruction indicated that purifying selection and gene loss are the main signatures of evolutionary dynamics in the S. agnetis pan-genome, with extensive gene loss particularly affecting cell wall biogenesis functions. Notably, significant gene gain events were observed at early-diverging internal nodes of the phylogeny, suggesting that gene acquisition occurred during the early diversification of S. agnetis. AMR profiling identified a limited repertoire of AMR genes. However, the detection of a plasmid-borne AMR gene and the distribution of plasmids highlight the potential for plasmid-mediated dissemination of AMR in S. agnetis. Virulence profiling identified 28 chromosomally located putative virulence-related genes, predominantly homologous to S. aureus, including core adherence factors and sporadically distributed enterotoxin homologs suggestive of acquisition via horizontal gene transfer (HGT). CONCLUSIONS: Collectively, this study provides comprehensive insights into the genomic diversification of S. agnetis and highlights its emerging AMR traits and putative virulence potential in animal-associated settings.},
}

@article {pmid42232900,
year = {2026},
author = {Elufisan, TO and Rodriguez-Luna, IC and Sanchez-Varela, A and Bustos, VP and Lozano, L and Dantan-Gonzalez, E and Oyedara, OO and Correa-Basurto, J and Estrada-Perez, AR and Cortes-Espinosa, DV and Villalobos-Lopez, MA and Guo, X},
title = {Stenotrophomonas oleivorans sp. nov., a polycyclic aromatic hydrocarbon-degrading bacterium isolated from crude oil-contaminated soil in Tabasco, Mexico.},
journal = {Frontiers in microbiology},
volume = {17},
number = {},
pages = {1793198},
pmid = {42232900},
issn = {1664-302X},
abstract = {INTRODUCTION: Crude oil-contaminated soils harbor bacteria with specialized hydrocarbon-degrading capabilities, yet the Stenotrophomonas genus remains incompletely characterized at the species level. Strain ASS1, a motile Gram-negative rod, was isolated from crude oil-contaminated soil in Tabasco, Mexico, and initial 16S rRNA gene sequencing indicated affiliation with Stenotrophomonas, warranting full polyphasic characterization.

METHODS: The complete genome was sequenced using Illumina MiSeq and assembled into a single closed contig (4,564,481 bp; G+C content 66.59%; GenBank: CP031167). Genome quality was assessed with BUSCO v6.0.0 and CheckM2. Species boundaries were evaluated using average nucleotide identity (ANIb via JSpeciesWS) and digital DNA-DNA hybridization (dDDH via GGDC Formula 2) against 38 representative Stenotrophomonas genomes. Taxonomic placement was further resolved by TYGS, MLST, and core genome phylogenomics. PAH catabolic capacity was assessed through genome annotation and in vitro growth assays on four PAHs as sole carbon sources, analyzed by Kruskal-Wallis test.

RESULTS: BUSCO completeness was 99.7% and CheckM2 confirmed 100.0% completeness with 0.0% contamination. Despite 99.86% 16S rRNA gene identity to Stenotrophomonas geniculata ATCC 19374T, ANIb against the closest neighbor Stenotrophomonas riyadhensis CFS3442T was 93.30%, and dDDH was 50.4% (95% CI: 47.8-53.1%), both below established species thresholds. No pairwise comparison across the 38 genomes exceeded 54.3% dDDH. TYGS, MLST, and core genome phylogenomics consistently resolved ASS1 as a distinct lineage. Pan genome analysis confirmed an open pan genome (alpha = 0.485). A complete upper pathway PAH catabolic gene cassette was identified, and in vitro growth was statistically equivalent across all four PAH substrates (Kruskal-Wallis H(3) = 2.403, p = 0.493).

DISCUSSION: Collectively, the genomic, phylogenomic, and phenotypic evidence supports ASS1 as the type strain of a novel species, Stenotrophomonas oleivorans sp. nov. (= WFCC 1006/CM-CNRG 934T), with demonstrated broad spectrum PAH degradation capacity relevant to bioremediation.},
}

@article {pmid42233158,
year = {2026},
author = {Zhong, S and Xing, L and Li, H and Wang, L and Zhu, X and Wang, C},
title = {Genomic characterization and niche adaptive analysis of Pseudomonas promysalinigenes W2469: the first clinical isolate from a human bile specimen.},
journal = {Frontiers in cellular and infection microbiology},
volume = {16},
number = {},
pages = {1825480},
pmid = {42233158},
issn = {2235-2988},
abstract = {BACKGROUND: Pseudomonas promysalinigenes is a newly described bacterial species renowned for producing promysalin, a species-selective lipopeptide antibiotic. All previously reported strains of this species are derived from environmental niches such as plant rhizospheres, and no clinical infection cases associated with this bacterium have been documented to date. Thus, the clinical microbiology relevance, genomic features, and adaptive potential of P. promysalinigenes remain largely unexplored, and current reference databases have limited coverage of this rare species.

METHODS: A bacterial strain designated W2469 was isolated from the bile specimen of a patient with acute suppurative cholecystitis and cholecystolithiasis. Conventional phenotypic and molecular identification [matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS), VITEK 2 biochemical assay, 16S ribosomal RNA (rRNA), and whole-genome sequencing (WGS)] was performed. Bioinformatics analyses, including average nucleotide identity (ANI), digital DNA-DNA hybridization (dDDH), core genome single-nucleotide polymorphism (cgSNP), pan-genome analysis, and functional annotation against COG, KEGG, CAZy, VFDB, and CARD databases, were conducted to characterize the strain.

RESULTS: Conventional methods yielded consistent misidentification of the strain, while WGS definitively assigned it to P. promysalinigenes (ANI = 98.8%, dDDH = 91.1% against the type strain RW10S1). The strain exhibited a narrow-spectrum resistance phenotype, with resistance to aztreonam and ticarcillin/clavulanic acid, intermediate susceptibility to meropenem, and susceptibility to most clinically used antibiotics. Genomic annotation identified 25 antimicrobial resistance genes and 139 niche adaptation-related factors, most of which are low-identity homologs (<80%) of canonical reference sequences. Pan-genome analysis identified 571 clinical-specific genes associated with host adaptation, with complete loss of the environmental promysalin biosynthetic gene cluster.

CONCLUSION: This study provides the first documentation of P. promysalinigenes as a clinical isolate from human bile, expanding the known ecological niche of this species to the clinical setting. Conventional methods are prone to misidentifying this rare species, and WGS is critical for accurate taxonomic identification. Importantly, the strain exhibits clear adaptive phenotypes despite low sequence identity to known functional elements, highlighting profound knowledge gaps in the genomic diversity and uncharacterized adaptive mechanisms of this rare Pseudomonas species. This work provides a foundational genomic resource for future investigations into this emerging opportunistic pathogen.},
}

@article {pmid42210697,
year = {2026},
author = {Deka, N and Brauer, AL and Connerton, K and Hanson, BM and Walker, JN and Armbruster, CE},
title = {Pangenome analysis of Proteus mirabilis reveals lineage-specific antimicrobial resistance profiles and discordant genotype-phenotype correlations.},
journal = {Antimicrobial agents and chemotherapy},
volume = {},
number = {},
pages = {e0176825},
doi = {10.1128/aac.01768-25},
pmid = {42210697},
issn = {1098-6596},
abstract = {Urinary tract infections (UTIs) impose a large healthcare burden, with escalating antimicrobial resistance (AMR), and treatment failure. Proteus mirabilis is an undercharacterized and challenging UTI pathogen due to intrinsic resistance and biofilm formation. To understand P. mirabilis population genomics, we combined pangenome analysis, in silico AMR prediction, and phenotypic antimicrobial susceptibility testing (AST) across 1,027 P. mirabilis genomes derived from human urine specimens. This revealed a mosaic pangenome driven by extensive accessory genome plasticity. Multilocus sequence typing (MLST) identified 213 MLSTs, with only 7% having ≥10 genomes, highlighting strain diversity. AMR gene profiles were largely lineage-specific, with 25% of genomes harboring resistances for >6 antimicrobial subclasses. ST135 was identified as a highly MDR lineage, with 95% of genomes carrying ≥16 resistance genes. Mobile genetic element (MGE) analysis of 22 clinical isolates with complete, reference-level genomes revealed that Tn7 transposons, IS26-mediated genomic islands, and class 1 integrons act as vehicles for high AMR gene dissemination, including IS26-mediated gene stacking within a P. mirabilis Genomic Resistance Island 1 (PmGRI1) in ST135 isolates. While the presence of genes like aph(3')-la reliably predicted kanamycin resistance, discordance for antibiotics such as trimethoprim-sulfamethoxazole and chloramphenicol revealed that AMR gene stacking, regulatory context, and intrinsic mechanisms, like efflux pumps, modulate phenotypic outcomes. In summary, our study provides a comprehensive and phenotypic resolution of P. mirabilis AMR, establishing that resistance architecture is lineage-structured, MGE-driven, and phenotypically non-deterministic. We emphasize the need to shift toward a standardized, genome-informed surveillance framework to translate into diagnostic and therapeutic strategies.},
}

@article {pmid42221884,
year = {2026},
author = {Han, T and Liu, H and Lu, T and Jiang, C and Wang, C and Miao, G},
title = {Pan-genome analysis of soybean terpene synthase identifies GmTPS20 as a defense-related linalool synthase.},
journal = {Frontiers in plant science},
volume = {17},
number = {},
pages = {1845603},
pmid = {42221884},
issn = {1664-462X},
abstract = {Soybean terpene synthase (TPS) genes are pivotal to ecological adaptation and stress resilience, yet their genetic diversity, evolutionary history, and enzymatic mechanisms remain poorly understood. A pan-genomic survey of 27 soybean genomes was performed to identify and classify TPS loci by conservation status. Phylogenetic reconstruction and Ka/Ks analysis were used to infer evolutionary relationships and selection regimes. An uncharacterized core gene, GmTPS20, and its close homolog GmTPS15 were prioritized for functional characterization using expression profiling, subcellular localization, in vitro enzyme assays with geranyl diphosphate (GPP), neryl diphosphate (NPP), and farnesyl diphosphate (FPP) isomers, transient expression in Nicotiana benthamiana, and structural docking. The pan-genome survey identified 26 TPS loci: 15 core, four near-core, five variable, and two private, highlighting strong purifying selection on conserved members alongside lineage-specific losses. Soybean TPSs fell within the TPS-a, TPS-b, TPS-c, TPS-e/f, and TPS-g clades, with most loci exhibiting Ka/Ks < 1. GmTPS20 showed broad expression peaking in young leaves and was induced by insect herbivory and methyl jasmonate, whereas GmTPS15 was enriched in reproductive tissues. Both proteins localized to chloroplasts, consistent with the MEP pathway. GmTPS20 acted as a substrate-specific monoterpene synthase that converted GPP to linalool and NPP to linalool and nerol, but did not accept FPP isomers; transient expression in N. benthamiana confirmed linalool accumulation in planta. Under matched conditions, GmTPS15 produced no detectable volatile products. Structural docking indicated that both enzymes can bind GPP; however, GmTPS20 features a more compact diphosphate-coordination network and a deeper, narrower active site, whereas GmTPS15 adopts a more open pocket with reduced polar constraints, rationalizing their divergent catalytic behaviors. Collectively, these findings clarify mechanisms of TPS functional diversification in legumes and provide molecular targets for engineering terpenoid-based defense and desirable agronomic traits in soybean.},
}

@article {pmid42225687,
year = {2026},
author = {Prabhaharan, D and Kang, S and Nair, PS and Jeon, BS and Sang, BI},
title = {High-Quality Genome Assembly, Metabolome, Pangenome, and Metabolic Models of Megasphaera hexanoica KCCM 43214[T].},
journal = {Scientific data},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41597-026-07473-z},
pmid = {42225687},
issn = {2052-4463},
abstract = {Megasphaera hexanoica KCCM 43214[T], isolated from cow rumen, is capable of producing medium-chain carboxylic acids such as hexanoate and octanoate. In this study, we present a high-quality genome assembly, along with intracellular metabolomic profiling and pangenomic analysis. Illumina sequencing generated 2.3 Gbp from 15,293,634 reads with a GC content of 49.5%, while PacBio HiFi sequencing produced 331.5 Mbp across 45,266 reads, with an average read length of 7,323 bp and a HiFi read N50 of 8,214 bp. Hybrid assembly of short and long reads resulted in a single 2.88 Mbp contig, containing 2,835 protein-coding genes. Genome-scale metabolic models were constructed to evaluate its metabolic capabilities under specific growth conditions. Intracellular metabolomic analysis of cells grown in medium containing fructose and lactate revealed key metabolic activities associated with chain elongation. Pangenomic analysis across nine annotated genomes identified 6,721 orthologous genes using OrthoMCL, emphasizing the genetic and functional diversity within the Megasphaera genus. This dataset offers valuable insights into the metabolism and biotechnological potential of M. hexanoica KCCM 43214[T].},
}

@article {pmid42210017,
year = {2026},
author = {Spanner, R and Nazareno, ES and Henningsen, EC and Feist, A and Matny, O and Moscou, MJ and Rouse, MN and Kianian, SF and Mangelson, H and Langford, K and Liachko, I and Lubega, J and Kanyuka, K and Sperschneider, J and Dodds, PN and Figueroa, M and Steffenson, BJ},
title = {Haplotype-phased genomes of the barley leaf rust pathogen reveal evidence of repeat element expansion and somatic hybridization.},
journal = {G3 (Bethesda, Md.)},
volume = {},
number = {},
pages = {},
doi = {10.1093/g3journal/jkag137},
pmid = {42210017},
issn = {2160-1836},
abstract = {Barley leaf rust disease, caused by Puccinia hordei, leads to substantial yield losses and diminished malting quality of barley across temperate growing regions worldwide. To address the paucity of high-resolution genomic resources for this pathogen, we generated haplotype-phased, chromosome-scale assemblies for ten globally distributed isolates using PacBio HiFi and Hi-C sequencing. Phylogenomic analysis revealed seven distinct lineages of P. hordei, including evidence of nuclear exchange, with a shared nuclear haplotype detected between two US lineages. Nuclear genome sizes ranged from ∼140-147Mbp, with the exception of isolate 90ISR03 from Israel (∼163Mbp), which also harbored a 6.2Mbp extra scaffold in one nucleus exhibiting chromosomal characteristics. Consistent with its larger genome, P. hordei had a higher repeat content (∼70%) than related cereal rust fungi, driven primarily by the proliferation of LTR retroelements and DNA transposons. Across the global pan-genome of 13 unique nuclear haplotypes, approximately one-third of all protein orthogroups were conserved across all isolates. Only 18% of predicted effector orthogroups were conserved across all haplotypes, reflecting the highly dynamic and variable nature of the effector repertoire. The long-term propagation of clonal P. hordei lineages is apparent both within the US and globally, and nuclear exchange plays a role in generating novel diversity. Genome plasticity is evident in extensive structural variation, including large-scale translocations and inversions as well as an extra chromosome. These chromosome-level, haplotype-resolved genomes provide a foundational resource for exploring the evolution, diversity, and avirulence gene repertoire of P. hordei.},
}

@article {pmid42210061,
year = {2026},
author = {Wang, B and Tian, S and Yao, X and Wan, Y and Xu, C and Luo, C and Tang, H and Yang, Z and Virk, MS and Bin, P and Lu, L},
title = {Pan-genomic and pan-transcriptomic integration unveils evolutionary dynamics and regulatory diversification of the WRKY gene family in Camellia sinensis.},
journal = {BMC plant biology},
volume = {},
number = {},
pages = {},
doi = {10.1186/s12870-026-09047-y},
pmid = {42210061},
issn = {1471-2229},
abstract = {BACKGROUND: The WRKY transcription factor family, characterized by its conserved WRKYGQK motif and zinc finger structure, serves as a central regulatory module in plants, mediating developmental, stress-responsive, and metabolic processes through W-box binding. In Camellia sinensis, WRKY genes act as molecular integrators that link environmental cues to the biosynthesis of quality-related compounds, underscoring the importance of understanding their evolutionary patterns for genetic improvement. However, previous research has been limited by single-reference genome approaches, which fail to capture the full spectrum of WRKY gene presence-absence variation across diverse tea plant cultivars.

RESULTS: This study presents the first pan-genome-wide analysis of the WRKY family in any plant species, integrating data from 22 tea plant genomes. We identified a comprehensive set of WRKY genes and classified them into core and dispensable categories, revealing extensive presence-absence variants (PAVs) that were overlooked in single-reference studies. Phylogenetic reconstruction resolved 11 subfamilies, with notable lineage-specific expansions. Mechanistically, core gene evolution was predominantly driven by whole-genome or segmental duplication under strong purifying selection, whereas dispensable genes, particularly in certain subfamilies, showed signals of adaptive evolution and were enriched through dispersed duplication. Transcriptomic analysis uncovered co-expression networks among highly expressed WRKY clusters, indicating functional redundancy and sub-functionalization in stress adaptation.

CONCLUSIONS: The findings from the present study provide insights into the evolutionary dynamics of presence-absence and copy-number variation within the WRKY family in tea plants, establishing a valuable genetic resource for enhancing stress resilience and metabolic traits in tea breeding programs.},
}

@article {pmid42203797,
year = {2026},
author = {Suzuki, Y and Owa, C and Kobayashi, H and Nakabayashi, R and McNulty, B and Violich, I and Paten, B and Miga, KH and Morishita, S},
title = {Accessing medically relevant complex regions with a pangenome graph of 20 near-complete Japanese haplotypes.},
journal = {Nature communications},
volume = {17},
number = {1},
pages = {},
pmid = {42203797},
issn = {2041-1723},
mesh = {Humans ; Male ; Gene Conversion ; Genetic Variation ; *Genome, Human/genetics ; *Haplotypes/genetics ; Japan ; Segmental Duplications, Genomic ; *East Asian People/genetics ; },
abstract = {Pangenome projects have enhanced our understanding of human genomic and genetic diversity, but repetitive regions are still challenging to assemble and yet medically important. Here we generate 20 near-complete haplotypes from 10 Japanese male individuals using three complementary long-read and long-range datasets and construct a pangenome graph from these haplotype-resolved assemblies. All haplotypes achieve an N50 value exceeding 100 Mbp for gapless contigs. We substantially improve the average reconstruction rate of complete haplotypes from 46.8% and 52.8% in two previous pangenome graphs to 91.2% within 30 segmentally duplicated complex regions. Furthermore, we identify complete minor haplotypes in the KIR and SMN regions that are absent in those previous pangenome graphs. We find putatively biased gene conversion events occurring in only one direction around the SMN and beta-defensin (DEFB) genes, implying non-random evolution in these regions. Our study contributes to the growing body of pangenomic data, offering a more refined view of human genomic diversity involving complex segmental duplications.},
}

Humans
Male
Gene Conversion
Genetic Variation
*Genome, Human/genetics
*Haplotypes/genetics
Japan
Segmental Duplications, Genomic
*East Asian People/genetics

@article {pmid42204142,
year = {2026},
author = {Jiu, S and Lei, Y and Fang, L and Huang, Y and Chen, W and Xu, Y and Wang, L and Lv, Z and Liu, X and Han, L and Liu, B and Zhang, C and Dong, X and Zhang, T and Wang, J and Zhang, X and Cai, Y and Zheng, W and Li, F and Liu, C and Li, H and Zhu, J and Yu, F and Li, M and Wang, J and Chen, L and Yin, C and Peng, L and Wang, J and Zhang, Z and An, X and Yu, L and Liu, R and Zhang, Y and Wang, L and Wu, Y and Bernard, A and Nakagomi, M and Wang, S and Elisabeth, D and Li, D and Zhao, Q and Xue, H and Dong, Y and Sun, Z and Duan, S and Zhang, C},
title = {Pangenome and resequencing analyses reveal flowering evolution and genetic control in Cerasus.},
journal = {Nature communications},
volume = {17},
number = {1},
pages = {},
pmid = {42204142},
issn = {2041-1723},
support = {CARS-30//Earmarked Fund for China Agriculture Research System/ ; 32541114//National Natural Science Foundation of China (National Science Foundation of China)/ ; 32260734//National Natural Science Foundation of China (National Science Foundation of China)/ ; },
mesh = {*Flowers/genetics/growth & development ; *Gene Expression Regulation, Plant ; *Genome, Plant ; *Prunus/genetics/growth & development ; Plant Proteins/genetics/metabolism ; MADS Domain Proteins/genetics/metabolism ; Promoter Regions, Genetic ; Evolution, Molecular ; Phylogeny ; Genomics ; Biological Evolution ; },
abstract = {Prunus subgenus Cerasus contains numerous species with ornamental, edible, and medicinal value. However, limited genomic resources have constrained systematic analyses of structural variation and the genetic basis of key phenological traits in this group. Here, we assemble eight genomes from diverse Cerasus species. Together with 13 published genomes, we construct a pangenome of 21 accessions representing 17 species. Phenological observations reveal substantial variation in flowering time. Integrating comparative genomics, transcriptomics, and population genetic analyses highlight candidate regulators of flowering time. We find that AGAMOUS-LIKE 9 (AGL9) is strongly associated with flowering progression. Both ectopic expression and transient overexpression of PavAGL9 can accelerate post-dormancy flowering progression. We reveal that PavBPC6 binds the PavAGL9 promoter and represses its transcription, indicating a negative regulatory role. Furthermore, PavAGL9 interacts physically with PavSEP1 and PavPMADS2, suggesting synergistic roles in floral organ development. Our pangenome resource establishes a comprehensive genomic framework for Cerasus and provides insights into the regulation of flowering progression.},
}

*Flowers/genetics/growth & development
*Gene Expression Regulation, Plant
*Genome, Plant
*Prunus/genetics/growth & development
Plant Proteins/genetics/metabolism
MADS Domain Proteins/genetics/metabolism
Promoter Regions, Genetic
Evolution, Molecular
Phylogeny
Genomics
Biological Evolution

@article {pmid42206158,
year = {2026},
author = {Abdurakhmonov, IY},
title = {Cotton genetic mapping for plant biotechnology: from markers to graph pan-genomes and sustainable breeding.},
journal = {Frontiers in plant science},
volume = {17},
number = {},
pages = {1825852},
pmid = {42206158},
issn = {1664-462X},
abstract = {Cotton improvement remains a major challenge in plant biotechnology because stable yield, fiber quality, and stress resilience must be delivered from complex allopolyploid genomes under variable environmental conditions. Genetic mapping has progressively transformed this challenge into deployable breeding knowledge, advancing from sparse marker systems to high-density SNP arrays, reference genomes, and, more recently, structural-variation-aware pan-genomes and graph genomes. This review argues that cotton's genomic complexity, homoeolog redundancy, and strong genotype-by-environment interactions have driven methodological innovation rather than the simple transfer of approaches developed in other crops. It synthesizes advances in linkage mapping, GWAS, eQTL analysis, fine mapping, functional validation, and marker deployment, with emphasis on how these tools have enabled breeder-ready assays, marker-assisted selection, and emerging predictive breeding frameworks. It further examines how cotton mapping contributes to sustainable intensification by enhancing disease resistance, abiotic resilience, fiber value, and trait-stacking efficiency. Finally, this review highlights unresolved challenges in homoeolog-aware inference, structural variant genotyping, phenotyping throughput, and environment-aware prediction. It outlines a next-phase agenda in which graph genomes, scalable validation, and climate-informed models become central to cotton biotechnology.},
}

@article {pmid42198589,
year = {2026},
author = {Desales-Decaro, EO and Castro-Escarpulli, G and Saldaña-Padilla, A and Cravioto, A and Castelán-Sánchez, HG and Navarro-Ocaña, A},
title = {Comparative Genomics of Escherichia coli Serogroups 64474, O179, O188 and Shigella boydii O16.},
journal = {Pathogens (Basel, Switzerland)},
volume = {15},
number = {5},
pages = {},
pmid = {42198589},
issn = {2076-0817},
mesh = {*Escherichia coli/genetics/classification ; *Serogroup ; *Genomics/methods ; Humans ; *Genome, Bacterial ; Phylogeny ; *Shigella boydii/genetics/classification ; Whole Genome Sequencing ; Virulence Factors/genetics ; Multigene Family ; Escherichia coli Infections/microbiology ; },
abstract = {Shigella spp., and Escherichia coli exhibit notable genomic and phenotypic similarities, including serologically and genetically related somatic antigens. For example, the relationship among pathogenic strains E. coli 64474, O179, O188, and S. boydii O16 suggests a shared clonal origin. To evaluate their genomic proximity, a comparative genomics study was conducted using whole-genome sequencing. Comparative genomics involved rfb gene cluster regions and whole-genome comparisons. Phylogenomic inferences were performed using the virtual genome fingerprint (VGF) method with bootstrap support. The results revealed a high degree of genomic similarity and a close evolutionary relationship among E. coli strains, which also demonstrated genetic associations with clinically relevant pathotypes through the presence of virulence genes. Furthermore, serogroups 64474, O188, and S. boydii O16 exhibited close genetic relationships, suggesting that serotype 64474 could represent a novel serogroup, although its similarity to O188 indicates the influence of divergent factors. These findings support the hypothesis that these E. coli strains originated from a common clonal lineage, enhancing our understanding of serogroup diversity and the evolutionary dynamics within enteric pathogens.},
}

*Escherichia coli/genetics/classification
*Serogroup
*Genomics/methods
Humans
*Genome, Bacterial
Phylogeny
*Shigella boydii/genetics/classification
Whole Genome Sequencing
Virulence Factors/genetics
Multigene Family
Escherichia coli Infections/microbiology

@article {pmid42185280,
year = {2026},
author = {Macias-Velasco, JF and Zhuo, X and Tomlinson, C and Belter, EA and Kremitzki, M and Albracht, D and Lindsay, T and Xing, X and Tekkey, N and Zhang, W and Garza, JE and Xu, Z and Xin, Z and Fu, Q and Lawson, HA and Stitziel, NO and Fulton, RS and Li, D and , and Wang, T},
title = {Benchmarking genome choice in functional genomics analyses.},
journal = {Nature communications},
volume = {},
number = {},
pages = {},
doi = {10.1038/s41467-026-73663-3},
pmid = {42185280},
issn = {2041-1723},
support = {U41HG010972//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; U41HG010971//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; U24HG012070//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; R01HG007175//U.S. Department of Health & Human Services | NIH | National Human Genome Research Institute (NHGRI)/ ; },
abstract = {The human genome reference established a shared coordinate system for genome function, but it is incomplete and not fully representative of human diversity. Here, we benchmark how genome representation and corresponding analytical frameworks for each representation shape functional genomics using chromatin accessibility sequencing (ATAC-seq), RNA sequencing, whole-genome bisulfite sequencing, and chromosome conformation capture (Hi-C) data from lymphoblastoid cell lines derived from five individuals with fully phased genome assemblies. We compare results across hg38, CHM13, the draft human pangenome, and each individual's maternal and paternal assemblies. Because current pipelines and quality control conventions are tuned to hg38, several of these comparisons reflect genome representation in the context of available methods, rather than sequence alone. Individual identity accounts for 57.52-78.47% of total variance in functional estimates, whereas genome choice contributes 0.002-7.85% and sample-by-genome interactions contribute 0.63-5.43%. About 2% of biological signals are detectable only with personal assemblies. Although these effects are modest overall, some biologically important features remain inaccessible to linear references. Consistent with this, graph-based DNA methylation analysis in the human pangenome reveals a non-reference AluY5a insertion within a putative TNKS enhancer at chromosome 8p23.1 that becomes visible and hypermethylated only in the pangenome.},
}