@article {pmid39805704,
year = {2025},
author = {Miao, Z and Yue, JX},
title = {Interactive visualization and interpretation of pangenome graphs by linear-reference-based coordinate projection and annotation integration.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279461.124},
pmid = {39805704},
issn = {1549-5469},
abstract = {With the increasing availability of high-quality genome assemblies, pangenome graphs emerged as a new paradigm in the genomics field for identifying, encoding, and presenting genomic variation at both population and species levels. However, it remains challenging to truly dissect and interpret pangenome graphs via biologically informative visualization. To facilitate better exploration and understanding of pangenome graphs towards novel biological insights, here we present a web-based interactive Visualization and interpretation framework for linear-Reference-projected Pangenome Graphs (VRPG). VRPG provides efficient and intuitive supports for exploring and annotating pangenome graphs along a linear-genome-based coordinate system (e.g., that of a primary linear reference genome). Moreover, VRPG offers many unique features such as in-graph path highlighting for graph-constituent input assemblies, copy number characterization for graph-embedding nodes, graph-based mapping for query sequences, all of which are highly valuable for researchers working with pangenome graphs. Additionally, VRPG enables side-by-side visualization between the graph-based pangenome representation and the conventional primary-linear-reference-genome-based feature annotations, therefore seamlessly bridging the graph and linear genomic contexts. To further demonstrate its functionality and scalability, we applied VRPG to the cutting-edge yeast and human reference pangenome graphs derived from hundreds of high-quality genome assemblies via a dedicated web portal and examined their local genome diversity in the graph contexts.},
}

@article {pmid39803467,
year = {2025},
author = {Shivakumar, VS and Langmead, B},
title = {Mumemto: efficient maximal matching across pangenomes.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2025.01.05.631388},
pmid = {39803467},
issn = {2692-8205},
abstract = {Aligning genomes into common coordinates is central to pangenome analysis and construction, but it is also computationally expensive. Multi-sequence maximal unique matches (multi-MUMs) are guideposts for core genome alignments, helping to frame and solve the multiple alignment problem. We introduce Mumemto, a tool that computes multi-MUMs and other match types across large pangenomes. Mumemto allows for visualization of synteny, reveals aberrant assemblies and scaffolds, and highlights pangenome conservation and structural variation. Mumemto computes multi-MUMs across 320 human genome assemblies (960GB) in 25.7 hours with under 800 GB of memory, and over hundreds of fungal genome assemblies in minutes. Mumemto is implemented in C++ and Python and available open-source at https://github.com/vikshiv/mumemto .},
}

@article {pmid39802740,
year = {2025},
author = {Liu, Z and Bernard, A and Wang, Y and Dirlewanger, E and Wang, X},
title = {Genomes and integrative genomic insights into the genetic architecture of main agronomic traits in the edible cherries.},
journal = {Horticulture research},
volume = {12},
number = {1},
pages = {uhae269},
pmid = {39802740},
issn = {2662-6810},
abstract = {Cherries are one of the economically important fruit crops in the Rosaceae family, Prunus genus. As the first fruits of the spring season in the northern hemisphere, their attractive appearance, intensely desirable tastes, high nutrients content, and consumer-friendly size captivate consumers worldwide. In the past 30 years, although cherry geneticists and breeders have greatly progressed in understanding the genetic and molecular basis underlying fruit quality, adaptation to climate change, and biotic and abiotic stress resistance, the utilization of cherry genomic data in genetics and molecular breeding has remained limited to date. Here, we thoroughly investigated recent discoveries in constructing genetic linkage maps, identifying quantitative trait loci (QTLs), genome-wide association studies (GWAS), and validating functional genes of edible cherries based on available de novo genomes and genome resequencing data of edible cherries. We further comprehensively demonstrated the genetic architecture of the main agronomic traits of edible cherries by methodically integrating QTLs, GWAS loci, and functional genes into the identical reference genome with improved annotations. These collective endeavors will offer new perspectives on the availability of sequence data and the construction of an interspecific pangenome of edible cherries, ultimately guiding cherry breeding strategies and genetic improvement programs, and facilitating the exploration of similar traits and breeding innovations across Prunus species.},
}

@article {pmid39802648,
year = {2025},
author = {Kan, NP and Yin, Z and Qiu, YF and Zheng, E and Chen, J and Huang, J and Du, Y},
title = {A pan-genome perspective on the evolutionary dynamics of polyphyly, virulence, and antibiotic resistance in Salmonella enterica serovar Mbandaka highlights emerging threats to public health and food safety posed by cloud gene families.},
journal = {Current research in food science},
volume = {10},
number = {},
pages = {100957},
pmid = {39802648},
issn = {2665-9271},
abstract = {Salmonella enterica serovar Mbandaka, a prevalent foodborne pathogen, poses a threat to public health but remains poorly understood. We have determined the phylogenomic tree, genetic diversity, virulence, and antimicrobial resistance (AMR) profiles on a large genomic scale to elucidate the evolutionary dynamics within the Mbandaka pan-genome. The polyphyletic nature of this serovar is characterized by two distinct phylogenetic groups and inter-serovar recombination boundaries, that potentially arising from recombination events at the H2-antigen loci. The open pan-genome exhibited a flexible gene repertoire, with numerous cloud gene families involved in virulence and AMR. Extensive gene gain and loss observed at the terminal nodes of the phylogenetic tree indicate that Mbandaka individuals have undergone frequent gene turnover. The resulting changes in virulence and AMR genes potentially pose emerging threats to public health. We explored serovar conversion due to recombination of H-antigen loci, inter-serovar divergences in gene gain and loss, prophage-mediated acquisition of virulence factors, and the role of incompatibility group plasmids in acquiring resistance determinants as key molecular mechanisms driving the pathogenicity and antibiotic resistance of Mbandaka. Our work contributes to a comprehensive understanding of the complex mechanisms of pathogenesis and the ongoing evolutionary arms race with current therapeutic approaches in serovar Mbandaka.},
}

@article {pmid39799915,
year = {2025},
author = {Yang, J and Zhang, S and Geng, L and Zhao, D and Xing, S and Ji, X and Yan, L},
title = {Comparative genomics analysis of the reason for [12]C[6+] heavy-ion irradiation in improving Fe3O4 nanoparticle yield of Acidithiobacillus ferrooxidans.},
journal = {Ecotoxicology and environmental safety},
volume = {289},
number = {},
pages = {117668},
doi = {10.1016/j.ecoenv.2025.117668},
pmid = {39799915},
issn = {1090-2414},
abstract = {The Fe3O4 nanoparticle synthesized by Acidithiobacillus ferrooxidans have a broad practical value, while the low yield limits their commercial application. Herein, we employed a [12]C[6+] heavy-ion beam to induce mutagenesis of A. ferrooxidans BYM and successfully screened a mutant BYMT-200 with a 1.36 mg/L Fe3O4 nanoparticle yield, which could stably inherit over many generations based on assessing cell magnetism and Fe3O4 nanoparticle synthesis. Comparative genome analysis detected 14 mutation sites, causing six synonymous mutations, one missense mutation, and one nonsense mutation. We further annotated the genes involved in the mutation, such as hcp, hsdM, yghU, K7B00_11365, and K7B00_11355, which are responsible for the substantial changes in the Fe3O4 nanoparticle yield of A. ferrooxidans. Additionally, we performed a pan-genome analysis to understand how these genes regulate Fe3O4 nanoparticle synthesis. The core genome of 2376 orthologous clusters was identified and visualized by progressive Mauve alignment and OrthoVenn. A total of 109 regulatory genes related to iron metabolism were identified, mainly involved in electron transport, iron acquisition, iron storage, and oxidative stress. The mutant genes are closely related to iron-sulfur clusters and oxidative stress. Accordingly, we proposed a hypothetical mechanism for increasing Fe3O4 nanoparticle production in A. ferrooxidans BYMT-200 to withstand high oxidative stress caused by heavy ion radiation. Our study offers significant theoretical guidance for further acquiring the high-yield Fe3O4 nanoparticle-producing bacteria and studying the mechanism of its synthesis.},
}

@article {pmid39799174,
year = {2025},
author = {Shin, HD and Park, W and Chai, HH and Lee, Y and Jung, J and Ko, BJ and Kim, H},
title = {Chromosome-level Genome Assembly of Korean Long-tailed Chicken and Pangenome of 40 Gallus gallus Assemblies.},
journal = {Scientific data},
volume = {12},
number = {1},
pages = {51},
pmid = {39799174},
issn = {2052-4463},
support = {PJ013341//Rural Development Administration (RDA)/ ; },
mesh = {Animals ; *Chickens/genetics ; *Genome ; *Chromosomes ; Republic of Korea ; },
abstract = {This study presents the first chromosome-level genome assembly of the Korean long-tailed chicken (KLC), a unique breed of Gallus gallus known as Ginkkoridak. Our assembly achieved a super contig N50 of 5.7 Mbp and a scaffold N50 exceeding 90 Mb, with a genome completeness of 96.3% as assessed by BUSCO using the aves_odb10 set. We also constructed a comprehensive pangenome graph, incorporating 40 Gallus gallus assemblies, including the KLC genome. This graph comprises 87,934,214 nodes, 121,720,974 edges, and a total sequence length of 1,709,850,352 bp. Notably, our KLC assembly contributed 1,919,925 bp of new sequences to the pangenome, underscoring the unique genetic makeup of this breed. Furthermore, in comparison with the pangenome, we identified 36,818 structural variants in KLC, which included 2,529 insertions, 27,743 deletions, and 6,546 of either insertions or deletions shorter than 1 kb. We also successfully identified pan-genome wide non-reference sequences. Our KLC assembly and pangenome graph provide valuable genomic resources for studying G. gallus populations.},
}

Animals
*Chickens/genetics
*Genome
*Chromosomes
Republic of Korea

@article {pmid39797734,
year = {2025},
author = {Ryu, H and Han, H and Kim, C and Kim, J},
title = {GDBr: genomic signature interpretation tool for DNA double-strand break repair mechanisms.},
journal = {Nucleic acids research},
volume = {53},
number = {2},
pages = {},
pmid = {39797734},
issn = {1362-4962},
support = {RS-2023-00247499//National Research Foundation of Korea/ ; CRC22013-300//National Research Council of Science and Technology/ ; HI22C132200//Korea Health Industry Development Institute/Republic of Korea ; //Korea Research Institute of Bioscience and Biotechnology/ ; CRC22013-300//NST grant funded by the Korea government (MSIT)/ ; },
mesh = {*DNA Breaks, Double-Stranded ; Humans ; *Software ; *Genomics/methods ; *DNA Repair/genetics ; Genome, Human ; DNA End-Joining Repair/genetics ; Homologous Recombination ; },
abstract = {Large genetic variants can be generated via homologous recombination (HR), such as polymerase theta-mediated end joining (TMEJ) or single-strand annealing (SSA). Given that these HR-based mechanisms leave specific genomic signatures, we developed GDBr, a genomic signature interpretation tool for DNA double-strand break repair mechanisms using high-quality genome assemblies. We applied GDBr to a draft human pangenome reference. We found that 78.1% of non-repetitive insertions and deletions and 11.0% of non-repetitive complex substitutions contained specific signatures. Of these, we interpreted that 98.7% and 1.3% of the insertions and deletions were generated via TMEJ and SSA, respectively, and all complex substitutions via TMEJ. Since population-level pangenome datasets are being dramatically accumulated, GDBr can provide mechanistic insights into how variants are formed. GDBr is available on GitHub at https://github.com/Chemical118/GDBr.},
}

*DNA Breaks, Double-Stranded
Humans
*Software
*Genomics/methods
*DNA Repair/genetics
Genome, Human
DNA End-Joining Repair/genetics
Homologous Recombination

@article {pmid39795357,
year = {2025},
author = {Jung, H and Han, G and Lee, D and Jung, HK and Kim, YS and Kong, HJ and Kim, YO and Seo, YS and Park, J},
title = {Understanding the Impact of Salt Stress on Plant Pathogens Through Phenotypic and Transcriptomic Analysis.},
journal = {Plants (Basel, Switzerland)},
volume = {14},
number = {1},
pages = {},
doi = {10.3390/plants14010097},
pmid = {39795357},
issn = {2223-7747},
support = {R2024019//National Institute of Fisheries Science/ ; },
abstract = {For plant diseases to become established, plant pathogens require not only virulence factors and susceptible hosts, but also optimal environmental conditions. The accumulation of high soil salinity can have serious impacts on agro-biological ecosystems. However, the interactions between plant pathogens and salinity have not been fully characterized. This study investigated the effects of salt stress on representative plant pathogens, such as Burkholderia gladioli, Burkholderia glumae, Pectobacterium carotovorum subsp. carotovorum (Pcc), Ralstonia solanacearum, and Xanthomonas oryzae pv. oryzae. Phenotypic assays revealed that B. gladioli and R. solanacearum are highly sensitive to salt stress, exhibiting significant reductions in growth, motility, and enzyme production, whereas Pcc showed notable tolerance. Pan-genome-based comparative transcriptomics identified co-downregulated patterns in B. gladioli and R. solanacearum under stress conditions, indicating the suppression of bacterial chemotaxis and type III secretion systems. Uniquely upregulated patterns in Pcc were associated with enhanced survival under high salinity, such as protein quality control, osmotic equilibrium, and iron acquisition. Additionally, the application of salt stress combined with the beneficial bacterium Chryseobacterium salivictor significantly reduced tomato wilt caused by R. solanacearum, suggesting a potential management strategy. This study underscores practical implications for effectively understanding and controlling plant pathogens under future climate changes involving salt stress.},
}

@article {pmid39794865,
year = {2025},
author = {Passarelli-Araujo, H and Venancio, TM and Hanage, WP},
title = {Relating ecological diversity to genetic discontinuity across bacterial species.},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {8},
pmid = {39794865},
issn = {1474-760X},
mesh = {*Genome, Bacterial ; *Bacteria/genetics/classification ; Genetic Variation ; Phylogeny ; Mycobacterium tuberculosis/genetics ; Machine Learning ; Evolution, Molecular ; Biodiversity ; },
abstract = {BACKGROUND: Genetic discontinuity represents abrupt breaks in genomic identity among species. Advances in genome sequencing have enhanced our ability to track and characterize genetic discontinuity in bacterial populations. However, exploring the degree to which bacterial diversity exists as a continuum or sorted into discrete and readily defined species remains a challenge in microbial ecology. Here, we aim to quantify the genetic discontinuity (δ) and investigate how this metric is related to ecology.

RESULTS: We harness a dataset comprising 210,129 genomes to systematically explore genetic discontinuity patterns across several distantly related species, finding clear breakpoints which vary depending on the taxa in question. By delving into pangenome characteristics, we uncover a significant association between pangenome saturation and genetic discontinuity. Closed pangenomes are associated with more pronounced breaks, exemplified by Mycobacterium tuberculosis. Additionally, through a machine learning approach, we detect key features such as gene conservation patterns and functional annotations that significantly impact genetic discontinuity prediction.

CONCLUSIONS: Our study clarifies bacterial genetic patterns and their ecological impacts, enhancing the delineation of species boundaries and deepening our understanding of microbial diversity.},
}

*Genome, Bacterial
*Bacteria/genetics/classification
Genetic Variation
Phylogeny
Mycobacterium tuberculosis/genetics
Machine Learning
Evolution, Molecular
Biodiversity

@article {pmid39791953,
year = {2025},
author = {Huang, Y and Sahu, SK and Liu, X},
title = {Deciphering recent transposition patterns in plants through comparison of 811 genome assemblies.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.14570},
pmid = {39791953},
issn = {1467-7652},
abstract = {Transposable elements (TEs) are significant drivers of genome evolution, yet their recent dynamics and impacts within and among species, as well as the roles of host genes and non-coding RNAs in the transposition process, remain elusive. With advancements in large-scale pan-genome sequencing and the development of open data sharing, large-scale comparative genomics studies have become feasible. Here, we performed complete de novo TE annotations and identified active TEs in 310 plant genome assemblies across 119 species and seven crop populations. Using 811 high-quality genomes, we detected 13 844 553 TE-induced structural variants (TE-SVs), providing unprecedented resolution in delineating recent TE activities. Our integrative analysis revealed a mutual evolutionary relationship between TEs and host genomes. On one hand, host genes and ncRNAs are involved in the transposition process, as evidenced by their colocalization and coactivation with TEs, and may play a role in chromatin regulation. On the other hand, TEs drive genetic innovation by promoting the duplication of host genes and inserting into regulatory regions. Moreover, genes influenced by active TEs are linked to plant growth, nutrient absorption, storage metabolism and environmental adaptation, aiding in crop domestication and adaptation. This TE dynamics atlas not only reveals evolutionary and functional features linked to transposition activity but also highlights the role of TEs in crop domestication and adaptation, paving the way for future exploration of TE-mediated genome evolution and crop improvement strategies.},
}

@article {pmid39789611,
year = {2025},
author = {Chen, W and Xie, Q and Fu, J and Li, S and Shi, Y and Lu, J and Zhang, Y and Zhao, Y and Ma, R and Li, B and Zhang, B and Grierson, D and Yu, M and Fei, Z and Chen, K},
title = {Graph pangenome reveals the regulation of malate content in blood-fleshed peach by NAC transcription factors.},
journal = {Genome biology},
volume = {26},
number = {1},
pages = {7},
pmid = {39789611},
issn = {1474-760X},
mesh = {*Malates/metabolism ; *Prunus persica/genetics/metabolism ; *Transcription Factors/metabolism/genetics ; *Fruit/genetics/metabolism ; *Plant Proteins/genetics/metabolism ; *Genome, Plant ; Gene Expression Regulation, Plant ; Genome-Wide Association Study ; Promoter Regions, Genetic ; },
abstract = {BACKGROUND: Fruit acidity and color are important quality attributes in peaches. Although there are some exceptions, blood-fleshed peaches typically have a sour taste. However, little is known about the genetic variations linking organic acid and color regulation in peaches.

RESULTS: Here, we report a peach graph-based pangenome constructed from sixteen individual genome assemblies, capturing abundant structural variations and 82.3 Mb of sequences absent in the reference genome. Pangenome analysis reveals a long terminal repeat retrotransposon insertion in the promoter of the NAC transcription factor (TF) PpBL in blood-fleshed peaches, which enhances PpBL expression. Genome-wide association study identifies a significant association between PpBL and malate content. Silencing PpBL in peach fruit and ectopic overexpression of PpBL in tomatoes confirm that PpBL is a positive regulator of malate accumulation. Furthermore, we demonstrate that PpBL works synergistically with another NAC TF, PpNAC1, to activate the transcription of the aluminum-activated malate transporter PpALMT4, leading to increased malate content.

CONCLUSIONS: These findings, along with previous research showing that PpBL and PpNAC1 also regulate anthocyanin accumulation, explain the red coloration and sour taste in blood-fleshed peach fruits.},
}

*Malates/metabolism
*Prunus persica/genetics/metabolism
*Transcription Factors/metabolism/genetics
*Fruit/genetics/metabolism
*Plant Proteins/genetics/metabolism
*Genome, Plant
Gene Expression Regulation, Plant
Genome-Wide Association Study
Promoter Regions, Genetic

@article {pmid39789465,
year = {2025},
author = {Yacoub, E and Baby, V and Sirand-Pugnet, P and Arfi, Y and Mardassi, H and Blanchard, A and Chibani, S and Ben Abdelmoumen Mardassi, B},
title = {A sweeping view of avian mycoplasmas biology drawn from comparative genomic analyses.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {24},
pmid = {39789465},
issn = {1471-2164},
abstract = {BACKGROUND: Avian mycoplasmas are small bacteria associated with several pathogenic conditions in many wild and poultry bird species. Extensive genomic data are available for many avian mycoplasmas, yet no comparative studies focusing on this group of mycoplasmas have been undertaken so far.

RESULTS: Here, based on the comparison of forty avian mycoplasma genomes belonging to ten different species, we provide insightful information on the phylogeny, pan/core genome, energetic metabolism, and virulence of these avian pathogens. Analyses disclosed considerable inter- and intra-species genomic variabilities, with genome sizes that can vary by twice as much. Phylogenetic analysis based on concatenated orthologous genes revealed that avian mycoplasmas fell into either Hominis or Pneumoniae groups within the Mollicutes and could split into various clusters. No host co-evolution of avian mycoplasmas can be inferred from the proposed phylogenetic scheme. With 3,237 different gene clusters, the avian mycoplasma group under study proved diverse enough to have an open pan genome. However, a set of 150 gene clusters was found to be shared between all avian mycoplasmas, which is likely encoding essential functions. Comparison of energy metabolism pathways showed that avian mycoplasmas rely on various sources of energy. Superposition between phylogenetic and energy metabolism groups revealed that the glycolytic mycoplasmas belong to two distinct phylogenetic groups (Hominis and Pneumoniae), while all the arginine-utilizing mycoplasmas belong only to Hominis group. This can stand for different evolutionary strategies followed by avian mycoplasmas and further emphasizes the diversity within this group. Virulence determinants survey showed that the involved gene arsenals vary significantly within and between species, and could even be found in species often reported apathogenic. Immunoglobulin-blocking proteins were detected in almost all avian mycoplasmas. Although these systems are not exclusive to this group, they seem to present some particular features making them unique among mycoplasmas.

CONCLUSION: This comparative genomic study uncovered the significant variable nature of avian mycoplasmas, furthering our knowledge on their biological attributes and evoking new hallmarks.},
}

@article {pmid39780644,
year = {2025},
author = {Yasuoka, K and Gotoh, Y and Taniguchi, I and Nagano, DS and Nakamura, K and Mizuno, Y and Abe, T and Ogura, Y and Nakajima, H and Uesugi, M and Miura, M and Seto, K and Wakabayashi, Y and Isobe, J and Watari, T and Senda, S and Hayakawa, N and Ogawa, E and Sato, T and Nanishi, E and Sakai, Y and Kato, A and Miyata, I and Ouchi, K and Ohga, S and Hara, T and Hayashi, T},
title = {Genome Analysis of Japanese Yersinia pseudotuberculosis Strains Isolated From Kawasaki Disease Patients and Other Sources and Their Phylogenetic Positions in the Global Y. pseudotuberculosis Population.},
journal = {Microbiology and immunology},
volume = {},
number = {},
pages = {},
doi = {10.1111/1348-0421.13199},
pmid = {39780644},
issn = {1348-0421},
support = {//This work was supported by a grant for Kawasaki Disease Research from the Japan Blood Products Organization and JSPS KAKENHI (Grant Number 23k15366)./ ; },
abstract = {Yersinia pseudotuberculosis (Ypt) is a gram-negative bacterium that infects both humans and animals primarily through fecal‒oral transmission. While Ypt causes acute gastroenteritis in humans, an association with Kawasaki disease (KD), a disease that primarily affects infants and young children and causes multisystemic vasculitis, has also been suspected. Although KD represents a significant health concern worldwide, the highest annual incidence rate is reported in Japan. Previously, a geographical origin-dependent population structure of Ypt comprising the Asian, transitional, and European clades was proposed. However, genomic data on KD-associated Ypt strains is currently unavailable. In this study, to analyze the phylogenetic and genomic features of KD-associated strains, we determined the whole-genome sequences of 35 Japanese Ypt strains, including 11 KD-associated strains, and constructed a genome set (n = 204) representing the global population of Ypt by adding publicly available Ypt genomes. In a phylogenetic analysis, all sequenced Japanese strains, including the KD-associated strains, belonged to the Asian clade, which appeared to be the ancestral clade of Ypt, and the KD-associated strains belonged to multiple lineages in this clade. Strains from patients with Far East scarlet-like fever (FESLF), a KD-related disease, also belonged to the Asian clade. Moreover, no KD strain-specific genes were identified in pan-genome-wide association study analyses. Notably, however, the gene encoding a superantigen called Yersinia pseudotuberculosis-derived mitogen (YPM) showed a distribution pattern highly biased to the Asian clade. Although further studies are needed, our results suggest that Asian clade strains may have a greater potential to trigger KD.},
}

@article {pmid39779953,
year = {2025},
author = {Secomandi, S and Gallo, GR and Rossi, R and Rodríguez Fernandes, C and Jarvis, ED and Bonisoli-Alquati, A and Gianfranceschi, L and Formenti, G},
title = {Pangenome graphs and their applications in biodiversity genomics.},
journal = {Nature genetics},
volume = {},
number = {},
pages = {},
pmid = {39779953},
issn = {1546-1718},
abstract = {Complete datasets of genetic variants are key to biodiversity genomic studies. Long-read sequencing technologies allow the routine assembly of highly contiguous, haplotype-resolved reference genomes. However, even when complete, reference genomes from a single individual may bias downstream analyses and fail to adequately represent genetic diversity within a population or species. Pangenome graphs assembled from aligned collections of high-quality genomes can overcome representation bias by integrating sequence information from multiple genomes from the same population, species or genus into a single reference. Here, we review the available tools and data structures to build, visualize and manipulate pangenome graphs while providing practical examples and discussing their applications in biodiversity and conservation genomics across the tree of life.},
}

@article {pmid39777507,
year = {2025},
author = {Shelton, AN and Yu, FB and Grossman, AR and Bhaya, D},
title = {Abundant and active community members respond to diel cycles in hot spring phototrophic mats.},
journal = {The ISME journal},
volume = {},
number = {},
pages = {},
doi = {10.1093/ismejo/wraf001},
pmid = {39777507},
issn = {1751-7370},
abstract = {Photosynthetic microbial mats in hot springs can provide insights into the diel behaviors of communities in extreme environments. In this habitat, photosynthesis dominates during the day, leading to super-oxic conditions, with a rapid transition to fermentation and anoxia at night. Multiple samples were collected from two springs over several years to generate metagenomic and metatranscriptomic datasets. Metagenome assembled genomes comprised 71 taxa (in 19 different phyla), of which twelve core taxa were present at high abundance in both springs. The eight most active taxa identified by metatranscriptomics were an oxygenic cyanobacterium (Synechococcus sp.), five anoxygenic phototrophs from three different phyla, and two understudied heterotrophs from phylum Armatimonadota. In all eight taxa, a significant fraction of genes exhibited a diel expression pattern although peak timing varied considerably. The two abundant heterotrophs exhibit starkly different peak timing of expression, which we propose is shaped by their metabolic and genomic potential to use carbon sources that become differentially available during the diel cycle. Network analysis revealed pathway expression patterns that had not previously been linked to diel cycles, including ribosome biogenesis and chaperones. This provides a framework for analyzing metabolically coupled communities and the dominant role of the diel cycle.},
}

@article {pmid39772210,
year = {2024},
author = {Jdeed, G and Morozova, VV and Tikunova, NV},
title = {Genome Analysis of Anti-Phage Defense Systems and Defense Islands in Stenotrophomonas maltophilia: Preservation and Variability.},
journal = {Viruses},
volume = {16},
number = {12},
pages = {},
doi = {10.3390/v16121903},
pmid = {39772210},
issn = {1999-4915},
support = {075-15-2021-1085//the Ministry of Science and Higher Education of the Russian Federation/ ; },
mesh = {*Stenotrophomonas maltophilia/genetics/virology ; *Bacteriophages/genetics/physiology ; *Phylogeny ; *Genome, Bacterial ; Genomic Islands ; },
abstract = {Anti-phage defense systems are widespread in bacteria due to the latter continuous adaptation to infection by bacteriophages (phages). Stenotrophomonas maltophilia has a high degree of intrinsic antibiotic resistance, which makes phage therapy relevant for the treatment of infections caused by this species. Studying the array of anti-phage defense systems that could be found in S. maltophilia helps in better adapting the phages to the systems present in the pathogenic bacteria. Pangenome analysis of the available S. maltophilia strains with complete genomes that were downloaded from GenBank, including five local genomes, indicated a wide set of 72 defense systems and subsystems that varied between the strains. Seven of these systems were present in more than 20% of the studied genomes and the proteins encoded by the systems were variable in most of the cases. A total of 27 defense islands were revealed where defense systems were found; however, more than 60% of the instances of systems were found in four defense islands. Several elements linked to the transfer of these systems were found. No obvious associations between the pattern of distribution of the anti-phage defense systems of S. maltophilia and the phylogenetic features or the isolation site were found.},
}

*Stenotrophomonas maltophilia/genetics/virology
*Bacteriophages/genetics/physiology
*Phylogeny
*Genome, Bacterial
Genomic Islands

@article {pmid39770839,
year = {2024},
author = {Gonzalez-Silva, A and San Juan-Mendo, M and Delgado-Prudencio, G and Hernández-García, JA and Larios-Serrato, V and Aguilar, C and Villa-Tanaca, L and Hernández-Rodríguez, C},
title = {Comparative Genomics and Biosynthetic Cluster Analysis of Antifungal Secondary Metabolites of Three Strains of Streptomyces albidoflavus Isolated from Rhizospheric Soils.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122637},
pmid = {39770839},
issn = {2076-2607},
support = {CB 283225//Consejo Nacional de Humanidades, Ciencia y Tecnología/ ; SIP 20220742, 20220795, 20231480, 20231481, 20240945, 20240946//Instituto Politécnico Nacional/ ; },
abstract = {Streptomyces is a genus of Gram-positive bacteria with high GC content. It remains attractive for studying and discovering new antibiotics, antifungals, and chemotherapeutics. Streptomyces genomes can contain more than 30 cryptic and expressed biosynthetic gene clusters (BGC) encoding secondary metabolites. In this study, three Streptomyces strains isolated from jungle rhizospheric soil exhibited supernatants that can inhibit sensitive and fluconazole-resistant Candida spp. The genomes of the strains Streptomyces sp. A1, J25, J29 ori2 were sequenced, assembled de novo, and analyzed. The genome assemblies revealed that the size of the genomes was 6.9 Mb, with linear topology and 73.5% GC. A phylogenomic approach identified the strains with high similitudes between 98.5 and 98.7% with Streptomyces albidoflavus SM254 and R-53649 strains, respectively. Pangenomic analysis of eight genomes of S. albidoflavus strains deposited in the Genomes database recognized 4707 core protein orthogroups and 745 abundant accessory and exclusive protein orthogroups, suggesting an open pangenome in this species. The antiSMASH software detected candicidin and surugamide BGC-encoding polyene and octapeptide antifungal secondary metabolites in other S. albidoflavus. CORASON software was used to compare the synteny, and the abundance of genes harbored in the clusters was used. In conclusion, although the three strains belong to the same species, each possesses a distinct genome, as evidenced by the different phenotypes, including antifungal and extracellular enzymatic activities.},
}

@article {pmid39770825,
year = {2024},
author = {Heidarpanah, S and Li, K and Thibodeau, A and Meniaï, I and Parreira, VR and Quessy, S and Segura, M and Fittipaldi, N and Gaucher, ML},
title = {Genomic Diversity and Virulence Factors of Clostridium perfringens Isolated from Healthy and Necrotic Enteritis-Affected Broiler Chicken Farms in Quebec Province.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122624},
pmid = {39770825},
issn = {2076-2607},
support = {IT09545//Mitacs/ ; },
abstract = {Avian necrotic enteritis due to the Gram-positive bacterium Clostridium perfringens has re-emerged following the ban on antibiotic growth promoters in many poultry producing countries. The limited number of previous studies has left important gaps in our understanding of the genetic diversity and virulence traits of the pathogen. To address these knowledge gaps, in this study, we sequenced the genomes of 41 Clostridium perfringens isolates recovered from commercial broiler chicken flocks in Quebec, Canada, including isolates from healthy birds and those affected by necrotic enteritis. We sought to understand the pangenome diversity and interrogated the genomes for key virulence factors involved in necrotic enteritis pathogenesis. On average, the genomes had a GC content of 28% and contained 3206 coding sequences. A variable presence of toxins, degradative hydrolytic enzymes, and collagen-binding proteins was also found. Through pangenome analysis, we revealed a total of 10,223 genes, 652 (6.4%) of which formed the core genome. Additionally, we identified 17 different plasmids, 12 antibiotic resistance genes, and nine prophage regions. Overall, our results demonstrated a relatively high genetic diversity among chicken Clostridium perfringens isolates collected from the same geographical location, offering new insights into potential virulence mechanisms and adaptation of the pathogen within poultry populations.},
}

@article {pmid39770754,
year = {2024},
author = {Bidzhieva, SK and Tourova, TP and Grouzdev, DS and Samigullina, SR and Sokolova, DS and Poltaraus, AB and Avtukh, AN and Tereshina, VM and Mardanov, AV and Zhaparov, NS and Nazina, TN},
title = {Sulfate-Reducing Bacteria Isolated from an Oil Field in Kazakhstan and a Description of Pseudodesulfovibrio karagichevae sp. nov.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122552},
pmid = {39770754},
issn = {2076-2607},
support = {21-64-00019//Russian Science Foundation/ ; },
abstract = {Sulfidogenic bacteria cause numerous issues in the oil industry since they produce sulfide, corroding steel equipment, reducing oil quality, and worsening the environmental conditions in oil fields. The purpose of this work was to isolate and taxonomically identify the sulfidogenic bacteria responsible for the corrosion of steel equipment at the Karazhanbas oil field (Kazakhstan). In this study, we characterized five sulfidogenic strains of the genera Pseudodesulfovibrio, Oleidesulfovibrio, and Acetobacterium isolated from the formation water of the Karazhanbas oil field (Kazakhstan). Sulfate-reducing strain 9FUS[T] revealed 98.9% similarity of the 16S rRNA gene sequence with the closely related strain 'Pseudodesulfovibrio methanolicus' 5S69[T] and was studied in detail to enhance the taxonomic resolution. Strain 9FUS[T] grew optimally at 23-28 °C, pH 6.5, and 0-2% (w/v) NaCl. The strain used lactate, pyruvate, methanol, ethanol, fructose, ribose, and H2/CO2 (in the presence of acetate) as carbon and energy sources for sulfate reduction. Iso-C17:1 ω11, C15:0, iso-C15:0, and C16:0 were the predominant fatty acids. The genome is 4.20 Mbp with a G + C content of 64.0%. The average nucleotide identity and digital DNA-DNA hybridization values with Pseudodesulfovibrio spp. genomes were 72.5-91.6% (<95%) and 18.5-45.0% (<70%), respectively, and supported our conclusion that 9FUS[T] (=VKM B-3654[T] = KCTC 25498[T]) belonged to a novel Pseudodesulfovibrio species, for which the name Pseudodesulfovibrio karagichevae sp. nov. is proposed. Pangenome analysis of sixteen Pseudodesulfovibrio species and functional annotation analysis of identified genes revealed complete modules of enzymes of the main metabolic pathways, characteristic of bacteria of this genus, and unique genes highlighting the adaptations of strain 9FUS[T] in carbohydrate metabolism, nutrient uptake, and environmental stress response. Isolation of these strains expands our understanding of the diversity of sulfidogens in oil reservoirs and can be used to test the effectiveness of biocides used in an oil field.},
}

@article {pmid39770704,
year = {2024},
author = {You, Y and Xu, X and Liu, H and Zhang, L},
title = {Locust Pathogen Aspergillus oryzae XJ1 Is Different from Aspergillus oryzae and Aspergillus flavus Based on Genomics Comparisons.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122501},
pmid = {39770704},
issn = {2076-2607},
support = {CXGC2024F05, CXGC2024D05//Agricultural scientific and technological innovation project of Shandong Academy of Ag-ricultural Sciences/ ; ZR2022MC117//Shandong Provincial Natural Science Foundation/ ; },
abstract = {Fungi play an increasingly important role in the biological control of insect pests. Aspergillus oryzae XJ1 is highly virulent to locust adults and nymphs, which are a destructive economic pest worldwide. Because of its host association with locusts, which is unique in Aspergillus, in this study, we examined the genetic relationships of A. oryzae XJ1 within Aspergillus. We sequenced the genome of A. oryzae XJ1 and compared it with the genomes of other Aspergillus species. The complete genome of A. oryzae XJ1 is 37.9 Mb, comprising 11,720 putative genes, assembled into eight chromosomes. The genome size is similar to that of other A. oryzae strains. Phylogenomic analysis indicated that A. oryzae XJ1 was most closely related to A. flavus NRRL3357, not A. oryzae RIB40. Core/pan-genome analysis of A. oryzae XJ1 and other Aspergillus species revealed that A. oryzae XJ1 had 704 strain-specific genes, whereas A. flavus NRRL3357, A. oryzae KDG 21, and A. parasiticus NRRL 2999 had 646, 955, and 779 unique genes, respectively. The A. oryzae XJ1 genome showed structural differences compared with the genomes of A. oryzae RIB40 and A. flavus NRRL3357 in genomic synteny analysis. These results indicate that A. oryzae XJ1 is genetically distinct at the genome level from other Aspergillus species, including A. oryzae and A. flavus, and may be as a distinct species. This will provide new insight into the classification of Aspergillus based on genomics.},
}

@article {pmid39770688,
year = {2024},
author = {Reynoso, EC and Delgado-Suárez, EJ and Hernández-Pérez, CF and Chavarin-Pineda, Y and Godoy-Lozano, EE and Fierros-Zárate, G and Aguilar-Vera, OA and Castillo-Ramírez, S and Gómez-Pedroso, LDCS and Sánchez-Zamorano, LM},
title = {Geography, Antimicrobial Resistance, and Genomics of Salmonella enterica (Serotypes Newport and Anatum) from Meat in Mexico (2021-2023).},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122485},
pmid = {39770688},
issn = {2076-2607},
support = {CF-2020-87198//Consejo Nacional de Humanidades, Ciencias y Tecnologías/ ; I1200/311/2023//Consejo Nacional de Humanidades, Ciencias y Tecnologías/ ; },
abstract = {Salmonella enterica non-typhoidal is a major contributor to diarrheal diseases, with over 2600 serovars identified across diverse environments. In Mexico, serovars Newport and Anatum have shown a marked increase, especially in foodborne disease, posing a public health problem. We conducted a cross-sectional study from 2021 to 2023 using active epidemiological surveillance to assess contamination in ground beef and pork at butcher shops nationwide. It involved isolation, phenotypic antimicrobial resistance, comparative genomics, spatial distribution, antimicrobial-resistance genes, and pangenome analysis. A total of 402 non-typhoidal S. enterica strains were isolated, including 59 Newport and 50 Anatum. After curating for redundancy, 45 Newport and 32 Anatum strains remained. We found that 75% of Newport strains exhibited multidrug resistance (MDR), compared to 25% of Anatum strains. Salmonella Newport also showed a broader distribution and stronger antibiotic-resistance capacity, particularly due to genes such as mphA and ramA. Our pangenome analysis showed a predominance of cell maintenance and survival-process genes in the accessory genome of both serotypes. Considering unique genes, Salmonella Anatum and Newport showed a notorious abundance of genes with functions related to replication, recombination, and repair. The substantial rise of Anatum and Newport strains in meat samples for human consumption presents an epidemiological alert, highlighting the critical need for stringent surveillance programs to mitigate human and ecosystem health risks.},
}

@article {pmid39770679,
year = {2024},
author = {Mwamburi, SM and Islam, SI and Dinh-Hung, N and Dangsawat, O and Sowanpreecha, R and Khang, LTP and Montha, N and Therdtatha, P and Dwinanti, SH and Permpoonpattana, P and Linh, NV},
title = {Genomic Characterization of Bacillus sp. THPS1: A Hot Spring-Derived Species with Functional Features and Biotechnological Potential.},
journal = {Microorganisms},
volume = {12},
number = {12},
pages = {},
doi = {10.3390/microorganisms12122476},
pmid = {39770679},
issn = {2076-2607},
abstract = {Bacillus sp. THPS1 is a novel strain isolated from a high-temperature hot spring in Thailand, exhibiting distinctive genomic features that enable adaptation to an extreme environment. This study aimed to characterize the genomic and functional attributes of Bacillus sp. THPS1 to understand its adaptation strategies and evaluate its potential for biotechnological applications. The draft genome is 5.38 Mbp with a GC content of 35.67%, encoding 5606 genes, including those linked to stress response and sporulation, which are essential for survival in high-temperature conditions. Phylogenetic analysis and average nucleotide identity (ANI) values confirmed its classification as a distinct species within the Bacillus genus. Pangenome analysis involving 19 others closely related thermophilic Bacillus species identified 1888 singleton genes associated with heat resistance, sporulation, and specialized metabolism, suggesting adaptation to nutrient-deficient, high-temperature environments. Genomic analysis revealed 12 biosynthetic gene clusters (BGCs), including those for polyketides and non-ribosomal peptides, highlighting its potential for synthesizing secondary metabolites that may facilitate its adaptation. Additionally, the presence of three Siphoviridae phage regions and 96 mobile genetic elements (MGEs) suggests significant genomic plasticity, whereas the existence of five CRISPR arrays implies an advanced defense mechanism against phage infections, contributing to genomic stability. The distinctive genomic features and functional capacities of Bacillus sp. THPS1 make it a promising candidate for biotechnological applications, particularly in the production of heat-stable enzymes and the development of resilient bioformulations.},
}

@article {pmid39768397,
year = {2024},
author = {Klaysubun, C and Chaichana, N and Suwannasin, S and Singkhamanan, K and Yaikhan, T and Kantachote, D and Pomwised, R and Wonglapsuwan, M and Surachat, K},
title = {Genomic Characterization of Probiotic Purple Nonsulfur Bacteria Cereibacter sphaeroides Strains S3W10 and SS15: Implications for Enhanced Shrimp Aquaculture.},
journal = {Life (Basel, Switzerland)},
volume = {14},
number = {12},
pages = {},
doi = {10.3390/life14121691},
pmid = {39768397},
issn = {2075-1729},
support = {B13F660074 and B13F670076//NSRF via the Program Management Unit for Human Resources and Institutional Development, Research and Innovation/ ; },
abstract = {Cereibacter sphaeroides strains S3W10 and SS15, isolated from shrimp ponds, exhibit potential probiotic benefits for aquaculture. In this study, the genomic features of S3W10 and SS15 were thoroughly characterized to evaluate their probiotic properties and safety for aquaculture use. The genomes of S3W10 and SS15 consist of 130 and 74 contigs, with sizes of 4.6 Mb and 4.4 Mb and GC contents of 69.2%. Average nucleotide identity (ANI), digital DNA-DNA hybridization (dDDH), and phylogenomic analyses confirmed that these strains belong to C. sphaeroides. Genome annotation predicted 4260 coding sequences (CDS) in S3W10 and 4086 CDS in SS15, including genes associated with stress tolerance, nutrient absorption, and antioxidant activity. Notably, genes related to vitamin B12 synthesis, digestive enzyme production, and carotenoid biosynthesis, which support shrimp health, were identified in both genomes. CAZyme analysis identified 116 and 115 carbohydrate-active enzymes in S3W10 and SS15, respectively, supporting adaptation to gastrointestinal environments and the host immune response. Pan-genome analysis across C. sphaeroides strains revealed 7918 gene clusters, highlighting the open pan-genome structure of this species and its high genetic diversity. Further bioinformatic analyses assessing mobile genetic elements, antibiotic-resistance genes, and virulence factors demonstrated the safety of both strains for aquaculture, as no plasmids or virulence genes were identified. The genomic insights in this study provide a deeper understanding of the strains' adaptability and functional potential, aligning with previous in vitro and in vivo studies and highlighting their potential for use in shrimp cultivation.},
}

@article {pmid39768396,
year = {2024},
author = {Adedibu, PA and Son, O and Tekutyeva, L and Balabanova, L},
title = {Pathogenomic Insights into Xanthomonas oryzae pv. oryzae's Resistome, Virulome, and Diversity for Improved Rice Blight Management.},
journal = {Life (Basel, Switzerland)},
volume = {14},
number = {12},
pages = {},
doi = {10.3390/life14121690},
pmid = {39768396},
issn = {2075-1729},
support = {15.BRK.21.0004 (Contract No. 075-15-2021-1052/9)//Ministry of Science and Higher Education of Russian Federation/ ; },
abstract = {Oryza sativa (rice) is a major staple food targeted for increased production to achieve food security. However, increased production is threatened by several biotic and abiotic factors, of which bacterial blight disease caused by Xanthomonas oryzae pathovar oryzae is severe. Developing effective control strategies requires an up-to-date understanding of its pathogenomics. This study analyzes the genomes of 30 X. oryzae strains collected from rice-producing regions across five continents to identify genetic elements critical for its pathogenicity and adaptability and for an intraspecific diversity assessment using advanced genomics and bioinformatics tools. Resistome analysis revealed 28 distinct types of antibiotic resistance genes (ARGs), both innate and acquired, indicating a growing threat from multidrug-resistant X. oryzae strains. Sixteen virulent genes, including type III and VI secretion systems, motility genes, and effector proteins, were identified. A unique 'MexCD-OprJ' multidrug efflux system was detected in the Tanzanian strains, conferring resistance to multiple antibiotic classes. To curb further ARG emergence, there is a need to regulate the use of antibiotics for X. oryzae control and adopt resistant rice varieties. Transposable elements were also discovered to contribute to X. oryzae pathogenicity, facilitating the horizontal transfer of virulence genes. Pangenome analysis revealed intraspecific variation among the population, with 112 unique CDS having diverse functional roles. Strains registered in the Philippines had the most unique genes. Phylogenetic analysis confirmed the divergent evolution of X. oryzae. This study's results will aid in identifying more effective management strategies and biocontrol alternatives for sustainable rice production.},
}

@article {pmid39766787,
year = {2024},
author = {Muto, Y and Tanaka, K},
title = {Comparative Evolutionary Genomics Reveals Genetic Diversity and Differentiation in Bacteroides fragilis.},
journal = {Genes},
volume = {15},
number = {12},
pages = {},
doi = {10.3390/genes15121519},
pmid = {39766787},
issn = {2073-4425},
support = {22K10486//Japan Society for the Promotion of Science/ ; },
mesh = {*Bacteroides fragilis/genetics/classification ; *Phylogeny ; *Genome, Bacterial ; *Evolution, Molecular ; *Genetic Variation ; *Genomics/methods ; Bacteroides Infections/microbiology/genetics ; },
abstract = {BACKGROUND/OBJECTIVES: Bacteroides fragilis is the pathogenic anaerobe most commonly isolated from intra-abdominal infections, abscesses, and blood. Despite its clinical importance, research on its pan-genome-scale evolution is still limited.

METHODS: Herein, we analyzed the pan-genome architecture of 374 B. fragilis strains to explore their intra-species genomic diversity and evolutionary patterns.

RESULTS: Our analysis revealed an open pan-genome with a high proportion of accessory genomes, indicating high genetic variability. Accessory genome genes were substantially enriched in the functions of "Replication, Recombination, and Repair" suggesting their roles in gene transfer and divergence. Phylogenomic analysis divided B. fragilis into two distinct clades: divisions I and II, differing in gene content, antimicrobial resistance genes, and mobile genetic elements. Division II revealed higher Tajima's D values, suggesting that it separated after B. fragilis's recent species diversification. The extreme shift in the distribution of gene-wise Hudson's fixation index (Fst) values for each division suggested that several genes are highly differentiated or evolved between the two clades. Average nucleotide identity and 16S rRNA analyses showed that B. fragilis division II represents a distinct species, Bacteroides hominis. Additionally, a considerable depletion of recombination in genes with Fst values > 0.99 was noted, suggesting that the highest Fst genes with little recombination are the basis for differentiation between divisions.

CONCLUSIONS: Overall, this study enhances the understanding of B. fragilis's genomic diversity, evolutionary dynamics, and potential role in pathogenesis, shedding light on its adaptation and diversification.},
}

*Bacteroides fragilis/genetics/classification
*Phylogeny
*Genome, Bacterial
*Evolution, Molecular
*Genetic Variation
*Genomics/methods
Bacteroides Infections/microbiology/genetics

@article {pmid39763808,
year = {2024},
author = {Ojeda, IG and Palace, SG and Martinez, PP and Azarian, T and Grant, LR and Hammitt, LL and Hanage, WP and Lipsitch, M},
title = {Linkage-based ortholog refinement in bacterial pangenomes with CLARC.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.12.18.629228},
pmid = {39763808},
issn = {2692-8205},
abstract = {Bacterial genomes exhibit significant variation in gene content and sequence identity. Pangenome analyses explore this diversity by classifying genes into core and accessory clusters of orthologous groups (COGs). However, strict sequence identity cutoffs can misclassify divergent alleles as different genes, inflating accessory gene counts. CLARC (Connected Linkage and Alignment Redefinition of COGs) [ https://github.com/IndraGonz/CLARC ] improves pangenome analyses by condensing accessory COGs using functional annotation and linkage information. Through this approach, orthologous groups are consolidated into more practical units of selection. Analyzing 8,000+ Streptococcus pneumoniae genomes, CLARC reduced accessory gene estimates by more than 30% and improved evolutionary predictions based on accessory gene frequencies. By refining COG definitions, CLARC offers critical insights into bacterial evolution, aiding genetic studies across diverse populations.},
}

@article {pmid39763645,
year = {2024},
author = {Zhou, Q and Ghezelji, M and Hari, A and Ford, MKB and Holley, C and Sahinalp, SC and Numanagić, I},
title = {Geny: a genotyping tool for allelic decomposition of killer cell immunoglobulin-like receptor genes.},
journal = {Frontiers in immunology},
volume = {15},
number = {},
pages = {1494995},
pmid = {39763645},
issn = {1664-3224},
mesh = {*Receptors, KIR/genetics ; Humans ; *Alleles ; *Genotyping Techniques/methods ; *Genotype ; High-Throughput Nucleotide Sequencing/methods ; Computational Biology/methods ; Software ; },
abstract = {INTRODUCTION: Accurate genotyping of Killer cell Immunoglobulin-like Receptor (KIR) genes plays a pivotal role in enhancing our understanding of innate immune responses, disease correlations, and the advancement of personalized medicine. However, due to the high variability of the KIR region and high level of sequence similarity among different KIR genes, the generic genotyping workflows are unable to accurately infer copy numbers and complete genotypes of individual KIR genes from next-generation sequencing data. Thus, specialized genotyping tools are needed to genotype this complex region.

METHODS: Here, we introduce Geny, a new computational tool for precise genotyping of KIR genes. Geny utilizes available KIR allele databases and proposes a novel combination of expectation-maximization filtering schemes and integer linear programming-based combinatorial optimization models to resolve ambiguous reads, provide accurate copy number estimation, and estimate the correct allele of each copy of genes within the KIR region.

RESULTS & DISCUSSION: We evaluated Geny on a large set of simulated short-read datasets covering the known validated KIR region assemblies and a set of Illumina short-read samples sequenced from 40 validated samples from the Human Pangenome Reference Consortium collection and showed that it outperforms the existing state-of-the-art KIR genotyping tools in terms of accuracy, precision, and recall. We envision Geny becoming a valuable resource for understanding immune system response and consequently advancing the field of patient-centric medicine.},
}

*Receptors, KIR/genetics
Humans
*Alleles
*Genotyping Techniques/methods
*Genotype
High-Throughput Nucleotide Sequencing/methods
Computational Biology/methods
Software

@article {pmid39759836,
year = {2024},
author = {Nesbø, CL and Kublanov, I and Yang, M and Sharan, AA and Meyer, T and Edwards, EA},
title = {High quality Bathyarchaeia MAGs from lignocellulose-impacted environments elucidate metabolism and evolutionary mechanisms.},
journal = {ISME communications},
volume = {4},
number = {1},
pages = {ycae156},
pmid = {39759836},
issn = {2730-6151},
abstract = {The archaeal class Bathyarchaeia is widely and abundantly distributed in anoxic habitats. Metagenomic studies have suggested that they are mixotrophic, capable of CO2 fixation and heterotrophic growth, and involved in acetogenesis and lignin degradation. We analyzed 35 Bathyarchaeia metagenome-assembled genomes (MAGs), including the first complete circularized MAG (cMAG) of the Bathy-6 subgroup, from the metagenomes of three full-scale pulp and paper mill anaerobic digesters and three laboratory methanogenic enrichment cultures maintained on pre-treated poplar. Thirty-three MAGs belong to the Bathy-6, lineage while two are from the Bathy-8 lineage. In our previous analysis of the microbial community in the pulp mill digesters, Bathyarchaeia were abundant and positively correlated to hydrogenotrophic and methylotrophic methanogenesis. Several factors likely contribute to the success of the Bathy-6 lineage compared to Bathy-8 in the reactors. The Bathy-6 genomes are larger than those of Bathy-8 and have more genes involved in lignocellulose degradation, including carbohydrate-active enzymes not present in the Bathy-8. Bathy-6 also shares the Bathyarchaeal O-demethylase system recently identified in Bathy-8. All the Bathy-6 MAGs had numerous membrane-associated pyrroloquinoline quinone-domain proteins that we suggest are involved in lignin modification or degradation, together with Radical-S-adenosylmethionine (SAM) and Rieske domain proteins, and AA2, AA3, and AA6-family oxidoreductases. We also identified a complete B12 synthesis pathway and a complete nitrogenase gene locus. Finally, comparative genomic analyses revealed that Bathyarchaeia genomes are dynamic and have interacted with other organisms in their environments through gene transfer to expand their gene repertoire.},
}

@article {pmid39758981,
year = {2024},
author = {Zakeri, M and Brown, NK and Ahmed, OY and Gagie, T and Langmead, B},
title = {Movi: A fast and cache-efficient full-text pangenome index.},
journal = {iScience},
volume = {27},
number = {12},
pages = {111464},
pmid = {39758981},
issn = {2589-0042},
abstract = {Pangenome indexes are promising tools for many applications, including classification of nanopore sequencing reads. Move structure is a compressed-index data structure based on the Burrows-Wheeler Transform (BWT). It offers simultaneous O(1)-time queries and O(r) space, where r is the number of BWT runs (consecutive sequence of identical characters). We developed Movi based on the move structure for indexing and querying pangenomes. Movi scales very well for repetitive text as its size grows strictly by r. Movi computes sophisticated matching queries for classification such as pseudo-matching lengths and backward search up to 30 times faster than existing methods by minimizing the number of cache misses and using memory prefetching to attain a degree of latency hiding. Movi's fast constant-time query loop makes it well suited to real-time applications like adaptive sampling for nanopore sequencing, where decisions must be made in a small and predictable time interval.},
}

@article {pmid39756800,
year = {2025},
author = {Jonkheer, EM and de Ridder, D and van der Lee, TAJ and de Haan, JR and Berke, L and Smit, S},
title = {Exploring intra- and intergenomic variation in haplotype-resolved pangenomes.},
journal = {Plant biotechnology journal},
volume = {},
number = {},
pages = {},
doi = {10.1111/pbi.14545},
pmid = {39756800},
issn = {1467-7652},
support = {ETEC.2019.019//Netherlands eScience Center/ ; //Genetwister Technologies B.V./ ; //Biointeractions and Plant Health, Wageningen Plant Research/ ; },
abstract = {With advances in long-read sequencing and assembly techniques, haplotype-resolved (phased) genome assemblies are becoming more common, also in the field of plant genomics. Computational tools to effectively explore these phased genomes, particularly for polyploid genomes, are currently limited. Here we describe a new strategy adopting a pangenome approach. To analyse both intra- and intergenomic variation in phased genome assemblies, we have made the software package PanTools ploidy-aware by updating the pangenome graph representation and adding several novel functionalities to assess synteny and gene retention, profile repeats and calculate synonymous and nonsynonymous mutation rates. Using PanTools, we constructed and analysed a pangenome comprising of one diploid and four tetraploid potato cultivars, and a pangenome of five diploid apple species. Both pangenomes show high intra- and intergenomic allelic diversity in terms of gene absence/presence, SNPs, indels and larger structural variants. Our findings show that the new functionalities and visualizations are useful to discover introgressions and detect likely misassemblies in phased genomes. PanTools is available at https://git.wur.nl/bioinformatics/pantools.},
}

@article {pmid39755794,
year = {2025},
author = {Sawaswong, V and Wongjarit, K and Petsong, S and Yuliani, Y and Somsukpiroh, U and Faksri, K and Forde, T and Payungporn, S and Rotcheewaphan, S},
title = {Diversity and antimicrobial resistance profiles of Mycobacterium avium complex clinical isolates in Thailand based on whole genome comparative analysis.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {772},
pmid = {39755794},
issn = {2045-2322},
support = {HEA663000042//Thailand Science research and Innovation Fund Chulalongkorn University/ ; RA66/026//Ratchadapiseksompotch Fund, Faculty of Medicine, Chulalongkorn University/ ; },
mesh = {Thailand/epidemiology ; *Mycobacterium avium Complex/genetics/drug effects/isolation & purification ; Humans ; *Phylogeny ; *Microbial Sensitivity Tests ; *Drug Resistance, Bacterial/genetics ; *Mycobacterium avium-intracellulare Infection/microbiology/drug therapy ; *Genome, Bacterial ; Anti-Bacterial Agents/pharmacology ; Whole Genome Sequencing/methods ; Genetic Variation ; Male ; Female ; Middle Aged ; Aged ; Adult ; },
abstract = {The Mycobacterium avium complex (MAC) is a group of closely related nontuberculous mycobacteria that can cause various diseases in humans. In this study, genome sequencing, comprehensive genomic analysis, and antimicrobial susceptibility testing of 66 MAC clinical isolates from King Chulalongkorn Memorial Hospital, Bangkok, Thailand were carried out. Whole-genome average nucleotide identity (ANI) revealed the MAC species distribution, comprising 54 (81.8%) M. intracellulare, 6 (9.1%) M. avium, 5 (7.6%) M. colombiense, and 1 (1.5%) M. timonense. Phylogenetic analysis revealed a high diversity of M. intracellulare isolates and their evolutionary relationships which could be divided into 2 subspecies: M. intracellulare subsp. intracellulare and M. intracellulare subsp. chimaera. In addition, M. intracellulare subsp. chimaera mostly clustered in the distinct clades separated from M. intracellulare strains originating from other countries. Most MAC isolates were resistant to linezolid and moxifloxacin based on phenotypic antimicrobial susceptibility testing. Mutations within rrl gene associated with clarithromycin resistance were detected in M. intracellulare and M. colombiense. The pan-genome analysis presented clade-specific proteins for M. intracellulare, such as PE and PPE protein families. This study provides valuable insights into the genomic diversity and antimicrobial resistance profiles of MAC isolates circulating in Thailand, which are useful for clinical management, guiding the development of targeted diagnostic, and treatment strategies for MAC infections.},
}

Thailand/epidemiology
*Mycobacterium avium Complex/genetics/drug effects/isolation & purification
Humans
*Phylogeny
*Microbial Sensitivity Tests
*Drug Resistance, Bacterial/genetics
*Mycobacterium avium-intracellulare Infection/microbiology/drug therapy
*Genome, Bacterial
Anti-Bacterial Agents/pharmacology
Whole Genome Sequencing/methods
Genetic Variation
Male
Female
Middle Aged
Aged
Adult

@article {pmid39754036,
year = {2025},
author = {Pan, M and O'Flaherty, S and Hibberd, A and Gerdes, S and Morovic, W and Barrangou, R},
title = {The curated Lactobacillus acidophilus NCFM genome provides insights into strain specificity and microevolution.},
journal = {BMC genomics},
volume = {26},
number = {1},
pages = {1},
pmid = {39754036},
issn = {1471-2164},
abstract = {BACKGROUND: The advent of next generation sequencing technologies has enabled a surge in the number of whole genome sequences in public databases, and our understanding of the composition and evolution of bacterial genomes. Besides model organisms and pathogens, some attention has been dedicated to industrial bacteria, notably members of the Lactobacillaceae family that are commonly studied and formulated as probiotic bacteria. Of particular interest is Lactobacillus acidophilus NCFM, an extensively studied strain that has been widely commercialized for decades and is being used for the delivery of vaccines and therapeutics.

RESULTS: Here, we revisit the L. acidophilus genome, which was sequenced twenty years ago, and determined the core and pan genomes of 114 publicly available L. acidophilus strains, spanning commercial isolates, academic strains and clones from the scientific literature. Results indicate a predictable high level of homogeneity within the species, but also reveal surprising mis-assemblies. Furthermore, by investigating twenty one available L. acidophilus NCFM-derived variants, we document overall genomic stability, with no observed genomic re-arrangement or inversions.

CONCLUSION: This study provides a comparative analysis of the currently available genomes for L. acidophilus and examines microevolution patterns for several strains derived from L. acidophilus NCFM, which revealed no to very few SNPs with strains sequenced at different points in time using different sequencing technologies and platforms. This re-affirms its suitability for industrial deployment as a probiotic and its use as an engineering chassis and delivery modality for novel biotherapeutics.},
}

@article {pmid39752324,
year = {2025},
author = {van Dijk, LR and Manson, AL and Earl, AM and Garimella, KV and Abeel, T},
title = {Fast exact gap-affine partial order alignment with POASTA.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btae757},
pmid = {39752324},
issn = {1367-4811},
abstract = {MOTIVATION: Partial order alignment is a widely used method for computing multiple sequence alignments, with applications in genome assembly and pangenomics, among many others. Current algorithms to compute the optimal, gap-affine partial order alignment do not scale well to larger graphs and sequences. While heuristic approaches exist, they do not guarantee optimal alignment and sacrifice alignment accuracy.

RESULTS: We present POASTA, a new optimal algorithm for partial order alignment that exploits long stretches of matching sequence between the graph and a query. We benchmarked POASTA against the state-of-the-art on several diverse bacterial gene datasets and demonstrated an average speed-up of 4.1x and up to 9.8x, using less memory. POASTA's memory scaling characteristics enabled the construction of much larger POA graphs than previously possible, as demonstrated by megabase-length alignments of 342 Mycobacterium tuberculosis sequences.

POASTA is available on Github at https://github.com/broadinstitute/poasta.},
}

@article {pmid39749377,
year = {2024},
author = {Oh, JY and Do, KH and Jeong, JH and Kwak, S and Choe, S and An, D and Chae, JC and Lee, K and Seo, KW},
title = {Whole genome sequencing analysis of enteropathogenic Escherichia coli from human and companion animals in Korea.},
journal = {Journal of veterinary science},
volume = {},
number = {},
pages = {},
doi = {10.4142/jvs.24225},
pmid = {39749377},
issn = {1976-555X},
support = {2022-ER2103-01/KDCA/Korea Disease Control and Prevention Agency/Korea ; 2024-ER2103-00/KDCA/Korea Disease Control and Prevention Agency/Korea ; 23194MFDS012/MFDS/Ministry of Food and Drug Safety/Korea ; },
abstract = {IMPORTANCE: This study is essential for comprehending the zoonotic transmission, antimicrobial resistance, and genetic diversity of enteropathogenic Escherichia coli (EPEC).

OBJECTIVE: To improve our understanding of EPEC, this study focused on analyzing and comparing the genomic characteristics of EPEC isolates from humans and companion animals in Korea.

METHODS: The whole genome of 26 EPEC isolates from patients with diarrhea and 20 EPEC isolates from companion animals in Korea were sequenced using the Illumina HiSeq X (Illumina, USA) and Oxford Nanopore MinION (Oxford Nanopore Technologies, UK) platforms.

RESULTS: Most isolates were atypical EPEC, and did not harbor the bfpA gene. The most prevalent virulence genes were found to be ompT (humans: 61.5%; companion animals: 60.0%) followed by lpfA (humans: 46.2%; companion animals: 60.0%). Although pan-genome analyses showed no apparent correlation among the origin of the strains, virulence profiles, and antimicrobial resistance profiles, isolates included in clade A obtained from both humans and companion animals exhibited high similarity. Additionally, all the isolates included in clade A encoded the ompT gene and did not encode the hlyE gene. The two isolates from companion animals harbored an incomplete bundle-forming pilus region encoding bfpA and bfpB. Moreover, the type IV secretion system-associated genes tra and trb were found in the bfpA-encoding isolates from humans.

CONCLUSIONS AND RELEVANCE: Whole-genome sequencing enabled a more accurate analysis of the phylogenetic structure of EPEC and provided better insights into the understanding of EPEC epidemiology and pathogenicity.},
}

@article {pmid39748179,
year = {2025},
author = {Michael, TP},
title = {Can a plant biologist fix a thermostat?.},
journal = {The New phytologist},
volume = {},
number = {},
pages = {},
doi = {10.1111/nph.20382},
pmid = {39748179},
issn = {1469-8137},
support = {INV-040541/GATES/Bill & Melinda Gates Foundation/United States ; },
abstract = {The shift to reductionist biology at the dawn of the genome era yielded a 'parts list' of plant genes and a nascent understanding of complex biological processes. Today, with the genomics era in full swing, advances in high-definition genomics enabled precise temporal and spatial analyses of biological systems down to the single-cell level. These insights, coupled with artificial intelligence-driven in silico design, are propelling the development of the first synthetic plants. By integrating reductionist and systems approaches, researchers are not only reimagining plants as sources of food, fiber, and fuel but also as 'environmental thermostats' capable of mitigating the impacts of a changing climate.},
}

@article {pmid39748007,
year = {2025},
author = {Islam, MR and Mondol, SM and Hossen, MA and Khatun, MP and Selim, S and Amiruzzaman, and Gomes, DJ and Rahaman, MM},
title = {First report on comprehensive genomic analysis of a multidrug-resistant Enterobacter asburiae isolated from diabetic foot infection from Bangladesh.},
journal = {Scientific reports},
volume = {15},
number = {1},
pages = {424},
pmid = {39748007},
issn = {2045-2322},
mesh = {*Diabetic Foot/microbiology ; *Enterobacter/genetics/isolation & purification/drug effects/pathogenicity ; Humans ; Bangladesh ; *Drug Resistance, Multiple, Bacterial/genetics ; *Anti-Bacterial Agents/pharmacology ; Genome, Bacterial ; Genomics/methods ; Whole Genome Sequencing ; Microbial Sensitivity Tests ; Virulence Factors/genetics ; Phylogeny ; Enterobacteriaceae Infections/microbiology ; Biofilms/drug effects ; },
abstract = {Enterobacter asburiae (E. asburiae) is a gram-negative rod-shaped bacterium which has emerging significance as an opportunistic pathogen having high virulence pattern and drug resistant properties. In this study, we present the detailed analysis of the whole genome sequence of a multidrug-resistant (MDR) E. asburiae strain BDW1M3 from Bangladesh. The isolate was collected from an infected foot wound of a diabetic foot ulcer patient. Through sophisticated genomic techniques encompassing whole genome sequencing and in-depth bioinformatic analyses, this research unveils a profound understanding of the isolate's antimicrobial resistance patterns, virulence determinants, biosynthetic gene clusters, metabolic pathways and pathogenic potential. The isolate displayed resistance to Ampicillin, Fosfomycin, Cefoxitin, Tigecycline, Meropenem, Linezolid, Vancomycin antibiotics and demonstrated the capacity for biofilm formation. Several antimicrobial resistance genes such as blaACT-2,fosA2, baeR, qnrE2, vanA and numbers of virulence genes including ybaJ, csrA, barA, uvrY, pgaD, hlyD, hlyC, terC, purD were detected. Metal resistance genes investigation revealed the presence of cusCFBA operon system, and many other genes including zntA, zitB, czrB. Prophage region of Myoviridae was detected. Comparative genomics with 47 whole genome sequence (n = 47) shed light on the genetic diversity of E. asburiae strains from diverse sources and countries, with a notable observation that strains from both human and non-human origins exhibited significant pathogenicity potential, genomic and phylogenomic relations hinting at potential cross-species transmission. Pangenome analysis indicated toward an expanding pangenome of E. asburiae. Further research and in-depth comprehensive studies are required to investigate the prevalence of E. asburiae in Bangladesh and emphasize towards unraveling the bacterium's inherent pathogenic potential and the intricate molecular mechanisms that underlie its resistance traits and virulence properties.},
}

*Diabetic Foot/microbiology
*Enterobacter/genetics/isolation & purification/drug effects/pathogenicity
Humans
Bangladesh
*Drug Resistance, Multiple, Bacterial/genetics
*Anti-Bacterial Agents/pharmacology
Genome, Bacterial
Genomics/methods
Whole Genome Sequencing
Microbial Sensitivity Tests
Virulence Factors/genetics
Phylogeny
Enterobacteriaceae Infections/microbiology
Biofilms/drug effects

@article {pmid39746989,
year = {2025},
author = {Hu, H and Zhao, J and Thomas, WJW and Batley, J and Edwards, D},
title = {The role of pangenomics in orphan crop improvement.},
journal = {Nature communications},
volume = {16},
number = {1},
pages = {118},
pmid = {39746989},
issn = {2041-1723},
support = {LP230100351//Department of Education and Training | Australian Research Council (ARC)/ ; DP210100296//Department of Education and Training | Australian Research Council (ARC)/ ; DP200100762//Department of Education and Training | Australian Research Council (ARC)/ ; },
mesh = {*Crops, Agricultural/genetics ; *Genomics/methods ; *Genome, Plant ; *Plant Breeding/methods ; Gene Editing/methods ; Genetic Variation ; Food Security ; },
abstract = {Global food security depends heavily on a few staple crops, while orphan crops, despite being less studied, offer the potential benefits of environmental adaptation and enhanced nutritional traits, especially in a changing climate. Major crops have benefited from genomics-based breeding, initially using single genomes and later pangenomes. Recent advances in DNA sequencing have enabled pangenome construction for several orphan crops, offering a more comprehensive understanding of genetic diversity. Orphan crop research has now entered the pangenomics era and applying these pangenomes with advanced selection methods and genome editing technologies can transform these neglected species into crops of broader agricultural significance.},
}

*Crops, Agricultural/genetics
*Genomics/methods
*Genome, Plant
*Plant Breeding/methods
Gene Editing/methods
Genetic Variation
Food Security

@article {pmid39745367,
year = {2024},
author = {Chauhan, SM and Ardalani, O and Hyun, JC and Monk, JM and Phaneuf, PV and Palsson, BO},
title = {Decomposition of the pangenome matrix reveals a structure in gene distribution in the Escherichia coli species.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0053224},
doi = {10.1128/msphere.00532-24},
pmid = {39745367},
issn = {2379-5042},
abstract = {UNLABELLED: Thousands of complete genome sequences for strains of a species that are now available enable the advancement of pangenome analytics to a new level of sophistication. We collected 2,377 publicly available complete genomes of Escherichia coli for detailed pangenome analysis. The core genome and accessory genomes consisted of 2,398 and 5,182 genes, respectively. We developed a machine learning approach to define the accessory genes characterizing the major phylogroups of E. coli plus Shigella: A, B1, B2, C, D, E, F, G, and Shigella. The analysis resulted in a detailed structure of the genetic basis of the phylogroups' differential traits. This pangenome structure was largely consistent with a housekeeping-gene-based MLST distribution, sequence-based Mash distance, and the Clermont quadruplex classification. The rare genome (consisting of genes found in <6.8% of all strains) consisted of 163,619 genes, about 79% of which represented variations of 315 underlying transposon elements. This analysis generated a mathematical definition of the genetic basis for a species.

IMPORTANCE: The comprehensive analysis of the pangenome of Escherichia coli presented in this study marks a significant advancement in understanding bacterial genetic diversity. By employing machine learning techniques to analyze 2,377 complete E. coli genomes, the study provides a detailed mapping of core, accessory, and rare genes. This approach reveals the genetic basis for differential traits across phylogroups, offering insights into pathogenicity, antibiotic resistance, and evolutionary adaptations. The findings enhance the potential for genome-based diagnostics and pave the way for future studies aimed at achieving a global genetic definition of bacterial phylogeny.},
}

@article {pmid39745363,
year = {2024},
author = {Akusobi, C and Choudhery, S and Benghomari, BS and Wolf, ID and Singhvi, S and Ioerger, TR and Rubin, EJ},
title = {Transposon-sequencing across multiple Mycobacterium abscessus isolates reveals significant functional genomic diversity among strains.},
journal = {mBio},
volume = {},
number = {},
pages = {e0337624},
doi = {10.1128/mbio.03376-24},
pmid = {39745363},
issn = {2150-7511},
abstract = {UNLABELLED: Mycobacterium abscessus (Mab) is a clinically significant pathogen and a highly genetically diverse species due to its large accessory genome. The functional consequence of this diversity remains unknown mainly because, to date, functional genomic studies in Mab have been primarily performed on reference strains. Given the growing public health threat of Mab infections, understanding the functional genomic differences among Mab clinical isolates can provide more insight into how its genetic diversity influences gene essentiality, clinically relevant phenotypes, and importantly, potential drug targets. To determine the functional genomic diversity among Mab strains, we conducted transposon-sequencing (TnSeq) on 21 genetically diverse clinical isolates, including 15 M. abscessus subsp. abscessus isolates and 6 M. abscessus subsp. massiliense isolates, cataloging all the essential and non-essential genes in each strain. Pan-genome analysis revealed a core set of 3,845 genes and a large accessory genome of 11,507. We identified 259 core essential genes across the 21 clinical isolates and 425 differentially required genes, representing ~10% of the Mab core genome. We also identified genes whose requirements were subspecies, lineage, and isolate-specific. Finally, by correlating TnSeq profiles, we identified 19 previously uncharacterized genetic networks in Mab. Altogether, we find that Mab clinical isolates are not only genetically diverse but functionally diverse as well.

IMPORTANCE: This study investigates the genetic diversity of Mycobacterium abscessus (Mab), a bacteria known for causing difficult-to-treat infections. Researchers performed transposon-sequencing (TnSeq) on 21 different clinical isolates of Mab to identify essential and non-essential genes in each strain. Through this analysis, they identified core genes required for growth across all strains. Interestingly, they also identified genes whose requirement for growth or "essentiality" were subspecies, lineage, and isolate-specific. This study reveals that Mab's genetic diversity translates into significant functional differences among clinical isolates. Insights from this paper lay essential groundwork for future studies exploring the biological and clinical implications of genetic diversity in Mab clinical isolates. Understanding this diversity could guide targeted therapies and offer new insights into managing infections caused by Mab, a growing public health concern.},
}

@article {pmid39742300,
year = {2024},
author = {Li, D and Wang, Y and Yuan, T and Cao, M and He, Y and Zhang, L and Li, X and Jiang, Y and Li, K and Sun, J and Lv, G and Su, G and Wang, Q and Pan, Y and Li, X and Jiang, Y and Yang, G and Groenen, MAM and Derks, MFL and Ding, R and Ding, X and Yu, T},
title = {Pangenome and genome variation analyses of pigs unveil genomic facets for their adaptation and agronomic characteristics.},
journal = {iMeta},
volume = {3},
number = {6},
pages = {e257},
pmid = {39742300},
issn = {2770-596X},
abstract = {The development of a comprehensive pig graph pangenome assembly encompassing 27 genomes represents the most extensive collection of pig genomic data to date. Analysis of this pangenome reveals the critical role of structural variations in driving adaptation and defining breed-specific traits. Notably, the study identifies BTF3 as a key candidate gene governing intramuscular fat deposition and meat quality in pigs. These findings underscore the power of pangenome approaches in uncovering novel genomic features underlying economically important agricultural traits. Collectively, these results demonstrate the value of leveraging large-scale, multi-genome analyses for advancing our understanding of livestock genomes and accelerating genetic improvement.},
}

@article {pmid39741590,
year = {2024},
author = {Banerjee, R and Chaudhari, NM and Lahiri, A and Gautam, A and Bhowmik, D and Dutta, C and Chattopadhyay, S and Huson, DH and Paul, S},
title = {Corrigendum: Interplay of various evolutionary modes in genome diversification and adaptive evolution of the family Sulfolobaceae.},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1538738},
doi = {10.3389/fmicb.2024.1538738},
pmid = {39741590},
issn = {1664-302X},
abstract = {[This corrects the article DOI: 10.3389/fmicb.2021.639995.].},
}

@article {pmid39738919,
year = {2024},
author = {Han, JE and Kang, S and Lee, SY and Bae, JW},
title = {Characterisation of Aequorivita ciconiae sp. nov., isolated from oriental stork, Ciconia boyciana.},
journal = {Antonie van Leeuwenhoek},
volume = {118},
number = {2},
pages = {47},
pmid = {39738919},
issn = {1572-9699},
support = {RS-2023-00227274//National Research Foundation of Korea/ ; NRF-2020R1A2C3012797//Mid-Career Researcher Programme/ ; 22213MFDS537//Ministry of Food and Drug Safety/ ; },
mesh = {*Phylogeny ; *RNA, Ribosomal, 16S/genetics ; *Flavobacteriaceae/genetics/classification/isolation & purification ; Animals ; *DNA, Bacterial/genetics ; *Base Composition ; *Fatty Acids/chemistry/analysis ; Republic of Korea ; *Bacterial Typing Techniques ; Birds/microbiology ; Feces/microbiology ; Sequence Analysis, DNA ; Phospholipids/analysis ; },
abstract = {A single novel bacterial strain designated as H23M31[T] was isolated from the faecal sample of oriental stork (Ciconia boyciana) that inhabits the Republic of Korea. It was a rod-shaped, facultative anaerobic, Gram-negative, and non-motile strain. Phylogenetic analysis based on the 16S rRNA gene sequence revealed that it branched from Aequorivita within Flavobacteriaceae. It was most closely related to A. capsosiphonis DSM 23843[ T], which shared the sequence similarity of 96.36%. The strain exhibited optimal growth at pH 7.0 in a marine broth medium with 1% NaCl incubated at 30 °C. Chemotaxonomic characteristics indicated that the predominant cellular fatty acids were iso-C15:0 (24.4%), iso-C17:0 3-OH (15.9%), and anteiso-C15:0 (13.9%). The polar lipid of the strain contained phosphatidylcholine (PC), phosphatidylglycerol (PG), and diphosphatidylglycerol (DPG). The major isoprenoid quinone was menaquinone 6 (MK-6), which was identical with that of a closely related Aequorivita species. The genomic G + C contents of the strain was 38.25 mol%. Average nucleotide identity (ANI), average amino acid identity (AAI), and digital DNA-DNA hybridization (dDDH) values between the novel isolate and A. viscosa CGMCC 1.11023[ T] were 75.83%, 80.34% and 20.50%, respectively. Phylogenetic analyses revealed the evolutionary relationships of the strain, demonstrating that the strain clusters with other Aequorivita species. Pan-genome analyses and genome comparisons indicated that, unlike other environmentally isolated species, it possesses unique genes that enhance its ability to colonise the harsh animal gut environment. Taxonomic characterisation suggested that strain H23M31[T] represents a novel Aequorivita species, and the proposed name is Aequorivita ciconiae sp. nov. The type strain of A. ciconiae is H23M31[T] (= KCTC 62809[ T] = JCM 33229[ T]).},
}

*Phylogeny
*RNA, Ribosomal, 16S/genetics
*Flavobacteriaceae/genetics/classification/isolation & purification
Animals
*DNA, Bacterial/genetics
*Base Composition
*Fatty Acids/chemistry/analysis
Republic of Korea
*Bacterial Typing Techniques
Birds/microbiology
Feces/microbiology
Sequence Analysis, DNA
Phospholipids/analysis

@article {pmid39736996,
year = {2024},
author = {Lu, W and Zha, B and Lyu, J and LingHu, C and Chen, J and Deng, S and Zhang, X and Li, L and Wang, G},
title = {Whole-genome sequencing and genomic analysis of four Akkermansia strains newly isolated from human feces.},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1500886},
pmid = {39736996},
issn = {1664-302X},
abstract = {BACKGROUND: Numerous studies have demonstrated that Akkermansia is closely associated with human health. These bacteria colonize the mucus layer of the gastrointestinal tract and utilize mucin as their sole source of carbon and nitrogen. Akkermansia spp. exhibit potential as probiotics under specific conditions. However, the gene accumulation curve derived from pan-genome analysis suggests that the genome of Akkermansia strains remains open. Consequently, current genome mining efforts are insufficient to fully capture the intraspecific and interspecific characteristics of Akkermansia, necessitating continuous exploration of the genomic and phenotypic diversity of new isolates.

METHODS: Based on this finding, we sequenced, assembled, and functionally annotated the whole genomes of four new human isolates from our laboratory: AKK-HX001, AKK-HX002, AKK-HX003, and AKK-HX004.

RESULTS: Phylogenetic analysis revealed that all four isolates belonged to the AmII phylogroup, whereas the type strain DSM 22959 is classified within the AmI phylogroup. Moreover, 2,184 shared homologous genes were identified among the four isolates. Functional annotation using the COG, KEGG, and CAZy databases indicated that the functional genes of the four isolates were primarily associated with metabolism. Two antibiotic resistance genes were identified in AKK-HX001 and AKK-HX002, while three resistance genes were detected in AKK-HX003 and AKK-HX004. Additionally, each of the four isolates possessed two virulence genes and three pathogenicity genes, none of which were associated with pathogenicity. The prediction of mobile genetic elements indicated unequal distributions of GIs among the isolates, and a complete CRISPR system was identified in all isolates except AKK-HX003. Two annotated regions of secondary metabolite biosynthesis genes, both belonging to Terpene, were detected using the antiSMASH online tool.

CONCLUSION: These findings indicate that the four Akkermansia isolates, which belong to a phylogroup distinct from the model strain DSM 22959, exhibit lower genetic risk and may serve as potential probiotic resources for future research.},
}

@article {pmid39736538,
year = {2024},
author = {Radjasa, OK and Steven, R and Natanael, Y and Nugrahapraja, H and Radjasa, SK and Kristianti, T and Moeis, MR and Trinugroho, JP and Suharya, HB and Rachmatsyah, AO and Dwijayanti, A and Putri, MR and de Fretes, CE and Siallagan, ZL and Fadli, M and Opier, RDA and Farahyah, JD and Rahmawati, V and Rizanti, M and Humaira, Z and Prihatmanto, AS and Hananto, ND and Susanto, RD and Chahyadi, A and Elfahmi, and Priharto, N and Kamarisima, and Dwivany, FM},
title = {From the depths of the Java Trench: genomic analysis of Priestia flexa JT4 reveals bioprospecting and lycopene production potential.},
journal = {BMC genomics},
volume = {25},
number = {1},
pages = {1259},
pmid = {39736538},
issn = {1471-2164},
mesh = {*Lycopene/metabolism ; Indonesia ; *Genome, Bacterial ; Bioprospecting ; Genomics/methods ; Phylogeny ; Multigene Family ; Peptide Synthases/genetics/metabolism ; Whole Genome Sequencing ; Carotenoids/metabolism ; Actinobacteria/genetics/metabolism ; },
abstract = {BACKGROUND: The marine environment boasts distinctive physical, chemical, and biological characteristics. While numerous studies have delved into the microbial ecology and biological potential of the marine environment, exploration of genetically encoded, deep-sea sourced secondary metabolites remains scarce. This study endeavors to investigate marine bioproducts derived from deep-sea water samples at a depth of 1,000 m in the Java Trench, Indonesia, utilizing both culture-dependent and whole-genome sequencing methods.

RESULTS: Our efforts led to the successful isolation and cultivation of a bacterium Priestia flexa JT4 from the water samples, followed by comprehensive genome sequencing. The resultant high-quality draft genome, approximately 4 Mb, harbored 5185 coding sequences (CDSs). Notably, 61.97% of these CDSs were inadequately characterized, presenting potential novel CDSs. This study is the first to identify the "open-type" (α < 1) pangenome within the genus Priestia. Moreover, our analysis uncovered eight biosynthetic gene clusters (BGCs) using the common genome mining pipeline, antiSMASH. Two non-ribosomal peptide synthetase (NRPS) BGCs within these clusters exhibited the potential to generate novel biological compounds. Noteworthy is the confirmation that the terpene BGC in P. flexa JT4 can produce lycopene, a compound in substantial industrial demand. The presence of lycopene in the P. flexa JT4 cells was verified using Ultra-performance liquid chromatography-mass spectrometry (UPLC-MS/MS) in multiple reaction modes.

CONCLUSIONS: This study highlights the bioprospecting opportunity to explore novel bioproducts and lycopene compounds from P. flexa JT4. It marks the pioneering exploration of deep-sea bacterium bioprospecting in Indonesia, seeking to unveil novel bioproducts and lycopene compounds through a genome mining approach.},
}

*Lycopene/metabolism
Indonesia
*Genome, Bacterial
Bioprospecting
Genomics/methods
Phylogeny
Multigene Family
Peptide Synthases/genetics/metabolism
Whole Genome Sequencing
Carotenoids/metabolism
Actinobacteria/genetics/metabolism

@article {pmid39725890,
year = {2024},
author = {Javier-López, R and Geliashvili, N and Birkeland, NK},
title = {Comparative genomics of Fervidobacterium: a new phylogenomic landscape of these wide-spread thermophilic anaerobes.},
journal = {BMC genomics},
volume = {25},
number = {1},
pages = {1248},
pmid = {39725890},
issn = {1471-2164},
support = {328955//Norges Forskningsråd/ ; 328955//Norges Forskningsråd/ ; 862555//ERA-NET Cofund on Food Systems and Climate (FOSC)/ ; 862555//ERA-NET Cofund on Food Systems and Climate (FOSC)/ ; 862555//ERA-NET Cofund on Food Systems and Climate (FOSC)/ ; CPEA-LT-2017/10061//Norwegian Directorate for Higher Education and Skills/ ; CPEA-LT-2017/10061//Norwegian Directorate for Higher Education and Skills/ ; },
mesh = {*Phylogeny ; *Genome, Bacterial ; *Genomics ; RNA, Ribosomal, 16S/genetics ; Base Composition ; },
abstract = {BACKGROUND: Fervidobacterium is a genus of thermophilic anaerobic Gram-negative rod-shaped bacteria belonging to the phylum Thermotogota. They can grow through fermentation on a wide range of sugars and protein-rich substrates. Some can also break down feather keratin, which has significant biotechnological potential. Fervidobacteria genomes have undergone several horizontal gene transfer events, sharing DNA with unrelated microbial taxa. Despite increasing biotechnological and evolutionary interest in this genus, only seven species have been described to date. Here, we present and describe six new and complete Fervidobacterium genomes, including the type strains Fervidobacterium gondwanense CBS-1[ T], F. islandicum H-21[ T] and F. thailandense FC2004[T], one novel isolate from Georgia (strain GSH) and two strains (DSM 21710 and DSM 13770) that have not been previously described along with an evolutionary and phylogenomic analysis of the genus.

RESULTS: The complete genomes were around 2 Mb with approximately 2,000 CDS identified and annotated in each of them and a G + C content ranging from 38.9 mol% to 45.8 mol%. Phylogenomic comparisons of all currently available Fervidobacterium genomes, including OrthoANI and TYGS analyses, as well as a phylogenetic analysis based on the 16S rRNA gene, identified six species and nine subspecies clusters across the genus, with a consistent topology and a distant and separately branching species, Fervidobacterium thailandense. F. thailandense harbored the highest number of transposases, CRISPR clusters, pseudo genes and horizontally transferred regions The pan genome of the genus showed that 44% of the genes belong to the cloud pangenome, with most of the singletons found also in F. thailandense.

CONCLUSIONS: The additional genome sequences described in this work and the comparison with all available Fervidobacterium genome sequences provided new insights into the evolutionary history of this genus and supported a phylogenetic reclassification. The phylogenomic results from OrthoANI and TYGS analyses revealed that F. riparium and F. gondwanense belong to the same genome species, and includes Fervidobacterium sp. 13770, while "F. pennivorans" strain DYC belongs to a separate genome species, whereas Fervidobacterium sp. 21710 and Fervidobacterium sp. GSH within the Fervidobacterium pennivorans clade represent two subspecies. F. changbaicum is reclassified as F. islandicum.},
}

*Phylogeny
*Genome, Bacterial
*Genomics
RNA, Ribosomal, 16S/genetics
Base Composition

@article {pmid39724170,
year = {2024},
author = {Farrell, AA and Nesbø, CL and Zhaxybayeva, O},
title = {Bacterial growth temperature as a horizontally acquired polygenic trait.},
journal = {Genome biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/gbe/evae277},
pmid = {39724170},
issn = {1759-6653},
abstract = {Evolutionary events leading to organismal preference for a specific growth temperature, as well as genes whose products are needed for a proper function at that temperature, are poorly understood. Using 64 bacteria from phylum Thermotogota as a model system, we examined how optimal growth temperature changed throughout Thermotogota history. We inferred that Thermotogota's last common ancestor was a thermophile and that some Thermotogota evolved the mesophilic and hyperthermophilic lifestyles secondarily. By modeling gain and loss of genes throughout Thermotogota history and by reconstructing their phylogenies, we demonstrated that adaptations to lower and higher growth temperature involve both the acquisition of necessary genes and loss of unnecessary genes. Via a pangenome-wide association study, we correlated presence/absence of 68 genes with specific optimal growth temperature intervals. While some of these genes are poorly characterized, most are involved in metabolism of amino acids, nucleotides, carbohydrates, and lipids, as well as in signal transduction and regulation of transcription. Most of the 68 genes have a history of horizontal gene transfer with other bacteria and archaea that often grow at similar temperatures, suggesting that parallel acquisitions of genes likely promote independent adaptations of different Thermotogota species to specific growth temperatures.},
}

@article {pmid39722670,
year = {2024},
author = {Yakubov, LA and Taranov, OS and Sidorov, SV and Nikonov, SD and Ostanin, AA and Chernykh, ER and Kolchanov, NA and Bogachev, SS},
title = {The concept of natural genome reconstruction.Part 1. Basic provisions of the "natural genome reconstruction" concept. Changing the genome of hematopoietic stem cells using several natural cellular mechanisms that are inherent in the hematopoietic cell and determine its biological status as "the source of the body's reparative potential".},
journal = {Vavilovskii zhurnal genetiki i selektsii},
volume = {28},
number = {7},
pages = {696-705},
doi = {10.18699/vjgb-24-78},
pmid = {39722670},
issn = {2500-0462},
abstract = {We present a series of articles proving the existence of a previously unknown mechanism of interaction between hematopoietic stem cells and extracellular double-stranded DNA (and, in particular, double-stranded DNA of the peripheral bloodstream), which explains the possibility of emergence and fixation of genetic information contained in double-stranded DNA of extracellular origin in hematopoietic stem cells. The concept of the possibility of stochastic or targeted changes in the genome of hematopoietic stem cells is formulated based on the discovery of new, previously unknown biological properties of poorly differentiated hematopoietic precursors. The main provisions of the concept are as follows. The hematopoietic stem cell takes up and internalizes fragments of extracellular double-stranded DNA via a natural mechanism. Specific groups of glycocalyx factors, including glycoproteins/proteoglycans, glycosylphosphatidylinositol-anchored proteins and scavenger receptors, take part in the internalization event. The binding sites for DNA fragments are heparin-binding domains and clusters of positively charged amino acid residues that are parts of protein molecules of these factors. Extracellular fragments delivered to the internal compartments of hematopoietic stem cells initiate terminal differentiation, colony formation, and proliferation of hematopoietic precursors. The molecular manifestation of these processes is the emergence and repair of pangenomic single-strand breaks. The occurrence of pangenomic single-strand breaks and restoration of genome (genomic DNA) integrity are associated with activation of a "recombinogenic situation" in the cell; during its active phase, stochastic homologous recombination or other recombination events between extracellular fragments localized in the nucleus and chromosomal DNA are possible. As a result, genetic material of initially extracellular localization either integrates into the recipient genome with the replacement of homologous chromosomal segments, or is transitively present in the nucleus and can manifest itself as a new genetic trait. It is assumed that as a result of stochastic acts of homologous exchange, chromosome loci are corrected in hematopoietic stem cells that have acquired mutations during the existence of the organism, which are the cause of clonal hematopoiesis associated with old age. In this regard, there is a fundamental possibility of changing the hematopoietic status of hematopoietic stem cells in the direction of polyclonality and the original diversity of clones. Such events can form the basis for the rejuvenation of the blood-forming cell system. The results of the laboratory's work indicate that other stem cells in the body capture extracellular DNA fragments too. This fact creates a paradigm for the overall rejuvenation of the body.},
}

@article {pmid39722539,
year = {2025},
author = {Zepeda-Rivera, MA and Eisele, Y and Baryiames, A and Wu, H and Mengoni, C and Piccinno, G and McMahon, EF and LaCourse, KD and Jones, DS and Hauner, H and Minot, SS and Segata, N and Dewhirst, FE and Johnston, CD and Bullman, S},
title = {Fusobacterium sphaericum sp. nov., isolated from a human colon tumor adheres to colonic epithelial cells and induces IL-8 secretion.},
journal = {Gut microbes},
volume = {17},
number = {1},
pages = {2442522},
doi = {10.1080/19490976.2024.2442522},
pmid = {39722539},
issn = {1949-0984},
mesh = {Humans ; *Interleukin-8/metabolism/genetics ; *Colonic Neoplasms/microbiology/pathology ; *Fusobacterium/isolation & purification/genetics ; *Epithelial Cells/microbiology ; *Phylogeny ; Bacterial Adhesion ; Colon/microbiology/pathology ; Feces/microbiology ; Adenocarcinoma/microbiology/pathology ; Gastrointestinal Microbiome ; RNA, Ribosomal, 16S/genetics ; Genome, Bacterial ; },
abstract = {Cancerous tissue is a largely unexplored microbial niche that provides a unique environment for the colonization and growth of specific bacterial communities, and with it, the opportunity to identify novel bacterial species. Here, we report distinct features of a novel Fusobacterium species, F. sphaericum sp. nov. (Fs), isolated from primary colon adenocarcinoma tissue. We acquire the complete closed genome and associated methylome of this organism and phylogenetically confirm its classification into the Fusobacterium genus, with F. perfoetens as its closest neighbor. Fs is phenotypically and genetically distinct, with morphological analysis revealing its coccoid shape, that while similar to F. perfoetens is rare for most Fusobacterium members. Fs displays a metabolic profile and antibiotic resistance repertoire consistent with other Fusobacterium species. In vitro, Fs has adherent and immunomodulatory capabilities, as it intimately associates with human colon cancer epithelial cells and promotes IL-8 secretion. An analysis of the prevalence and abundance of Fs in > 20,000 human metagenomic samples shows that it is a rarely detected member within human stool with variable relative abundance, found in both healthy controls and patients with colorectal cancer (CRC). Our study sheds light on a novel bacterial species isolated directly from the human CRC tumor niche and given its in vitro interaction with cancer epithelial cells suggests that its role in human health and disease warrants further investigation.},
}

Humans
*Interleukin-8/metabolism/genetics
*Colonic Neoplasms/microbiology/pathology
*Fusobacterium/isolation & purification/genetics
*Epithelial Cells/microbiology
*Phylogeny
Bacterial Adhesion
Colon/microbiology/pathology
Feces/microbiology
Adenocarcinoma/microbiology/pathology
Gastrointestinal Microbiome
RNA, Ribosomal, 16S/genetics
Genome, Bacterial

@article {pmid39722458,
year = {2024},
author = {He, W and Li, X and Qian, Q and Shang, L},
title = {The Developments and Prospects of Plant Super Pangenomes: Demands, Approaches and Applications.},
journal = {Plant communications},
volume = {},
number = {},
pages = {101230},
doi = {10.1016/j.xplc.2024.101230},
pmid = {39722458},
issn = {2590-3462},
abstract = {By integrating genomes of different accessions, the pangenome can offer more comprehensive and reference-bias-free population genetic information in a species than a single reference genome. With the rapid accumulation of genomic sequencing data and the expanding scope of plant research, the focus of plant pangenomics research has gradually evolved from a single species to multiple species in recent years, giving rise to the concept of super pangenome that cover all genomic sequences of a genus-level taxonomic groups. By integrating more cultivated and wild species, the super pangenome has made significant contributions to the resolution of multiple research areas such as plant genetic diversity, evolution, domestication, and molecular breeding. Here, we provide a comprehensive overview of the plant super pangenomes, focusing on its unique value and development demands, construction approaches, potential applications and achievements. We highlight the distinctive advantages and promising prospects of super pangenomes and discuss the current challenges and future directions.},
}

@article {pmid39719828,
year = {2024},
author = {Zhang, L and Liu, Y and Huang, Y and Zhang, Y and Fu, Y and Xiao, Y and Chen, S and Zhang, K and Cheng, F},
title = {SolPGD: Solanaceae Pan-genomes Reveal Extensive Fractionation and Functional Innovation of Duplicated Genes.},
journal = {Plant communications},
volume = {},
number = {},
pages = {101231},
doi = {10.1016/j.xplc.2024.101231},
pmid = {39719828},
issn = {2590-3462},
abstract = {The Solanaceae family contains many agriculturally important crops, including tomato, potato, pepper, and tobacco, as well as others with growing potential, such as the orphan crops groundcherry, wolfberry, and pepino. Research progress varies greatly among these species, with model crops like tomato far ahead, which limits the broader agricultural application of other solanaceous species. Here, we constructed the interspecies pan-genome for the Solanaceae family and identified distinct patterns of gene retention. We reveal that the activity of specific transposable elements is associated with gene fractionation and transposition. The pan-genome is further resolved at the level of T subgenomes that were generated by Solanaceae specific paleo-hexaploidization (T event). We show the strong fractionation (loss) and divergence of genes resulting from ancient duplications. For example, all the class A and E flower model genes in Solanaceae originally evolved from two tandemly duplicated genes, which further expanded through the γ and T events and then fractionated into ten genes in tomato, acquiring distinct functions critical for fruit development. Based on these results, we developed the Solanaceae Pan-Genome Database (SolPGD, http://www.bioinformaticslab.cn/SolPGD), which integrates various datasets of the inter- and intra-pangenomes of Solanaceae. These findings and valuable resources will further promote studies of solanaceous species, including the orphan crops.},
}

@article {pmid39718018,
year = {2024},
author = {Tian, R and Xie, F and Wang, X and Dai, L and Wang, J and Liu, Y and Zhao, C and Li, Q and Zhang, W},
title = {Epidemiological investigation and drug resistance analysis of Avian pathogenic Escherichia coli (APEC) of Wenchang chickens in Hainan, China.},
journal = {Avian pathology : journal of the W.V.P.A},
volume = {},
number = {},
pages = {1-41},
doi = {10.1080/03079457.2024.2447296},
pmid = {39718018},
issn = {1465-3338},
abstract = {Avian pathogenic Escherichia coli (APEC) is one of the major causes of poultry morbidity worldwide, severely reducing egg production and embryo hatchability in laying hens. Hainan Wenchang chicken is an important poultry breed in Hainan, China, and its culture has been affected by APEC for a long time. In this study, in order to investigate the causes of low hatchability and a large number of weak chicks during the breeding of Wenchang chicken, a total of 130 strains of APEC were isolated from 591 chicken embryo samples collected from five large-scale farms of Wenchang chicken in Hainan area. The APEC isolates from Hainan Wenchang chicken embryos were analyzed in terms of serotypes, drug resistance, genomes and evolutionary relationships. O8 was the main prevalent serotype of APEC from embryos, and the isolates were highly resistant to antibiotics and multi-drug resistant. 19.2% of the isolates were resistant to 14 antibiotics with a resistance rate of more than 73%. The number of resistance genes carried by APEC isolates from embryos was stabilized at 53. The results of pan-genomic analysis showed that the genomes of Hainan Wenchang chicken embryo APEC isolates would be concentrated in 2 evolutionary clusters, and the isolates of the same serotype had extremely close evolutionary relationships. This study is the first large-scale isolation and analysis of APEC isolated from Wenchang chicken embryos, which can provide a reference for the prevention and control of APEC and antibiotic use in Hainan Wenchang chickens.},
}

@article {pmid39717611,
year = {2024},
author = {Baati, H and Siala, M and Benali, S and Azri, C and Dunlap, C and Martínez-Espinosa, RM and Trigui, M},
title = {Elucidating metabolic pathways through genomic analysis in highly heavy metal-resistant Halobacterium salinarum strains.},
journal = {Heliyon},
volume = {10},
number = {23},
pages = {e40822},
pmid = {39717611},
issn = {2405-8440},
abstract = {The annotated and predicted genomes of five archaeal strains (AS1, AS2, AS8, AS11 and AS19), isolated from Sfax solar saltern sediments (Tunisia) and affiliated with Halobacterium salinarum, were performed by RAST webserver (Rapid Annotation using Subsystem Technology) and NCBI prokaryotic genome annotation pipeline (PGAP). The results showed the ability of strains to use a reduced semi-phosphorylative Entner-Doudoroff pathway for glucose degradation and an Embden-Meyerhof one for gluconeogenesis. They could use glucose, fructose, glycerol, and acetate as sole source of carbon and energy. ATP synthase, various cytochromes and aerobic respiration proteins were encoded. All strains showed fermentation capability through the arginine deiminase pathway and facultative anaerobic respiration using electron acceptors (Dimethyl sulfoxide and trimethylamine N-oxide). Several biosynthesis pathways for many amino acids were identified. Comparative and pangenome analyses between the strains and the well-studied halophilic archaea Halobacterium NRC-1 highlighted a notable dissimilarity. Besides, the strains shared a core genome of 1973 genes and an accessory genome of 767 genes. 129, 94, 67, 15 and 29 unique genes were detected in the AS1, AS2, AS8, AS11 and AS19 genomes, respectively. Most of these unique genes code for hypothetical proteins. The strains displayed plant-growth promoting characteristics under heavy metal stress (Ammonium assimilation, phosphate solubilization, chemotaxis, cell motility and production of indole acetic acid, siderophore and phenazine). Therefore, they could be used as a biofertilizer to promote plant growth. The genomes encoded numerous biotechnologically relevant genes responsible for vitamin biosynthesis, including cobalamin, folate, biotin, pantothenate, riboflavin, thiamine, menaquinone, nicotinate, and nicotinamide. The carotenogenetic pathway of the studied strains was also predicted. Consequently, the findings of this study contribute to a better understanding of the halophilic archaea metabolism providing valuable insights into their ecophysiology as well as relevant biotechnological applications.},
}

@article {pmid39713061,
year = {2024},
author = {Ning, W and Wang, W and Liu, Z and Xie, W and Chen, H and Hong, D and Yang, QY and Cheng, S and Guo, L},
title = {The pan-NLRome analysis based on 23 genomes reveals the diversity of NLRs in Brassica napus.},
journal = {Molecular breeding : new strategies in plant improvement},
volume = {44},
number = {12},
pages = {2},
pmid = {39713061},
issn = {1572-9788},
abstract = {Brassica napus, a globally significant oilseed crop, exhibits a wide distribution across diverse climatic zones. B. napus is being increasingly susceptible to distinct diseases, such as blackleg, clubroot and sclerotinia stem rot, leading to substantial reductions in yield. Nucleotide-binding site leucine-rich repeat genes (NLRs), the most pivotal family of resistance genes, can be effectively harnessed by identifying and uncovering their diversity to acquire premium disease-resistant gene resources. Here, we collected the genomes of 23 accessions and established the first comprehensive pan-NLRome in B. napus by leveraging multiple genomic resources. We observe significant variation in the number of NLR genes across different B. napus accessions, ranging from 189 to 474. Notably, TNL (TIR-NBS-LRR) genes constitute approximately half of the total count, indicating their predominant presence in B. napus. The number of NLRs in the C subgenome is significantly higher than that in the A subgenome, and chromosome C09 exhibits the highest density of NLR genes with featuring multiple NLR clusters. Domain analysis reveals that the integrated domains significantly enhance the diversity of NLRs, with B3 DNA binding, VQ, and zinc fingers being the most prevalent integrated domains. Pan-genomic analysis reveals that the core type of NLR genes, which is present in most accessions, constitutes approximately 58% of the total NLRs. Furthermore, we conduct a comparative analysis of the diversity of NLR genes across distinct ecotypes, leading to the identification of ecotype-specific NLRs and their integrated domains. In conclusion, our study effectively addresses the limitations of a single reference genome and provides valuable insights into the diversity of NLR genes in B. napus, thereby contributing to disease resistance breeding.},
}

@article {pmid39708886,
year = {2024},
author = {Bano, S and Khatoon, A and Quareshi, U and Ul-Haq, Z and Karim, A},
title = {Pan-genome analysis and drug repurposing strategies for extensively drug-resistant Salmonella Typhi: Subtractive genomics and e-pharmacophore approaches.},
journal = {International journal of biological macromolecules},
volume = {},
number = {},
pages = {139003},
doi = {10.1016/j.ijbiomac.2024.139003},
pmid = {39708886},
issn = {1879-0003},
abstract = {In the current study, we presented the genome sequence and taxonomic classification of the new extensively drug-resistant (XDR) Salmonella enterica serovar Typhi strain JRCGR-ST-AK02. Its genome size was found to be 4,780,534 bp, containing 4864 genes. Taxonomic classification was performed based on the Average Nucleotide Identity (ANI), Genome-to-Genome Distance Calculator (GGDC) and Average Amino Acid Identity (AAI) analysis. Pan-genome analysis revealed 34,4915 core genes, which are predominantly involved in general functions and carbohydrate metabolism. We used a subtractive genomics approach and identified the PocR protein as a drug target. Its 3D structure was built using homology modeling, and an e-pharmacophore hypothesis was created using its binding site. The pharmacophore hypothesis was screened against FDA-approved ligands library and a total of 2018 out 9392 drugs were selected for molecular docking. Cangrelor and Pentagastrin presented the highest docking scores (≥ -9.0). The binding dynamics of these promising FDA-approved drugs were further confirmed through 200 ns molecular dynamics simulation, highlighting their stable and strong interactions with the PocR protein. Our study highlights the potential of Cangrelor and Pentagastrin for repurposing against XDR Salmonella Typhi. By identifying these drugs as promising candidates, we pave the way for new treatments for XDR Salmonella Typhi infections.},
}

@article {pmid39702388,
year = {2024},
author = {Liu, H and Fan, Z and Tong, N and Lin, J and Huang, Y and Duan, Y and Zhu, X},
title = {The exploration of high production of tiancimycins in Streptomyces sp. CB03234-S revealed potential influences of universal stress proteins on secondary metabolisms of streptomycetes.},
journal = {Microbial cell factories},
volume = {23},
number = {1},
pages = {337},
pmid = {39702388},
issn = {1475-2859},
support = {CX20210112//the Hunan Provincial Innovation Foundation for Postgraduate/ ; 2021zzts0330//the Fundamental Research Funds for the Central Universities of Central South University (CSU)/ ; 2023SK2071//the Science and Technology Innovation Program of Hunan Province/ ; BP0820034//the Chinese Ministry of Education 111 Project/ ; BP0820034//the Chinese Ministry of Education 111 Project/ ; },
mesh = {*Streptomyces/metabolism/genetics ; *Secondary Metabolism ; *Bacterial Proteins/genetics/metabolism ; Genome, Bacterial ; },
abstract = {BACKGROUND: Universal stress proteins (USPs) are prevalent in various bacteria to cope with different adverse stresses, while their possible effects on secondary metabolisms of hosts are unclear. Tiancimycins (TNMs) are ten-membered endiynes possessing excellent potential for development of anticancer antibody-drug conjugates. During our efforts to improve TNMs titer, a high-producing strain Streptomyces sp. CB03234-S had been obtained and its possible high yield mechanism is being continuously explored to further enhance TNMs production.

RESULTS: In this work, the whole-genome resequencing and analysis results revealed a notable 583 kb terminal deletion containing 8 highly expressed usp genes in the genome of CB03234-S. The individual complementation of lost USPs in CB03234-S all showed differential effects on secondary metabolism, especially TNMs production. Among them, the overexpression of USP3 increased TNMs titer from 12.8 ± 0.2 to 31.1 ± 2.3 mg/L, while the overexpression of USP8 significantly reduced TNMs titer to only 1.0 ± 0.1 mg/L, but activated the production of porphyrin-type compounds. Subsequent genetic manipulations on USP3/USP8 orthologs in Streptomyces. coelicolor A3(2) and Streptomyces sp. CB00271 also presented clear effects on the secondary metabolisms of hosts. Further sequence similarity network analysis and Streptomyces-based pan‑genomic analysis suggested that the USP3/USP8 orthologs are widely distributed across Streptomyces.

CONCLUSION: Our studies shed light on the potential effects of USPs on secondary metabolisms of streptomycetes for the first time, and USPs could become novel targets for exploring and exploiting natural products in streptomycetes.},
}

*Streptomyces/metabolism/genetics
*Secondary Metabolism
*Bacterial Proteins/genetics/metabolism
Genome, Bacterial

@article {pmid39699575,
year = {2024},
author = {Xie, X and Deng, X and Chen, L and Yuan, J and Chen, H and Wei, C and Feng, C and Liu, X and Qiu, G},
title = {From Gene to Structure: Unraveling Genomic Dark Matter in Ca. Accumulibacter.},
journal = {Environmental science & technology},
volume = {},
number = {},
pages = {},
doi = {10.1021/acs.est.4c09948},
pmid = {39699575},
issn = {1520-5851},
abstract = {"Candidatus Accumulibacter" is a unique and pivotal genus of polyphosphate-accumulating organisms prevalent in wastewater treatment plants and plays mainstay roles in the global phosphorus cycle. However, the efforts to fully understand their genetic and metabolic characteristics are largely hindered by major limitations in existing sequence-based annotation methods. Here, we reported an integrated approach combining pangenome analysis, protein structure prediction and clustering, and meta-omic characterization, to uncover genetic and metabolic traits previously unexplored for Ca. Accumulibacter. The identification of a previously overlooked pyrophosphate-fructose 6-phosphate 1-phosphotransferase gene (pfp) suggested that all Ca. Accumulibacter encoded a complete Embden-Meyerhof-Parnas pathway. A homologue of the phosphate-specific transport system accessory protein (PhoU) was suggested to be an inorganic phosphate transport (Pit) accessory protein (Pap) conferring effective and efficient phosphate transport. Additional lineage members were found to encode complete denitrification pathways. A pipeline was built, generating a pan-Ca. Accumulibacter annotation reference database, covering >200,000 proteins and their encoding genes. Benchmarking on 27 Ca. Accumulibacter genomes showed major improvement in the average annotation coverage from 51% to 82%. This pipeline is readily applicable to diverse cultured and uncultured bacteria to establish high-coverage annotation reference databases, facilitating the exploration of genomic dark matter in the bacterial domain.},
}

@article {pmid39696427,
year = {2024},
author = {Sarashetti, P and Lipovac, J and Tomas, F and Šikić, M and Liu, J},
title = {Evaluating data requirements for high-quality haplotype-resolved genomes for creating robust pangenome references.},
journal = {Genome biology},
volume = {25},
number = {1},
pages = {312},
pmid = {39696427},
issn = {1474-760X},
support = {IP-2018-01-5886//Hrvatska Zaklada za Znanost/ ; KK.01.1.1.01.0009//European Regional Development Fund/ ; MOH-000588-01//National Precision Medicine Program/ ; },
mesh = {*Haplotypes ; Humans ; Genomics/methods ; Genome, Human ; },
abstract = {BACKGROUND: Long-read technologies from Pacific Biosciences (PacBio) and Oxford Nanopore Technologies (ONT) have transformed genomics research by providing diverse data types like HiFi, Duplex, and ultra-long ONT. Despite recent strides in achieving haplotype-phased gapless genome assemblies using long-read technologies, concerns persist regarding the representation of genetic diversity, prompting the development of pangenome references. However, pangenome studies face challenges related to data types, volumes, and cost considerations for each assembled genome, while striving to maintain sensitivity. The absence of comprehensive guidance on optimal data selection exacerbates these challenges.

RESULTS: Our study evaluates recommended data types and volumes required to establish a robust de novo genome assembly pipeline for population-level pangenome projects, extensively examining performance between ONT's Duplex and PacBio HiFi datasets in the context of achieving high-quality phased genomes with enhanced contiguity and completeness. The results show that achieving chromosome-level haplotype-resolved assembly requires 20 × high-quality long reads such as PacBio HiFi or ONT Duplex, combined with 15-20 × of ultra-long ONT per haplotype and 10 × of long-range data such as Omni-C or Hi-C. High-quality long reads from both platforms yield assemblies with comparable contiguity, with HiFi excelling in phasing accuracies, while Duplex generates more T2T contigs.

CONCLUSION: Our study provides insights into optimal data types and volumes for robust de novo genome assembly in population-level pangenome projects. Reassessing the recommended data types and volumes in this study and aligning them with practical economic limitations are vital to the pangenome research community, contributing to their efforts and pushing genomic studies with broader impacts.},
}

*Haplotypes
Humans
Genomics/methods
Genome, Human

@article {pmid39695301,
year = {2024},
author = {Rey, E and Abrouk, M and Dufau, I and Rodde, N and Saber, N and Cizkova, J and Fiene, G and Stanschewski, C and Jarvis, DE and Jellen, EN and Maughan, PJ and von Baer, I and Troukhan, M and Kravchuk, M and Hribova, E and Cauet, S and Krattinger, SG and Tester, M},
title = {Genome assembly of a diversity panel of Chenopodium quinoa.},
journal = {Scientific data},
volume = {11},
number = {1},
pages = {1366},
pmid = {39695301},
issn = {2052-4463},
mesh = {*Chenopodium quinoa/genetics ; *Genome, Plant ; Genetic Variation ; },
abstract = {Quinoa (Chenopodium quinoa) is an important crop for the future challenges of food and nutrient security. Deep characterization of quinoa diversity is needed to support the agronomic improvement and adaptation of quinoa as its worldwide cultivation expands. In this study, we report the construction of chromosome-scale genome assemblies of eight quinoa accessions covering the range of phenotypic and genetic diversity of both lowland and highland quinoas. The assemblies were produced from a combination of PacBio HiFi reads and Bionano Saphyr optical maps, with total assembly sizes averaging 1.28 Gb with a mean N50 of 71.1 Mb. Between 43,733 and 48,564 gene models were predicted for the eight new quinoa genomes, and on average, 66% of each quinoa genome was classified as repetitive sequences. Alignment between the eight genome assemblies allowed the identification of structural rearrangements including inversions, translocations, and duplications. These eight novel quinoa genome assemblies provide a resource for association genetics, comparative genomics, and pan-genome analyses for the discovery of genetic components and variations underlying agriculturally important traits.},
}

*Chenopodium quinoa/genetics
*Genome, Plant
Genetic Variation

@article {pmid39694196,
year = {2024},
author = {Panigrahi, M and Rajawat, D and Nayak, SS and Jain, K and Nayak, A and Rajput, AS and Sharma, A and Dutt, T},
title = {A Comprehensive Review on Genomic Insights and Advanced Technologies for Mastitis Prevention in Dairy Animals.},
journal = {Microbial pathogenesis},
volume = {},
number = {},
pages = {107233},
doi = {10.1016/j.micpath.2024.107233},
pmid = {39694196},
issn = {1096-1208},
abstract = {Mastitis, is a multi-etiological disease that significantly impacts milk production and reproductive efficiency. This is highly prevalent in dairy populations subjected to intensive selection for higher milk yield and where inbreeding is common. The issue is amplified by climate change and poor hygiene management, making disease control challenging. Key obstacles include antibiotic resistance, maximum residue levels, horizontal gene transfer, and limited success in breeding for resistance. Predictive genomics offers a promising solution for mastitis prevention by identifying genetic traits linked with susceptibility to mastitis. This review compiles the research and findings on genomics and its allied approaches such as pan-genomics, epigenetics, proteomics, and transcriptomics for diagnosing, understanding, and treating mastitis. In dairy production, artificial intelligence (AI), particularly deep learning (DL) techniques like convolutional neural networks (CNNs), has demonstrated significant potential to enhance milk production and improve farm profitability. It highlights the integration of advanced technologies like machine learning (ML), CRISPR, and pan-genomics to enhance our knowledge of mastitis epidemiology, pathogen evolution, and the development of more effective diagnostic, preventive, and therapeutic strategies for dairy herds. Genomic advancements provide critical insights into the complexities of mastitis, offering new avenues for understanding its dynamics. Integrating these findings with key predisposing factors can drive targeted prevention and more effective disease management.},
}

@article {pmid39694857,
year = {2024},
author = {Milia, S and Leonard, A and Mapel, XM and Bernal Ulloa, SM and Drögemüller, C and Pausch, H},
title = {Taurine pangenome uncovers a segmental duplication upstream of KIT associated with depigmentation in white-headed cattle.},
journal = {Genome research},
volume = {},
number = {},
pages = {},
doi = {10.1101/gr.279064.124},
pmid = {39694857},
issn = {1549-5469},
abstract = {Cattle have been selectively bred for coat color, spotting, and depigmentation patterns. The assumed autosomal dominant inherited genetic variants underlying the characteristic white head of Fleckvieh, Simmental, and Hereford cattle have not been identified yet, although the contribution of structural variation upstream the KIT gene has been proposed. Here, we construct a graph pangenome from 24 haplotype assemblies representing seven taurine cattle breeds to identify and characterize the white head-associated locus for the first time based on long-read sequencing data and pangenome analyses. We introduce a pangenome-wide association mapping approach which examines assembly path similarities within the graph to reveal an association between two most likely serial alleles of a complex structural variant 66 kb upstream KIT and facial depigmentation. The complex structural variant contains a variable number of tandemly duplicated 14.3 kb repeats, consisting of LTRs, LINEs, and other repetitive elements, leading to misleading alignments of short and long reads when using a linear reference. We align 250 short-read sequencing samples spanning 15 cattle breeds to the pangenome graph, further validating that the alleles of the structural variant segregate with head depigmentation. We estimate an increased count of repeats in Hereford relative to Simmental and other white-headed cattle breeds from the graph alignment coverage, suggesting a large under-assembly in the current Hereford-based cattle reference genome which had fewer copies. Our work shows that exploiting assembly path similarities within graph pangenomes can reveal trait-associated complex structural variants.},
}

@article {pmid39687382,
year = {2024},
author = {Shayerul Abedin Shayer, KM and Shuvo, SR and Jabeen, I and Hossain, M and Islam, S},
title = {Draft genome sequence data of Serratia marcescens strain harboring blaNDM-7 from Dhaka, Bangladesh.},
journal = {Data in brief},
volume = {57},
number = {},
pages = {111133},
doi = {10.1016/j.dib.2024.111133},
pmid = {39687382},
issn = {2352-3409},
abstract = {Here, the draft genome sequence of a multi-drug resistant (MDR) Serratia marcescens strain BMD28, isolated from a clinical source from Dhaka, Bangladesh, has been reported. The sequence raw read files were generated using Illumina sequencing technology utilizing genomic DNA from the pure culture of this strain. The strain has a genome size of around 5.4 million base pairs, a GC content of 59.70 %, and 5,141 coding sequences. We conducted genomic studies using several bioinformatics tools focusing on resistance genes, virulence factors, toxin-antitoxin systems, and pangenome analysis. Strain BMD28 harbored the blaNDM-7 gene in an IncX3 plasmid. A phylogenomic study with S. marcescens strains isolated worldwide revealed that our strain is in the same clade as other strains reported in Bangladesh. The data can be used primarily to understand the genomic content, epidemiology, and evolution of S. marcescens in Bangladesh. The genome sequence data of BMD28 has been deposited in the NCBI database under BioSample accession number SAMN41260295.},
}

@article {pmid39684382,
year = {2024},
author = {Salgado-Morales, R and Barba-Xochipa, K and Martínez-Ocampo, F and Dantán-González, E and Hernández-Mendoza, A and Quiterio-Trenado, M and Rodríguez-Santiago, M and Rivera-Ramírez, A},
title = {Pangenome-Wide Association Study in the Chlamydiaceae Family Reveals Key Evolutionary Aspects of Their Relationship with Their Hosts.},
journal = {International journal of molecular sciences},
volume = {25},
number = {23},
pages = {},
doi = {10.3390/ijms252312671},
pmid = {39684382},
issn = {1422-0067},
mesh = {*Chlamydiaceae/genetics ; Animals ; *Genome, Bacterial ; *Genome-Wide Association Study ; Humans ; *Chlamydia/genetics/classification ; Phylogeny ; Host-Pathogen Interactions/genetics ; Evolution, Molecular ; Chlamydophila/genetics ; },
abstract = {The Chlamydiaceae are a family of obligate intracellular bacteria known for their unique biphasic developmental cycle. Chlamydial are associated with various host organisms, including humans, and have been proposed as emerging pathogens. Genomic studies have significantly enhanced our understanding of chlamydial biology, host adaptation, and evolutionary processes. In this study, we conducted a complete pangenome association analysis (pan-GWAS) using 101 genomes from the Chlamydiaceae family to identify differentially represented genes in Chlamydia and Chlamydophila, revealing their distinct evolutionary strategies for interacting with eukaryotic hosts. Our analysis identified 289 genes with differential abundance between the two clades: 129 showed a strong association with Chlamydia and 160 with Chlamydophila. Most genes in Chlamydia were related to the type III secretion system, while Chlamydophila genes corresponded to various functional categories, including translation, replication, transport, and metabolism. These findings suggest that Chlamydia has developed a high dependence on mammalian cells for replication, facilitated by a complex T3SS for intracellular manipulation. In contrast, the metabolic and functional diversity in Chlamydophila allows it to colonize a broad range of hosts, such as birds, reptiles, amphibians, and mammals, making it a less specialized clade.},
}

*Chlamydiaceae/genetics
Animals
*Genome, Bacterial
*Genome-Wide Association Study
Humans
*Chlamydia/genetics/classification
Phylogeny
Host-Pathogen Interactions/genetics
Evolution, Molecular
Chlamydophila/genetics

@article {pmid39675005,
year = {2024},
author = {Rubio, A and Garzón, A and Moreno-Rodríguez, A and Pérez-Pulido, AJ},
title = {Biological warfare between two bacterial viruses in a defense archipelago sheds light on the spread of CRISPR-Cas systems.},
journal = {Cell reports},
volume = {43},
number = {12},
pages = {115085},
doi = {10.1016/j.celrep.2024.115085},
pmid = {39675005},
issn = {2211-1247},
abstract = {CRISPR-Cas systems are adaptive immunity systems of bacteria and archaea that prevent infection by viruses and other external mobile genetic elements. It is currently known that these defense systems can be co-opted by the same viruses. We have found one of these viruses in the opportunistic pathogen Acinetobacter baumannii, and the same system has been also found in an integration hotspot of the bacterial genome that harbors other multiple defense systems. The CRISPR-Cas system appears to especially target another virus that could compete with the system itself for the same integration site. This virus is prevalent in strains of the species belonging to the so-called Global Clone 2, which causes the most frequent outbreaks worldwide. Knowledge of this viral warfare involving antiviral systems could be useful in the fight against infections caused by bacteria, and it would also shed light on how CRISPR-Cas systems expand in bacteria.},
}

@article {pmid39673077,
year = {2024},
author = {Alkemade, JA and Hohmann, P and Messmer, MM and Barraclough, TG},
title = {Comparative Genomics Reveals Sources of Genetic Variability in the Asexual Fungal Plant Pathogen Colletotrichum lupini.},
journal = {Molecular plant pathology},
volume = {25},
number = {12},
pages = {e70039},
pmid = {39673077},
issn = {1364-3703},
support = {//Bundesamt für Landwirtschaft/ ; //Calleva Research Centre for Evolution and Human Science/ ; 727230//Horizon 2020 Framework Programme/ ; 17.00090//Staatssekretariat für Bildung, Forschung und Innovation/ ; RYC2022-037997//MICIU/AEI/10.13039/501100011033 and FSE+/ ; },
mesh = {*Colletotrichum/genetics/pathogenicity ; *Genetic Variation ; *Genome, Fungal ; *Genomics ; *Phylogeny ; Plant Diseases/microbiology ; DNA Transposable Elements/genetics ; Reproduction, Asexual/genetics ; Genome Size ; },
abstract = {Fungal plant pathogens cause major crop losses worldwide, with many featuring compartmentalised genomes that include both core and accessory regions, which are believed to drive adaptation. The highly host-specific fungus Colletotrichum lupini greatly impacts lupin (Lupinus spp.) cultivation. This pathogen is part of clade 1 of the C. acutatum species complex and comprises four genetically uniform, presumably clonal, lineages (I-IV). Despite this, variation in virulence and morphology has been observed within these lineages. To investigate the potential sources of genetic variability in this asexual fungus, we compared the genomes of 16 C. lupini strains and 17 related Colletotrichum species. Phylogenomics confirmed the presence of four distinct lineages, but further examination based on genome size, gene content, transposable elements (TEs), and deletions revealed that lineage II could be split into two groups, II-A and II-B. TE content varied between lineages and correlated strongly with genome size variation, supporting a role for TEs in genome expansion in this species. Pangenome analysis revealed a highly variable accessory genome, including a minichromosome present in lineages II, III, and IV, but absent in lineage I. Accessory genes and effectors appeared to cluster in proximity to TEs. Presence/absence variation of putative effectors was lineage-specific, suggesting that these genes play a crucial role in determining host range. Notably, no effectors were found on the TE-rich minichromosome. Our findings shed light on the potential mechanisms generating genetic diversity in this asexual fungal pathogen that could aid future disease management.},
}

*Colletotrichum/genetics/pathogenicity
*Genetic Variation
*Genome, Fungal
*Genomics
*Phylogeny
Plant Diseases/microbiology
DNA Transposable Elements/genetics
Reproduction, Asexual/genetics
Genome Size

@article {pmid39671861,
year = {2024},
author = {Buzzanca, D and Giordano, M and Chiarini, E and Ferrocino, I and Cocolin, L and Zeppa, G and Alessandria, V},
title = {Delving into Roccaverano PDO cheese: A comprehensive examination of microbial diversity and flavour profiles compared to non-PDO cheeses.},
journal = {International journal of food microbiology},
volume = {429},
number = {},
pages = {111014},
doi = {10.1016/j.ijfoodmicro.2024.111014},
pmid = {39671861},
issn = {1879-3460},
abstract = {Roccaverano Protected Designation of Origin (PDO) is a fresh soft cheese produced in Roccaverano area (Italy). This study aimed to evaluate Roccaverano PDO microbiota, together with aromatic profile and sensory analysis to be compared with 15 non-PDO cheeses of the same type. Microbiota was evaluated through shotgun metagenomics sequencing, while GC-MS analysis was conducted to study volatile organic compounds (VOCs) presence and concentration. Sensory analyses were conducted through ONAF (Italian National Organization of Cheese Tasters) evaluation parameters followed by flash profile sensory analysis of selected cheeses. The results demonstrated Lactococcus lactis predominance in both non-PDO and PDO cheeses, while Streptococcus thermophilus was more abundant in non-PDO group. A higher abundance of Kluyveromyces lactis was observed in Roccaverano PDO, which exhibited greater fungal diversity compared to non-PDO cheeses. Metagenome-Assembled Genomes of 26 L. lactis and 19 Leuconostoc mesenteroides showed absence of significant differences in terms of average nucleotide identity and pangenomes partitions. The ONAF sensory evaluation demonstrated a higher average score of Roccaverano PDO group. Flash profile analysis demonstrated that lactic aroma/odour, acid, astringent, vegetal odour, exotic fruit and fermented aroma, hazelnut flavour and sweet were associated with high ONAF scores. The concentration of butanoic acid, 2-methyl-, ethyl ester and butanoic acid, 3-methyl- (sweat, acid, rancid related) were higher in PDO cheeses, while reads related to butanoate metabolism were less abundant compared to non-PDO samples. Several fungal species (included K. lactis) were associated with astringents, acid and chalky flavours. Roccaverano PDO demonstrates unique characteristics even maintaining a certain degree of variability between samples.},
}

@article {pmid39670914,
year = {2024},
author = {Yang, Y and Yan, X and Haley, BJ and Li, C and Nou, X},
title = {Genomic Comparison of Reoccurring, Emerging, and Persistent (REP) Shiga Toxin-Producing Escherichia coli O157:H7.},
journal = {Foodborne pathogens and disease},
volume = {},
number = {},
pages = {},
doi = {10.1089/fpd.2024.0144},
pmid = {39670914},
issn = {1556-7125},
abstract = {Escherichia coli O157:H7 strains associated with several recent (2017-2020) multi-state outbreaks linked to leafy green vegetables have been characterized as "reoccurring, emerging, and persistent" (REP). Our recent unpublished work demonstrated that the REP strains had significantly enhanced potential for biofilm formation. In this study, comparative genomic analyses were conducted for a better understanding of the mechanisms behind the enhanced biofilm formation, and thereby potentially increased environmental fitness, by the REP strains. Phylogenetically, the recent outbreak strains formed two distinct clusters represented by REPEXH01 and REPEXH02. Compared with EDL933 and other previous outbreak reference strains, the REP strains (clustering with REPEXH02) exhibiting strong biofilm formation were found to have acquired two genes encoding proteins of unknown functions (hypothetical proteins) and lost certain prophage-related genes. In addition, several single nucleotide polymorphisms in genes related to biofilm formation were identified.},
}

@article {pmid39670058,
year = {2024},
author = {Kantor, EJH and Robicheau, BM and Tolman, J and Archibald, JM and LaRoche, J},
title = {Metagenomics reveals the genetic diversity between sublineages of UCYN-A and their algal host plastids.},
journal = {ISME communications},
volume = {4},
number = {1},
pages = {ycae150},
pmid = {39670058},
issn = {2730-6151},
abstract = {UCYN-A (or Cand. Atelocyanobacterium thalassa) has been recognized as a globally distributed, early stage, nitrogen-fixing organelle (the "nitroplast") of cyanobacterial origin present in the haptophyte alga Braarudosphaera bigelowii. Although the nitroplast was recognized as UCYN-A2, not all sublineages of UCYN-A have been confirmed as nitroplasts, and full genomes are still lacking for several known sublineages. We investigated the differences between UCYN-A sublineages by sequencing and assembly of metagenomic sequences acquired from cultured biomass from NW Atlantic seawater, which yielded near-complete Metagenome Assembled Genomes (MAGs) corresponding to UCYN-A1, -A4, and the plastid of the UCYN-A4-associated B. bigelowii. Weekly time-series data paired with the recurrence of specific microbes in cultures used for metagenomics gave further insight into the microbial community associated with the algal/UCYN-A complex. The UCYN-A1 MAG was found to have 99% average nucleotide identity (ANI) to the Pacific-derived reference genome despite its Atlantic Ocean origin. Comparison of the UCYN-A4 MAG (the initial genome sequenced from this sublineage) to other genomes showed that UCYN-A4 is sufficiently genetically distinct from both UCYN-A1 and UCYN-A2 (ANI of ~83% and ~85%, respectively) to be considered its own sublineage, but more similar to UCYN-A2 than -A1, supporting its possible classification as a nitroplast. The B. bigelowii plastid sequence was compared with published plastid sequences (sharing 78% ANI with Chrysochromulina parva) adding to our understanding of genomic variation across Haptophyta organelles and emphasizing the need for further full genomic sequencing of B. bigelowii genotypes and their organelles.},
}

@article {pmid39667962,
year = {2024},
author = {Zeng, W and Luo, M and Du, P and Li, Z and Peng, Y and Wang, M and Zhao, W and Zhang, H and Li, Y and Luo, P and Wu, Y and Xu, J and Li, X and Lu, X and Kan, B},
title = {bla NDM-1 Carried by a Transferable Plasmid in a Salmonella Strain Isolated from Healthy Individuals.},
journal = {Biomedical and environmental sciences : BES},
volume = {37},
number = {11},
pages = {1252-1261},
doi = {10.3967/bes2024.104},
pmid = {39667962},
issn = {2214-0190},
mesh = {*beta-Lactamases/genetics ; *Plasmids/genetics ; Humans ; Anti-Bacterial Agents/pharmacology ; China ; Microbial Sensitivity Tests ; Salmonella typhimurium/genetics/drug effects/isolation & purification ; Salmonella/genetics/drug effects/isolation & purification ; Salmonella Infections/microbiology ; },
abstract = {OBJECTIVE: Our study aimed to conduct genomic characterization of Salmonella strains carrying the bla NDM-1 gene in the intestinal tract of healthy individuals. The objectives were to underscore the importance of genomic surveillance for drug resistance in both commensal and pathogenic bacteria among healthy populations, and to establish protocols for regulating drug resistance plasmids based on the completion of a comprehensive map of drug resistance plasmid genomes.

METHODS: We performed antimicrobial susceptibility testing and employed second- and third-generation sequencing techniques to analyze Salmonella strains harboring the bla NDM-1 gene, to surveil drug-resistant bacteria in the intestines of healthy subjects. Sequence comparison was conducted using both core- and pan-genome approaches. Concurrently, conjugation experiments were carried out to assess the efficiency of plasmid transfer.

RESULTS: We isolated a carbapenem-resistant Salmonella enterica serovar Typhimurium strain from a healthy food worker in China. This strain harbored an IncHI2/IncHI2A plasmid carrying bla NDM-1 along with multiple antibiotic resistance genes (ARGs). Our findings highlight the potential for asymptomatic carriers to facilitate the transmission of ARGs. Pan-genomic analysis revealed that bla NDM-1-positive plasmids could traverse bacterial species barriers, facilitating cross-host transmission.

CONCLUSION: This study marks the first detection of bla NDM-1 in Salmonella strains isolated from healthy individuals. We underscore the risk associated with the transmission of conjugative hybrid plasmids carrying bla NDM-1, which have the potential to be harbored and transmitted among healthy individuals. Enhanced surveillance of drug-resistant pathogens and plasmids in the intestinal microbiota of healthy individuals could provide insights into the risk of ARG transmission and pathways for population-wide dissemination via ARG transfer factors.},
}

*beta-Lactamases/genetics
*Plasmids/genetics
Humans
Anti-Bacterial Agents/pharmacology
China
Microbial Sensitivity Tests
Salmonella typhimurium/genetics/drug effects/isolation & purification
Salmonella/genetics/drug effects/isolation & purification
Salmonella Infections/microbiology

@article {pmid39665690,
year = {2024},
author = {Bian, P and Li, J and Zhou, S and Wang, X and Gong, M and Guo, X and Cai, Y and Yang, Q and Fu, J and Li, R and Huang, S and Luo, F and Shah, AM and Lenstra, JA and Mwacharo, JM and Li, R and Ren, G and Wang, X and Li, C and Zheng, W and Jiang, Y and Wang, X},
title = {A graph-based goat pangenome reveals structural variations involved in domestication and adaptation.},
journal = {Molecular biology and evolution},
volume = {},
number = {},
pages = {},
doi = {10.1093/molbev/msae251},
pmid = {39665690},
issn = {1537-1719},
abstract = {Pangenomes can facilitate a deeper understanding of genome complexity. Using de novo phased long-read assemblies of eight representative goat breeds, we constructed a graph-based pangenome of goats (Capra hircus) and discovered 113 Mb autosomal novel sequences. Combining this multi-assembly pangenome with low-coverage PacBio HiFi sequences, we constructed a long-read structural variations (SVs) database containing 59,325 SV deletions, 84,910 SV insertions and 24,954 other complex SV alleles. This resource allowed reliable graph-based genotyping from short reads of 79 wild and 1,148 worldwide domestic goats. Selection signal analysis of SV captured a novel immune-related domestication locus containing the galectin-9 gene and extra copies of the ruminant-specific galectin-9-like genes (LGALS9L), which have high tissue specificity. A segmental duplication in domestic goats generates three additional LGALS9L copies. Ancient goat genome sequences show a gradual increase in frequency of this duplication from the Neolithic to the present. Two other newly detected SVs also have higher selection signals than adjacent SNPs, a truncated-LINE1 deletion in EDAR2 associated with cashmere production and a VNTR-related insertion in PAPSS2 linked to high-altitude adaptation. In summary, the multi-assembly goat pangenome and long-read SV database facilitates detecting complex variations that are important in evolution and selection.},
}

@article {pmid39664816,
year = {2024},
author = {Öztürk, Ü and Mattavelli, M and Ribeca, P},
title = {GIN-TONIC: non-hierarchical full-text indexing for graph genomes.},
journal = {NAR genomics and bioinformatics},
volume = {6},
number = {4},
pages = {lqae159},
pmid = {39664816},
issn = {2631-9268},
abstract = {This paper presents a new data structure, GIN-TONIC (Graph INdexing Through Optimal Near Interval Compaction), designed to index arbitrary string-labelled directed graphs representing, for instance, pangenomes or transcriptomes. GIN-TONIC provides several capabilities not offered by other graph-indexing methods based on the FM-Index. It is non-hierarchical, handling a graph as a monolithic object; it indexes at nucleotide resolution all possible walks in the graph without the need to explicitly store them; it supports exact substring queries in polynomial time and space for all possible walk roots in the graph, even if there are exponentially many walks corresponding to such roots. Specific ad-hoc optimizations, such as precomputed caches, allow GIN-TONIC to achieve excellent performance for input graphs of various topologies and sizes. Robust scalability capabilities and a querying performance close to that of a linear FM-Index are demonstrated for two real-world applications on the scale of human pangenomes and transcriptomes. Source code and associated benchmarks are available on GitHub.},
}

@article {pmid39662211,
year = {2024},
author = {Ye, YQ and Zhang, XY and Gong, HN and Ye, MQ and Du, ZJ},
title = {Description of Hyphococcus formosus sp. nov. and Hyphococcus lacteus sp. nov., isolated from coastal sediment, and reclassification of Marinicaulis flavus as Hyphococcus luteus nom. nov. and Marinicaulis aureus as Hyphococcus aureus comb. nov.},
journal = {Systematic and applied microbiology},
volume = {48},
number = {1},
pages = {126575},
doi = {10.1016/j.syapm.2024.126575},
pmid = {39662211},
issn = {1618-0984},
abstract = {During a study on sediment bacterial diversity in coastal China, three bacterial strains, DH-69[T], EH-24, and ECK-19[T], were isolated from coastal sediments off Xiaoshi Island, Weihai. These strains were Gram-staining-negative, aerobic, and coccoid to rod-shaped with prosthecae and flagella. Comparison of the 16S rRNA gene showed that they shared the highest identity values with Hyphococcus flavus MCCC 1K03223[T] (96.2-97.6 %), followed by Marinicaulis flavus SY-3-19[T] (95.2-96.8 %) and Marinicaulis aureus HHTR114[T] (95.2-96.2 %). Genome comparisons using average nucleotide identity (ANI) and average amino acid identity (AAI) suggested that the three novel strains and the three related strains belonged to the same genus, with strains DH-69[T], EH-24, and ECK-19[T] identified as two distinct novel species. Pan-genome analysis revealed that 995 core genes were shared among 23 Hyphococcus genomes/MAGs. Secondary metabolites analysis identified a biosynthesis gene cluster for microsclerodermin, a potent antifungal peptide, in the novel strains. Moreover, these newly isolated strains were detected in various ecosystems, with a particular prevalence in marine environments, based on analysis of 500,048 amplicon datasets, underscoring their ecological preference. Based on polyphasic characterizations, strains DH-69[T] and EH-24 represent a novel species of the genus Hyphococcus, for which the name Hyphococcus formosus sp. nov. is proposed with the type strain DH-69[T] (= MCCC 1H00436[T] = KCTC 8010[T]). Strain ECK-19[T] represents another novel Hyphococcus species, for which the name Hyphococcus lacteus sp. nov. is proposed with the type strain ECK-19[T] (= MCCC 1H00435[T] = KCTC 8009[T]). Furthermore, Marinicaulis flavus and Marinicaulis aureus are proposed to be reclassified as Hyphococcus luteus nom. nov. and Hyphococcus aureus comb. nov., respectively, accompanied by an emended description of the genus Hyphococcus.},
}

@article {pmid39661475,
year = {2024},
author = {Wittouck, S and Eilers, T and van Noort, V and Lebeer, S},
title = {SCARAP: scalable cross-species comparative genomics of prokaryotes.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btae735},
pmid = {39661475},
issn = {1367-4811},
abstract = {MOTIVATION: Much of prokaryotic comparative genomics currently relies on two critical computational tasks: pangenome inference and core genome inference. Pangenome inference involves clustering genes from a set of genomes into gene families, enabling genome-wide association studies and evolutionary history analysis. The core genome represents gene families present in nearly all genomes and is required to infer a high-quality phylogeny. For species-level datasets, fast pangenome inference tools have been developed. However, tools applicable to more diverse datasets are currently slow and scale poorly.

RESULTS: Here, we introduce SCARAP, a program containing three modules for comparative genomics analyses: a fast and scalable pangenome inference module, a direct core genome inference module and a module for subsampling representative genomes. When benchmarked against existing tools, the SCARAP pan module proved up to an order of magnitude faster with comparable accuracy. The core module was validated by comparing its result against a core genome extracted from a full pangenome. The sample module demonstrated the rapid sampling of genomes with decreasing novelty. Applied to a dataset of over 31,000 Lactobacillales genomes, SCARAP showcased its ability to derive a representative pangenome. Finally, we applied the novel concept of gene fixation frequency to this pangenome, showing that Lactobacillales genes that are prevalent but rarely fixate in species often encode bacteriophage functions.

The SCARAP toolkit is publicly available at https://github.com/swittouck/scarap.

SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.},
}

@article {pmid39653491,
year = {2024},
author = {Armer, VJ and Kroll, E and Darino, M and Smith, DP and Urban, M and Hammond-Kosack, KE},
title = {Navigating the Fusarium species complex: Host-range plasticity and genome variations.},
journal = {Fungal biology},
volume = {128},
number = {8 Pt B},
pages = {2439-2459},
doi = {10.1016/j.funbio.2024.07.004},
pmid = {39653491},
issn = {1878-6146},
mesh = {*Fusarium/genetics/classification ; *Genome, Fungal ; *Host Specificity ; Animals ; Genetic Variation ; Humans ; Phylogeny ; Ecosystem ; Plants/microbiology ; Plant Diseases/microbiology ; },
abstract = {The Ascomycete genus Fusarium, first introduced by Link in 1809, currently consists of 431 species and 3558 unclassified isolates and hybrids (according to NCBI Taxonomy lists). Collectively, these fungi have diverse lifestyles and infection cycles exploiting a wide range of environments, hosts, ecological niches, and nutrient sources. Here, we carried out a pan-Fusarium species review to describe and explore the glamorous, and the less attractive niches, exploited by pathogenic and endophytic species. We survey species that infect plant, human, animal and/or invertebrate hosts, free-living non-pathogenic species dwelling in land, air or water-based natural ecosystems, through to those species that exploit human-modified environments or are cultivated in industrial production systems. Fully sequenced, assembled and annotated reference genomes are already available for 189 Fusarium species, many at chromosome scale. In addition, for some of the world's most important species extensive single species pangenomes or closely related formae speciales genome clusters are readily available. Previous comparative genomics studies have focussed on taxonomically restricted clusters of Fusarium species. We now investigate potential new relationships between these vastly contrasting Fusarium biologies, niches and environmental occupancies and the evolution of their respective genomes.},
}

*Fusarium/genetics/classification
*Genome, Fungal
*Host Specificity
Animals
Genetic Variation
Humans
Phylogeny
Ecosystem
Plants/microbiology
Plant Diseases/microbiology

@article {pmid39652592,
year = {2024},
author = {Ciccolella, S and Cozzi, D and Della Vedova, G and Kuria, SN and Bonizzoni, P and Denti, L},
title = {Differential quantification of alternative splicing events on spliced pangenome graphs.},
journal = {PLoS computational biology},
volume = {20},
number = {12},
pages = {e1012665},
doi = {10.1371/journal.pcbi.1012665},
pmid = {39652592},
issn = {1553-7358},
abstract = {Pangenomes are becoming a powerful framework to perform many bioinformatics analyses taking into account the genetic variability of a population, thus reducing the bias introduced by a single reference genome. With the wider diffusion of pangenomes, integrating genetic variability with transcriptome diversity is becoming a natural extension that demands specific methods for its exploration. In this work, we extend the notion of spliced pangenomes to that of annotated spliced pangenomes; this allows us to introduce a formal definition of Alternative Splicing (AS) events on a graph structure. To investigate the usage of graph pangenomes for the quantification of AS events across conditions, we developed pantas, the first pangenomic method for the detection and differential analysis of AS events from short RNA-Seq reads. A comparison with state-of-the-art linear reference-based approaches proves that pantas achieves competitive accuracy, making spliced pangenomes effective for conducting AS events quantification and opening future directions for the analysis of population-based transcriptomes.},
}

@article {pmid39648684,
year = {2024},
author = {MacNish, TR and Al-Mamun, HA and Bayer, PE and McPhan, C and Fernandez, CGT and Upadhyaya, SR and Liu, S and Batley, J and Parkin, IAP and Sharpe, AG and Edwards, D},
title = {Brassica Panache: A multi-species graph pangenome representing presence absence variation across forty-one Brassica genomes.},
journal = {The plant genome},
volume = {},
number = {},
pages = {e20535},
doi = {10.1002/tpg2.20535},
pmid = {39648684},
issn = {1940-3372},
support = {DP200100762//Australian Research Council/ ; DP210100296//Australian Research Council/ ; },
abstract = {Brassicas are an economically important crop species that provide a source of healthy oil and vegetables. With the rising population and the impact of climate change on agriculture, there is an increasing need to improve agronomically important traits of crops such as Brassica. The genomes of plant species have significant sequence presence absence variation (PAV), which is a source of genetic variation that can be used for crop improvement, and this species variation can be captured through the construction of pangenomes. Graph pangenomes are a recent reference format that represent the genomic variation with a species or population as alternate paths in a sequence graph. Graph pangenomes contain information on alignment, PAV, and annotation. Here we present the first multi-species graph pangenome for Brassica visualized with pangenome analyzer with chromosomal exploration (Panache).},
}

@article {pmid39644982,
year = {2024},
author = {Mertz, P and Hentgen, V and Boursier, G and Delon, J and Georgin-Lavialle, S},
title = {Current landscape of monogenic autoinflammatory actinopathies: A literature review.},
journal = {Autoimmunity reviews},
volume = {24},
number = {2},
pages = {103715},
doi = {10.1016/j.autrev.2024.103715},
pmid = {39644982},
issn = {1873-0183},
abstract = {Autoinflammatory diseases (AID) are conditions leading to a hyperactivation of innate immunity without any underlying infection, and may be poly- (e.g. Still's disease) or monogenic. The number of monogenic AID is continuously expanding, with the discovery of novel pathologies and pathophysiological mechanisms, facilitated in part by easier access to pangenomic sequencing. Actinopathies with autoinflammatory manifestations represent a newly emerging subgroup of AID, associated with defects in the regulation of actin cytoskeleton dynamics. These diseases typically manifest in the neonatal period and variably combine a primary immunodeficiency of varying severity, cytopenia (particularly thrombocytopenia), autoinflammatory manifestations primarily affecting the skin and digestive system, as well as atopic and autoimmune features. Diagnosis should be considered primarily when encountering an early-onset autoinflammatory skin and digestive disorder, along with a primary immunodeficiency and either thrombocytopenia or a bleeding tendency. Some of these diseases exhibit specific features, such as a risk of macrophage activation syndrome (MAS) or a predisposition to atopy or lymphoproliferation. The complete pathophysiology of these diseases is not yet fully understood, and further studies are required to elucidate the underlying mechanisms, which could guide therapeutic choices. In most cases, the severity of the conditions necessitates allogeneic marrow transplantation as a treatment option. In this review, we discuss these novel diseases, providing a practical approach based on the main associated biological abnormalities and specific clinical characteristics, with a special focus on the newly described actinopathies DOCK11 and ARPC5 deficiency. Nonetheless, genetic testing remains essential for definitive diagnosis, and various differential diagnoses must be considered.},
}

@article {pmid39641568,
year = {2024},
author = {Lian, S and Liu, Y and Hu, S and Shen, C and Ma, Y and Yin, P and He, Z},
title = {Genomic insights on cgMLST markers, drug resistance, and urease cluster of Proteus mirabilis strains.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0099224},
doi = {10.1128/spectrum.00992-24},
pmid = {39641568},
issn = {2165-0497},
abstract = {UNLABELLED: Proteus mirabilis, a significant pathogenic bacterium within the Enterobacteriaceae family, is widely distributed across various natural environments. This study conducted a genomic comparison analysis of 1,267 strains of P. mirabilis using extensive genome data from public databases. The objective was to elucidate the pan-genomic structure of P. mirabilis, revealing the composition and distribution of core and accessory gene families among different strains. Additionally, an attempt was made to construct a core genome multilocus sequence typing scheme specific to this species in order to enhance the precision of describing genetic diversity and evolutionary relationships. Furthermore, the study delved into the mechanisms of resistance of P. mirabilis to carbapenems and quinolones. Our findings underscore significant challenges posed by P. mirabilis in terms of antibiotic resistance, with widespread resistance observed particularly against beta-lactams and an increasing trend in resistance to carbapenems and quinolones. These results highlight the severity of P. mirabilis as a pathogen and underscore its rapid evolution and adaptability in developing resistance. This study aims to deepen our understanding of the antibiotic resistance of P. mirabilis, providing important insights for the development of future antimicrobial drugs, promoting effective treatment and control of this pathogen, and mitigating its threat to human health.

IMPORTANCE: The bacterium Proteus mirabilis is a common pathogenic bacterium that is known to cause a variety of human infections. The drug-resistant genes carried by P. mirabilis present a significant challenge to clinical treatment, particularly in regard to the organism's notable resistance to commonly used beta-lactam and quinolone drugs. Furthermore, the prevalence of the urease gene cluster of P. mirabilis at the urease gene level may be associated with the formation of kidney stones. The objective of the study is to analyze the bacterium's drug resistance, urease gene clusters, and gene distribution in genomes in order to facilitate the development of antimicrobial drugs and improve the treatment and control of P. mirabilis infections.},
}

@article {pmid39640918,
year = {2024},
author = {Baede, VO and Jlassi, O and Lesiczka, PM and Younsi, H and Jansen, HJ and Dachraoui, K and Segobola, J and Ben Said, M and Veneman, WJ and Dirks, RP and Sprong, H and Zhioua, E},
title = {Similarities between Ixodes ricinus and Ixodes inopinatus genomes and horizontal gene transfer from their endosymbionts.},
journal = {Current research in parasitology & vector-borne diseases},
volume = {6},
number = {},
pages = {100229},
pmid = {39640918},
issn = {2667-114X},
abstract = {The taxa Ixodes ricinus and Ixodes inopinatus are sympatric in Tunisia. The genetics underlying their morphological differences are unresolved. In this study, ticks collected in Jouza-Amdoun, Tunisia, were morphologically identified and sequenced using Oxford Nanopore Technologies. Three complete genome assemblies of I. inopinatus and three of I. ricinus with BUSCO scores of ∼98% were generated, including the reconstruction of mitochondrial genomes and separation of both alleles of the TRPA1, TROSPA and calreticulin genes. Deep sequencing allowed the first descriptions of complete bacterial genomes for "Candidatus Midichloria mitochondrii", Rickettsia helvetica and R. monacensis from North Africa, and the discovery of extensive integration of parts of the Spiroplasma ixodetis and "Ca. M. mitochondrii" into the nuclear genome of these ticks. Phylogenetic analyses of the mitochondrial genome, the nuclear genes, and symbionts showed differentiation between Tunisian and Dutch ticks, but high genetic similarities between Tunisian I. ricinus and I. inopinatus. Subtraction of the genome assemblies identified the presence of some unique sequences, which could not be confirmed when screening a larger batch of I. ricinus and I. inopinatus ticks using PCR. Our findings yield compelling evidence that I. inopinatus is genetically highly similar, if not identical, to sympatric I. ricinus. Defined morphological differences might be caused by extrinsic factors such as micro-climatic conditions or bloodmeal composition. Our findings support the existence of different lineages of I. ricinus as well of its symbionts/pathogens from geographically dispersed locations.},
}

@article {pmid39633035,
year = {2024},
author = {Rocha, BMO and Sabino, YNV and de Almeida, TC and Palacio, FB and Rotta, IS and Dias, VC and da Silva, VL and Diniz, CG and Azevedo, VAC and Brenig, B and Soares, SC and Paiva, AD and Medeiros, JD and Machado, ABF},
title = {Unlocking Probiotic Potential: Genomic Insights into Weissella paramesenteroides UFTM 2.6.1.},
journal = {Probiotics and antimicrobial proteins},
volume = {},
number = {},
pages = {},
pmid = {39633035},
issn = {1867-1314},
abstract = {Weissella, a genus of lactic acid bacteria, has diverse beneficial attributes including probiotic activity and biotechnological applications. Therefore, the investigation of the Weissella genus has garnered growing interest. In this study, we sequenced the complete genome of Weissella paramesenteroides UFTM 2.6.1 isolated from unpasteurized cow's milk from the Triângulo Mineiro region and performed probiogenomic analyses. Taxonomic characterization confirmed the identity of W. paramesenteroides. The genome comprises 1926 protein-coding genes, mainly related to cell metabolism, information storage and processing, and cellular processes and signaling. Ninety-nine unique genes associated with probiotic functions were identified in the genome of W. paramesenteroides UFTM 2.6.1, including genes involved in stress response, bacterial persistence in the gastrointestinal tract, and biosynthesis of vitamins. In silico analysis of bacteriocin-related genes identified Pediocin, and subsequent in vitro testing confirmed that W. paramesenteroides UFTM 2.6.1 exhibits antimicrobial activity against Listeria spp. Genomic characterization revealed the presence of the replicon pLCK4 and four prophage regions, one of which was intact. Moreover, no CRISPR-Cas array or associated Cas proteins were found, along with an absence of resistance and virulence genes, suggesting a safety aspect of the evaluated strain. Pan-genome analysis unveiled 204 exclusive genes in the genome of W. paramesenteroides UFTM 2.6.1, which includes metabolism and stress-associated genes. In general, the results indicate probiotic potential of W. paramesenteroides UFTM 2.6.1. Further studies are required to ensure the safety and beneficial effects of this bacterium in vivo, aiming for future applications in the food industry and animal and human medicine.},
}

@article {pmid39630499,
year = {2024},
author = {Matlock, W and Shaw, LP and Stoesser, N},
title = {Global genomic epidemiology of bla GES-5 carbapenemase-associated integrons.},
journal = {Microbial genomics},
volume = {10},
number = {12},
pages = {},
pmid = {39630499},
issn = {2057-5858},
mesh = {*Integrons/genetics ; *beta-Lactamases/genetics ; *Plasmids/genetics ; *Bacterial Proteins/genetics ; Humans ; *Pseudomonas aeruginosa/genetics/drug effects ; Anti-Bacterial Agents/pharmacology ; Pseudomonas Infections/microbiology/epidemiology ; Genome, Bacterial ; },
abstract = {Antimicrobial resistance (AMR) gene cassettes comprise an AMR gene flanked by short recombination sites (attI and attC or attC and attC). Integrons are genetic elements able to capture, excise and shuffle these cassettes, providing 'adaptation on demand', and can be found on both chromosomes and plasmids. Understanding the patterns of integron diversity may help to understand the epidemiology of AMR genes. As a case study, we examined the clinical resistance gene bla GES-5, an integron-associated class A carbapenemase first reported in Greece in 2004 and since observed worldwide, which to our knowledge has not been the subject of a previous global analysis. Using a dataset comprising all de-duplicated NCBI contigs containing bla GES-5 (n=104), we developed a pangenome graph-based workflow to characterize and cluster the diversity of bla GES-5-associated integrons. We demonstrate that bla GES-5-associated integrons on plasmids are different to those on chromosomes. Chromosomal integrons were almost all identified in Pseudomonas aeruginosa ST235, with a consistent gene cassette content and order. We observed instances where insertion sequence IS110 disrupted attC sites, which might immobilize the gene cassettes and explain the conserved integron structure despite the presence of intI1 integrase promoters, which would typically facilitate capture or excision and rearrangement. The plasmid-associated integrons were more diverse in their gene cassette content and order, which could be an indication of greater integrase activity and 'shuffling' of integrons on plasmids.},
}

*Integrons/genetics
*beta-Lactamases/genetics
*Plasmids/genetics
*Bacterial Proteins/genetics
Humans
*Pseudomonas aeruginosa/genetics/drug effects
Anti-Bacterial Agents/pharmacology
Pseudomonas Infections/microbiology/epidemiology
Genome, Bacterial

@article {pmid39628721,
year = {2024},
author = {Anjum, A and Tabassum, J and Islam, S and Hassan, AKMI and Jabeen, I and Shuvo, SR},
title = {Deciphering the genomic character of the multidrug-resistant Staphylococcus aureus from Dhaka, Bangladesh.},
journal = {AIMS microbiology},
volume = {10},
number = {4},
pages = {833-858},
pmid = {39628721},
issn = {2471-1888},
abstract = {Staphylococcus aureus is one of the leading agents of nosocomial and community-acquired infections. In this study, we explored the genomic characterization of eight methicillin-resistant clinical isolates of S. aureus from Dhaka, Bangladesh. Notably, all strains were resistant to penicillin, cephalosporins, and monobactams, with partial susceptibility to meropenem and complete susceptibility to amikacin, vancomycin, and tigecycline antibiotics. The strains were found to have an average genome size of 2.73 Mbp and an average of 32.64% GC content. Multi-locus sequence typing analysis characterized the most predominant sequence type as ST361, which belongs to the clonal complex CC361. All isolates harbored the mecA gene, often linked to SCCmec_type IV variants. Multidrug resistance was attributed to efflux pumps NorA, NorC, SdrM, and LmrS alongside genes encoding beta-lactamase BlaZ and factors like ErmC and MepA. Additionally, virulence factors including adsA, sdrC, cap8D, harA, esaA, essC, isdB, geh, and lip were commonly identified. Furthermore, genes associated with heme uptake and clumping were present, highlighting their roles in S. aureus colonization and pathogenesis. Nine secondary metabolite biosynthetic gene clusters were found, of which six were common in all the strains. Numerous toxin-antitoxin systems were predicted, with ParE and ParB-like nuclease domains found to be the most prevalent toxin and antitoxin, respectively. Pan-genome analysis revealed 2007 core genes and 229 unique genes in the studied strains. Finally, the phylogenomic analysis showed that most Bangladeshi strains were grouped into two unique clades. This study provides a genomic and comparative insight into the multidrug resistance and pathogenicity of S. aureus strains, which will play a crucial role in the future antibiotic stewardship of Bangladesh.},
}

@article {pmid39628536,
year = {2024},
author = {Wang, J and Liang, X and Zhang, W and Khalil, A and Wu, Y and Liu, S and Tahir Ul Qamar, M and Wang, X and Guo, J},
title = {Comparative genomic profiling of CBFs pan-gene family in five yellowhorn cultivars and functional identification of Xg11_CBF11.},
journal = {Frontiers in plant science},
volume = {15},
number = {},
pages = {1481358},
pmid = {39628536},
issn = {1664-462X},
abstract = {C-repeat binding factor (CBF) transcription factors can activate the expression of a series of cold regulation-related genes, thereby improving the cold resistance of plants. However, no detailed information is known about the biological functions of CBF proteins in yellowhorn (Xanthoceras sorbifolium). In this study, a total of 59 CBF gene family members were identified in five yellowhorn cultivars (WF18, Zhongshi 4, Jinguanxipei 2021, Zhong Guan NO.2, and XsoG11), revealing their intraspecific structural and functional diversity, with 8 core genes present in all cultivars. Phylogenetic and motif analyses highlighted conserved features and species-specific adaptations. Gene duplication events revealed that tandem duplicates are major factors involved in the expansion of this gene family in yellowhorn. Expression profiling under stress conditions demonstrated the involvement of these genes in stress responses. Of particular interest was Xg11_CBF11, which showed strong induction by low-temperature stress. Overexpression of Xg11_CBF11 in Arabidopsis thaliana was performed to validate its cold resistance function. The wild-type and T2 transgenic A. thaliana plants were subjected to low-temperature stress at 4°C for 0, 24, and 48 h, and physiological indexes related to antioxidant enzyme activity, photosynthesis, and cell membrane permeability were determined by comparative test. The results were as follows: the POD and SOD activities of transgenic lines were significantly higher than those of wild-type lines, indicating Xg11_CBF11 improved the adaptability of A. thaliana to low-temperature; The increase of relative conductivity and malondialdehyde, the decrease of chlorophyll content in transgenic lines were smaller than those of wild-type lines, indicating Xg11_CBF11 enhanced the resistance of A. thaliana to low-temperature stress. These results implied that Xg11_CBF11 has a positive regulatory effect on A. thaliana 's response to low-temperature stress.},
}

@article {pmid39627700,
year = {2024},
author = {Hoque, MN and Mannan, ABA and Hossian, A and Faisal, GM and Hossain, MA and Sultana, M},
title = {Arsenotrophic Achromobacter aegrifaciens strains isolated from arsenic contaminated tubewell water and soil sources shared similar genomic potentials.},
journal = {BMC microbiology},
volume = {24},
number = {1},
pages = {518},
pmid = {39627700},
issn = {1471-2180},
mesh = {*Achromobacter/genetics/isolation & purification/classification/metabolism ; *Soil Microbiology ; *Arsenic/metabolism ; *Phylogeny ; *Genome, Bacterial/genetics ; *Biodegradation, Environmental ; Whole Genome Sequencing ; Soil Pollutants/metabolism ; Bangladesh ; Water Pollutants, Chemical/metabolism ; Genomics ; },
abstract = {BACKGROUND: Arsenic (As), found in diverse ecosystems, poses major public health risks in various parts of the world. Arsenotrophic bacteria in contaminated environments help reduce toxicity by converting arsenite (AsIII) to less harmful arsenate (AsV). We assumed that Achromobacter aegrifaciens strains from As-contaminated tubewell water and soil would share similar genomic characteristics associated with arsenic detoxification and bioremediation. To investigate this, we employed both culture-dependent and culture-independent viz. whole genome sequencing (WGS) methods to thoroughly elucidate the phenotypic and genotypic features of two A. aegrifaciens strains isolated from As-contaminated tubewell water (BAW48) and soil (BAS32) samples collected in the Bogura district of Bangladesh.

RESULTS: Both BAW48 and BAS32 isolates demonstrated As(III) oxidation in the KMNO4 test, which was corroborated by molecular analysis confirming the presence of aioA and arsB genes in both strains. These strains were found to be phylogenetically related to many strains of Achromobacter spp., isolated from biological inorganic reactors, environmental soils, sediments and human clinical samples across diverse geographical regions. Moreover, both strains possessed distinct heavy metal resistance genes conferring resistance to Co, Zn, Cu, Cd, Hg, As, and Cr. Three As gene clusters such as As(III) oxidizing aioBA, As(III) reducing arsRCDAB and the MMA(III) oxidizing ars resistance gene (arsHCsO) cluster were predicted in both genomes of A. aegrifaciens. Further genomic analyses revealed similar profiles in both strains, with mobile genetic elements, antimicrobials and heavy metal resistance genes, virulence genes, and metabolic features. Pangenome and synteny analysis showed that the two genomes are evolutionary distinct from other strains, but closely related to one another.

CONCLUSION: The genomic data confirmed that A. aegrifaciens strains can oxidize As(III) and detoxify heavy metals like As, suggesting their potential for As detoxification and bioremediation. These findings align with our assumption and provide a basis for developing sustainable solutions for bioremediation efforts in As-contaminated environments.},
}

*Achromobacter/genetics/isolation & purification/classification/metabolism
*Soil Microbiology
*Arsenic/metabolism
*Phylogeny
*Genome, Bacterial/genetics
*Biodegradation, Environmental
Whole Genome Sequencing
Soil Pollutants/metabolism
Bangladesh
Water Pollutants, Chemical/metabolism
Genomics

@article {pmid39627497,
year = {2024},
author = {Jones, DAB and Rybak, K and Hossain, M and Bertazzoni, S and Williams, A and Tan, KC and Phan, HTT and Hane, JK},
title = {Repeat-induced point mutations driving Parastagonospora nodorum genomic diversity are balanced by selection against non-synonymous mutations.},
journal = {Communications biology},
volume = {7},
number = {1},
pages = {1614},
pmid = {39627497},
issn = {2399-3642},
support = {CUR00023//Grains Research and Development Corporation (Grains Research & Development Corporation)/ ; },
mesh = {*Ascomycota/genetics ; *Point Mutation ; *Genome, Fungal ; Plant Diseases/microbiology ; Polymorphism, Single Nucleotide ; Triticum/microbiology/genetics ; Genetic Variation ; Fungal Proteins/genetics/metabolism ; Repetitive Sequences, Nucleic Acid/genetics ; Selection, Genetic ; },
abstract = {Parastagonospora nodorum is necrotrophic fungal pathogen of wheat with significant genomic resources. Population-level pangenome data for 173 isolates, of which 156 were from Western Australia (WA) and 17 were international, were examined for overall genomic diversity and effector gene content. A heterothallic core population occurred across all regions of WA, with asexually-reproducing clonal clusters in dryer northern regions. High potential for SNP diversity in the form of repeat-induced point mutation (RIP)-like transitions, was observed across the genome, suggesting widespread 'RIP-leakage' from transposon-rich repetitive sequences into non-repetitive regions. The strong potential for RIP-like mutations was balanced by negative selection against non-synonymous SNPs, that was observed within protein-coding regions. Protein isoform profiles of known effector loci (SnToxA, SnTox1, SnTox3, SnTox267, and SnTox5) indicated low-levels of non-synonymous and high-levels of silent RIP-like mutations. Effector predictions identified 186 candidate secreted predicted effector proteins (CSEPs), 69 of which had functional annotations and included confirmed effectors. Pangenome-based effector isoform profiles across WA were distinct from global isolates and were conserved relative to population structure, and may enable new approaches for monitoring crop disease pathotypes.},
}

*Ascomycota/genetics
*Point Mutation
*Genome, Fungal
Plant Diseases/microbiology
Polymorphism, Single Nucleotide
Triticum/microbiology/genetics
Genetic Variation
Fungal Proteins/genetics/metabolism
Repetitive Sequences, Nucleic Acid/genetics
Selection, Genetic

@article {pmid39626271,
year = {2024},
author = {Parmigiani, L and Garrison, E and Stoye, J and Marschall, T and Doerr, D},
title = {Panacus: fast and exact pangenome growth and core size estimation.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btae720},
pmid = {39626271},
issn = {1367-4811},
abstract = {MOTIVATION: Using a single linear reference genome poses a limitation to exploring the full genomic diversity of a species. The release of a draft human pangenome underscores the increasing relevance of pangenomics to overcome these limitations. Pangenomes are commonly represented as graphs, which can represent billions of base pairs of sequence. Presently, there is a lack of scalable software able to perform key tasks on pangenomes, such as quantifying universally shared sequence across genomes (the core genome) and measuring the extent of genomic variability as a function of sample size (pangenome growth).

RESULTS: We introduce Panacus (pangenome-abacus), a tool designed to rapidly perform these tasks and visualize the results in interactive plots. Panacus can process GFA files, the accepted standard for pangenome graphs, and is able to analyze a human pangenome graph with 110 million nodes in less than one hour.

Panacus is implemented in Rust and is published as Open Source software under the MIT license. The source code and documentation are available at https://github.com/marschall-lab/panacus. Panacus can be installed via Bioconda at https://bioconda.github.io/recipes/panacus/README.html.},
}

@article {pmid39621536,
year = {2024},
author = {Jayakodi, M and Shim, H and Mascher, M},
title = {What Are We Learning from Plant Pangenomes?.},
journal = {Annual review of plant biology},
volume = {},
number = {},
pages = {},
doi = {10.1146/annurev-arplant-090823-015358},
pmid = {39621536},
issn = {1545-2123},
abstract = {A single reference genome does not fully capture species diversity. By contrast, a pangenome incorporates multiple genomes to capture the entire set of nonredundant genes in a given species, along with its genome diversity. New sequencing technologies enable researchers to produce multiple high-quality genome sequences and catalog diverse genetic variations with better precision. Pangenomic studies have detected structural variants in plant genomes, dissected the genetic architecture of agronomic traits, and helped unravel molecular underpinnings and evolutionary origins of plant phenotypes. The pangenome concept has further evolved into a so-called superpangenome that includes wild relatives within a genus or clade and shifted to graph-based reference systems. Nevertheless, building pangenomes and representing complex structural variants remain challenging in many crops. Standardized computing pipelines and common data structures are needed to compare and interpret pangenomes. The growing body of plant pangenomics data requires new algorithms, huge data storage capacity, and training to help researchers and breeders take advantage of newly discovered genes and genetic variants.},
}

@article {pmid39618494,
year = {2024},
author = {Negro, G and Semeraro, M and Cook, PR and Marenduzzo, D},
title = {A unified-field theory of genome organization and gene regulation.},
journal = {iScience},
volume = {27},
number = {12},
pages = {111218},
pmid = {39618494},
issn = {2589-0042},
abstract = {Our aim is to predict how often genic and non-genic promoters fire within a cell. We first review a parsimonious pan-genomic model for genome organization and gene regulation, where transcription rate is determined by proximity in 3D space of promoters to clusters containing appropriate factors and RNA polymerases. This model reconciles conflicting results indicating that regulatory mammalian networks are both simple (as over-expressing just 4 transcription factors switches cell state) and complex (as genome-wide association studies show phenotypes like cell type are determined by thousands of loci rarely encoding such factors). We then present 3D polymer simulations, and a proximity formula based on our biological model that enables prediction of transcriptional activities of all promoters in three human cell types. This simple fitting-free formula contains just one variable (distance on the genetic map to the nearest active promoter), and we suggest it can in principle be applied to any organism.},
}

@article {pmid39615045,
year = {2024},
author = {Valentino, V and De Filippis, F and Marotta, R and Pasolli, E and Ercolini, D},
title = {Genomic features and prevalence of Ruminococcus species in humans are associated with age, lifestyle, and disease.},
journal = {Cell reports},
volume = {43},
number = {12},
pages = {115018},
doi = {10.1016/j.celrep.2024.115018},
pmid = {39615045},
issn = {2211-1247},
abstract = {The genus Ruminococcus is dominant in the human gut, but higher levels of some species, such as R. gnavus, R. torques, and R. bromii, have been linked to health or disease. In this study, we analyzed >9,000 Ruminococcus metagenome-assembled genomes (MAGs) reconstructed from >5,000 subjects and revealed significant links between the prevalence of some species/subspecies and geographic origin, age, lifestyle, and disease, with subspecies prevalent in specific subpopulations showing divergent metabolic potential. Furthermore, Ruminococcus species from Lachnospiraceae encoded for carbohydrate-active enzymes (CAZy) potentially involved in the metabolism of human N- and O-glycans, whereas those from Oscillospiraceae appear to be more adapted toward fiber metabolism. These new findings contribute to elucidating the potential functional role of Ruminococcus in specific lifestyles and diseases and to decipher the diversity and the adaptation of members of this genus to the human gut.},
}

@article {pmid39613891,
year = {2024},
author = {Foysal, MJ and Momtaz, F and Chowdhury, AMMA and Tanni, AA and Salauddin, A and Hasan, MZ and Mina, SA and Sultana, N and Biswas, SK and Islam, K and Tay, A and Mannan, A},
title = {Whole-Genome Analysis of Multidrug-Resistant Klebsiella pneumoniae Kp04 Reveals Distinctive Antimicrobial and Arsenic-Resistance Genomic Features: A Case Study from Bangladesh.},
journal = {Current microbiology},
volume = {82},
number = {1},
pages = {22},
pmid = {39613891},
issn = {1432-0991},
support = {504-CU-RPC-2023-24/34/2024//Research and Publication Cell, University of Chittagong/ ; },
mesh = {*Klebsiella pneumoniae/genetics/drug effects/isolation & purification ; Bangladesh ; *Drug Resistance, Multiple, Bacterial/genetics ; *Anti-Bacterial Agents/pharmacology ; Humans ; *Genome, Bacterial ; *Whole Genome Sequencing ; *Klebsiella Infections/microbiology ; Microbial Sensitivity Tests ; Arsenic/pharmacology ; beta-Lactamases/genetics ; Genomics ; },
abstract = {Multidrug-resistant bacteria, particularly extended-spectrum-beta-lactamase-producing (ESBL) bacteria, pose a significant global public health challenge. Klebsiella pneumoniae (KPN) is frequently implicated in cases of this resistance. This study aimed to investigate the presence of drug and metal resistance genes in clinical K. pneumoniae isolate Kp04 and comparative genomics of clinical KPN isolates characterized from Bangladesh. A total of 12 isolates were collected. Disk-diffusion assay showed that all five isolates were resistant to 14 out of 21 tested antibiotics and sensitive to only three-tigecycline, imipenem, and meropenem. KPN Kp04 was positive for both blaSHV and blaCTX-M ESBL genes in PCR. All five isolates produced PCR amplicons of the correct size for ampicillin (ampC), tetracycline (tetC), fluoroquinolone (qnrS), and aminoglycoside (aadA) resistance genes. The whole genome of Kp04 was sequenced using the MiSeq Platform (V3 kit, 2 × 300 cycles). We utilized different databases to detect Antibiotic-Resistant Genes (ARGs), virulence factor genes (VFGs), and genomic functional features of the Kp04 strain. Whole-genome sequencing identified 75 ESBL, virulence, and multiple drug-resistant (MDR) genes including blaSHV, tetA, oqxA, oqxB, aadA, sul1-5, and mphA in KPN Kp04 isolate. Pan-genomic analysis of 43 Bangladeshi KPN isolates showed similarities between Dhaka and Chattogram isolates regarding virulence and antibiotic-resistant genes. Our results indicate the transmission of similar virulent KPN strains in Dhaka and Chattogram. This study would provide valuable information about drug sensitivity, antibiotic, and metal resistance features of K. pneumoniae circulated among hospitalized patients in Bangladeshi megacities.},
}

*Klebsiella pneumoniae/genetics/drug effects/isolation & purification
Bangladesh
*Drug Resistance, Multiple, Bacterial/genetics
*Anti-Bacterial Agents/pharmacology
Humans
*Genome, Bacterial
*Whole Genome Sequencing
*Klebsiella Infections/microbiology
Microbial Sensitivity Tests
Arsenic/pharmacology
beta-Lactamases/genetics
Genomics

@article {pmid39611087,
year = {2024},
author = {Aziz, T and Naveed, M and Shabbir, MA and Sarwar, A and Naseeb, J and Zhao, L and Yang, Z and Cui, H and Lin, L and Albekairi, TH},
title = {Unveiling the whole genomic features and potential probiotic characteristics of novel Lactiplantibacillus plantarum HMX2.},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1504625},
pmid = {39611087},
issn = {1664-302X},
abstract = {This study investigates the genomic features and probiotic potential of Lactiplantibacillus plantarum HMX2, isolated from Chinese Sauerkraut, using whole-genome sequencing (WGS) and bioinformatics for the first time. This study also aims to find genetic diversity, antibiotic resistance genes, and functional capabilities to help us better understand its food safety applications and potential as a probiotic. L. plantarum HMX2 was cultured, and DNA was extracted for WGS. Genomic analysis comprised average nucleotide identity (ANI) prediction, genome annotation, pangenome, and synteny analysis. Bioinformatics techniques were used to identify CoDing Sequences (CDSs), transfer RNA (tRNA) and ribosomal RNA (rRNA) genes, and antibiotic resistance genes, as well as to conduct phylogenetic analysis to establish genetic diversity and evolution. The study found a significant genetic similarity (99.17% ANI) between L. plantarum HMX2 and the reference strain. Genome annotation revealed 3,242 coding sequences, 65 tRNA genes, and 16 rRNA genes. Significant genetic variety was found, including 25 antibiotic resistance genes. A phylogenetic study placed L. plantarum HMX2 among closely related bacteria, emphasizing its potential for probiotic and food safety applications. The genomic investigation of L. plantarum showed essential genes, including plnJK and plnEF, which contribute to antibacterial action against foodborne pathogens. Furthermore, genes such as MurA, Alr, and MprF improve food safety and probiotic potential by promoting bacterial survival under stress conditions in food and the gastrointestinal tract. This study introduces the new genomic features of L. plantarum HMX2 about specific genetics and its possibility of relevant uses in food security and technologies. These findings of specific genes involved in antimicrobial activity provide fresh possibilities for exploiting this strain in forming probiotic preparations and food preservation methods. The future research should focus on the experimental validation of antibiotic resistance genes, comparative genomics to investigate functional diversity, and the development of novel antimicrobial therapies that take advantage of L. plantarum's capabilities.},
}

@article {pmid39609363,
year = {2024},
author = {Xu, S and Akhatayeva, Z and Liu, J and Feng, X and Yu, Y and Badaoui, B and Esmailizadeh, A and Kantanen, J and Amills, M and Lenstra, JA and Johansson, AM and Coltman, DW and Liu, GE and Curik, I and Orozco-terWengel, P and Paiva, SR and Zinovieva, NA and Zhang, L and Yang, J and Liu, Z and Wang, Y and Yu, Y and Li, M},
title = {Genetic advancements and future directions in ruminant livestock breeding: from reference genomes to multiomics innovations.},
journal = {Science China. Life sciences},
volume = {},
number = {},
pages = {},
pmid = {39609363},
issn = {1869-1889},
abstract = {Ruminant livestock provide a rich source of products, such as meat, milk, and wool, and play a critical role in global food security and nutrition. Over the past few decades, genomic studies of ruminant livestock have provided valuable insights into their domestication and the genetic basis of economically important traits, facilitating the breeding of elite varieties. In this review, we summarize the main advancements for domestic ruminants in reference genome assemblies, population genomics, and the identification of functional genes or variants for phenotypic traits. These traits include meat and carcass quality, reproduction, milk production, feed efficiency, wool and cashmere yield, horn development, tail type, coat color, environmental adaptation, and disease resistance. Functional genomic research is entering a new era with the advancements of graphical pangenomics and telomere-to-telomere (T2T) gap-free genome assembly. These advancements promise to improve our understanding of domestication and the molecular mechanisms underlying economically important traits in ruminant livestock. Finally, we provide new perspectives and future directions for genomic research on ruminant genomes. We suggest how ever-increasing multiomics datasets will facilitate future studies and molecular breeding in livestock, including the potential to uncover novel genetic mechanisms underlying phenotypic traits, to enable more accurate genomic prediction models, and to accelerate genetic improvement programs.},
}

@article {pmid39607778,
year = {2024},
author = {Li, H},
title = {BWT construction and search at the terabase scale.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btae717},
pmid = {39607778},
issn = {1367-4811},
abstract = {MOTIVATION: Burrows-Wheeler Transform (BWT) is a common component in full-text indices. Initially developed for data compression, it is particularly powerful for encoding redundant sequences such as pangenome data. However, BWT construction is resource intensive and hard to be parallelized, and many methods for querying large full-text indices only report exact matches or their simple extensions. These limitations have hampered the biological applications of full-text indices.

RESULTS: We developed ropebwt3 for efficient BWT construction and query. Ropebwt3 indexed 320 assembled human genomes in 65 hours and indexed 7.3 terabases of commonly studied bacterial assemblies in 26 days. This was achieved using up to 170 gigabytes of memory at the peak without working disk space. Ropebwt3 can find maximal exact matches and inexact alignments under affine-gap penalties, and can retrieve similar local haplotypes matching a query sequence. It demonstrates the feasibility of full-text indexing at the terabase scale.

https://github.com/lh3/ropebwt3.},
}

@article {pmid39606685,
year = {2024},
author = {Mohabati, R and Rezaei, R and Mohajel, N and Ranjbar, MM and Samimi-Rad, K and Azadmanesh, K and Roohvand, F},
title = {Generation of Optimized Consensus Sequences for Hepatitis C virus (HCV) Envelope 2 Glycoprotein (E2) by a Modified Algorithm: Implication for a Pan-genomic HCV Vaccine.},
journal = {Avicenna journal of medical biotechnology},
volume = {16},
number = {4},
pages = {268-278},
pmid = {39606685},
issn = {2008-2835},
abstract = {BACKGROUND: Despite the success of "direct-acting antivirals" in treating Hepatitis C Virus (HCV) infection, invention of a preventive HCV vaccine is crucial for global elimination of the virus. Recent data indicated the importance of the induction of Pangenomic neutralizing Antibodies (PnAbs) against heterogenic HCV Envelope 2(E2), the cellular receptor binding antigen, by any HCV vaccine candidate. To overcome HCVE2 heterogeneity, "generation of consensus HCVE2 sequences" is proposed. However, Consensus Sequence (CS) generating algorithms such as "Threshold" and "Majority" have certain limitations including "Threshold-rigidity" which leads to induction of undefined residues and insensitivity of the "Majority" towards the "evolutionary cost of residual substitutions".

METHODS: Herein, first a modification to the "Majority" algorithm was introduced by incorporating BLOSUM matrices. Secondly, the HCVE2 sequences generated by the "Fitness" algorithm (using 1698 sequences from genotypes 1, 2, and 3) was compared with those generated by the "Majority" and "Threshold" algorithms using several in silico tools.

RESULTS: Results indicated that only "Fitness" provided completely defined, gapless HCVE2s for all genotypes/subtypes, while considered the evolutionary cost of amino acid replacements (main "Majority/Threshold" limitations) by substitution of several residues within the generated consensuses. Moreover, "Fitness-generated HCVE2 CSs" were superior for antigenic/immunogenic characteristics as an antigen, while their positions within the phylogenetic trees were still preserved.

CONCLUSION: "Fitness" algorithm is capable of generating superior/optimum HCVE2 CSs for inclusion in a pan-genomic HCV vaccine and can be similarly used in CS generation for other highly variable antigens from other heterogenic pathogens.},
}

@article {pmid39606674,
year = {2024},
author = {Zhang, C and Li, H and Yin, J and Han, Z and Liu, X and Chen, Y},
title = {Pan-genome wide identification and analysis of the SAMS gene family in sunflowers (Helianthus annuus L.) revealed their intraspecies diversity and potential roles in abiotic stress tolerance.},
journal = {Frontiers in plant science},
volume = {15},
number = {},
pages = {1499024},
pmid = {39606674},
issn = {1664-462X},
abstract = {INTRODUCTION: S-adenosylmethionine (SAM), a key molecule in plant biology, plays an essential role in stress response and growth regulation. Despite its importance, the SAM synthetase (SAMS) gene family in sunflowers (Helianthus annuus L.) remains poorly understood.

METHODS: In this study, the SAMS genes were identified from the sunflower genome. Subsequently, the protein properties, gene structure, chromosomal location, cis-acting elements, collinearity, and phylogeny of the SAMS gene family were analyzed by bioinformatic methods. Finally, the expression patterns of SAMS genes in different tissues, under different hormonal treatment and abiotic stress were analyzed based on transcriptome data and qRT-PCR.

RESULTS: This study identified 58 SAMS genes across nine cultivated sunflower species, which were phylogenetically classified into seven distinct subgroups. Physicochemical properties and gene structure analysis showed that the SAMS genes are tightly conserved between cultivars. Collinearity analysis revealed segmental duplications as the primary driver of gene family expansion. The codon usage bias analysis suggested that natural selection substantially shapes the codon usage patterns of sunflower SAMS genes, with a bias for G/C-ending high-frequency codons, particularly encoding glycine, leucine, and arginine. Analysis of the cis-regulatory elements in promoter regions, implied their potential roles in stress responsiveness. Differential expression patterns for HanSAMS genes were observed in different tissues as well as under hormone treatment or abiotic stress conditions by analyzing RNA-seq data from previous studies and qRT-PCR data in our current study. The majority of genes demonstrated a robust response to BRA and IAA treatments in leaf tissues, with no significant expression change observed in roots, suggesting the response of HanSAMS genes to hormones is tissue-specific. Expression analyses under abiotic stresses demonstrated diverse expression profiles of HanSAMS genes, with HanSAMS5 showing significant upregulation in response to both drought and salt stresses.

DISCUSSION: This comprehensive genomic and expression analysis provides valuable insights into the SAMS gene family in sunflowers, laying a robust foundation for future functional studies and applications in crop improvement for stress resilience.},
}

@article {pmid39606487,
year = {2024},
author = {Depuydt, L and Renders, L and de Vyver, SV and Veys, L and Gagie, T and Fostier, J},
title = {b-move: Faster Lossless Approximate Pattern Matching in a Run-Length Compressed Index.},
journal = {Research square},
volume = {},
number = {},
pages = {},
doi = {10.21203/rs.3.rs-5367343/v1},
pmid = {39606487},
issn = {2693-5015},
abstract = {Background : Due to the increasing availability of high-quality genome sequences, pan-genomes are gradually replacing single consensus reference genomes in many bioinformatics pipelines to better capture genetic diversity. Traditional bioinformatics tools using the FM-index face memory limitations with such large genome collections. Recent advancements in run-length compressed indices like Gagie et al.'s r-index and Nishimoto and Tabei's move structure, alleviate memory constraints but focus primarily on backward search for MEM-finding. Arakawa et al.'s br-index initiates complete approximate pattern matching using bidirectional search in run-length compressed space, but with significant computational overhead due to complex memory access patterns. Results : We introduce b-move, a novel bidirectional extension of the move structure, enabling fast, cache-efficient, lossless approximate pattern matching in run-length compressed space. It achieves bidirectional character extensions up to 7 times faster than the br-index, closing the performance gap with FM-index-based alternatives. For locating occurrences, b-move performs φ and φ inverse operations up to 7 times faster than the br-index. At the same time, it maintains the favorable memory characteristics of the br-index, for example, all available complete E. coli genomes on NCBI's RefSeq collection can be compiled into a b-move index that fits into the RAM of a typical laptop. Conclusions : b-move proves practical and scalable for pan-genome indexing and querying. We provide a C++ implementation of b-move, supporting efficient lossless approximate pattern matching including locate functionality, available at https://github.com/biointec/b-move under the AGPL-3.0 license.},
}

@article {pmid39605465,
year = {2024},
author = {Qin, C and Lypaczewski, P and Sayeed, MA and Cuénod, AC and Brinkley, L and Creasy-Marrazzo, A and Cato, ET and Islam, K and Ul Khabir, MI and Bhuiyan, MTR and Begum, Y and Qadri, F and Khan, AI and Nelson, EJ and Shapiro, BJ},
title = {Vibrio cholerae lineage and pangenome diversity varies geographically across Bangladesh over one year.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.11.12.623281},
pmid = {39605465},
issn = {2692-8205},
abstract = {Cholera is a diarrhoeal disease caused by Vibrio cholerae . It remains a major public health challenge in the endemic region around the Bay of Bengal. Over decadal time scales, one lineage typically dominates the others and spreads in global pandemic waves. However, it remains unclear to what extent diverse lineages co-circulate during a single outbreak season. Defining the pool of diversity during finer time scales is important because the selective pressures that impact V. cholerae - namely antibiotics and phages - are dynamic on these time scales. To study the nationwide diversity of V. cholerae , we long-read sequenced 273 V. cholerae genomes from seven hospitals over one year (2018) in Bangladesh. Four major V. cholerae lineages were identified: known lineages BD-1, BD-2a, and BD-2b, and a novel lineage that we call BD-3. In 2022, BD-1 caused a large cholera outbreak in Dhaka, apparently outcompeting BD-2 lineages. We show that, in 2018, BD-1 was already dominant in the five northern regions, including Dhaka, consistent with an origin from India in the north. By contrast, we observed a higher diversity of lineages in the two southern regions near the coast. The four lineages differed in pangenome content, including integrative and conjugative elements (ICEs) and genes involved in resistance to bacteriophages and antibiotics. Notably, BD-2a lacked an ICE and is predicted to be more sensitive to phages and antibiotics, but nevertheless persisted throughout the year-long sampling period. Genes associated with antibiotic resistance in V. cholerae from Bangladesh in 2006 were entirely absent from all lineages in 2018-19, suggesting shifting costs and benefits of encoding these genes. Together, our results highlight the dynamic nature of the V. cholerae pangenome and the geographic structure of its lineage diversity.},
}

@article {pmid39605388,
year = {2024},
author = {Versoza, CJ and Ehmke, EE and Jensen, JD and Pfeifer, SP},
title = {Characterizing the rates and patterns of de novo germline mutations in the aye-aye (Daubentonia madagascariensis).},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.11.08.622690},
pmid = {39605388},
issn = {2692-8205},
abstract = {Given the many levels of biological variation in mutation rates observed to date in primates - spanning from species to individuals to genomic regions - future steps in our understanding of mutation rate evolution will be aided by both a greater breadth of species coverage across the primate clade, but also by a greater depth as afforded by an evaluation of multiple trios within individual species. In order to help bridge these gaps, we here present an analysis of a species representing one of the most basal splits on the primate tree (aye-ayes), combining whole-genome sequencing of seven parent-offspring trios from a three-generation pedigree with a novel computational pipeline that takes advantage of recently developed pan-genome graphs, thereby circumventing the application of (highly subjective) quality metrics that has previously been shown to result in notable differences in the detection of de novo mutations, and ultimately estimates of mutation rates. This deep sampling has enabled both a detailed picture of parental age effects as well as sex dependency in mutation rates which we here compare with previously studied primates, but has also provided unique insights into the nature of genetic variation in one of the most endangered primates on the planet.},
}

@article {pmid39605354,
year = {2024},
author = {Eichelman, MC and Meyer, MM},
title = {Assessing the conservation and targets of putative sRNAs in Streptococcus pneumoniae.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.11.14.623631},
pmid = {39605354},
issn = {2692-8205},
abstract = {RNA regulators are often found in complex regulatory networks and may mediate metabolism and virulence in bacteria. Small RNAs (sRNA's), a class of non-coding RNAs that interact with an mRNA transcript via base pairing, modulate translation initiation and mRNA degradation. To better understand the role of sRNAs in pathogenicity several studies identified sRNAs in Streptococcus pneumoniae , however little functional characterization has followed. The goal of this study is threefold: 1) take an inventory of putative sRNAs in S. pneumoniae ; 2) assess the conservation of these sRNAs; and 3) examine their predicted targets. Three previous studies in S. pneumoniae identified 287 putative sRNAs by high-throughput sequencing using a variety of distinct inclusion criteria. This study narrows the candidates to a list of 59 putative sRNAs. BLAST analysis shows that each of the 59 sequences are highly conserved across the S. pneumoniae pangenome while only 5 sRNAs have corresponding sequences with substantial similarity in other members of the Streptococcus genus. We used four RNA-RNA interaction prediction programs (IntaRNA, CopraRNA, sRNARFTarget, and TargetRNA3) to predict targets for each of the 59 putative sRNAs. Across all probable predictions, only seven sRNAs have overlap in the targets predicted by multiple programs, four of which target numerous transposases. Moreover, sRNAs targeting transposases do so with nearly identical and perfect base pairing. One sRNA, named M63 (Spd_sr37), has several probable targets in the CcpA regulon, a network responsible for global catabolite repression, suggesting a possible biological function in control of carbon metabolism. Further, each M63-target interaction exhibits unique base pairing increasing confidence in the biological relevance of the result. This study produces a curated list of S. pneumoniae putative sRNAs whose predicted targets suggest functional significance in transposon and carbon metabolism regulation.},
}

@article {pmid39604761,
year = {2024},
author = {Chang, HY and Yen, HC and Chu, HA and Kuo, CH},
title = {Population genomics of a thermophilic cyanobacterium revealed divergence at subspecies level and possible adaptation genes.},
journal = {Botanical studies},
volume = {65},
number = {1},
pages = {35},
pmid = {39604761},
issn = {1817-406X},
abstract = {BACKGROUND: Cyanobacteria are diverse phototrophic microbes with ecological importance and potential for biotechnology applications. One species of thermophilic cyanobacteria, Thermosynechococcus taiwanensis, has been studied for biomass pyrolysis, estrogen degradation, and the production of bioethanol, monosaccharide, and phycocyanin. To better understand the diversity and evolution of this species, we sampled across different regions in Taiwan for strain isolation and genomic analysis.

RESULTS: A total of 27 novel strains were isolated from nine of the 12 hot springs sampled and subjected to whole genome sequencing. Including strains studied previously, our genomic analyses encompassed 32 strains from 11 hot springs. Genome sizes among these strains ranged from 2.64 to 2.70 Mb, with an average of 2.66 Mb. Annotation revealed between 2465 and 2576 protein-coding genes per genome, averaging 2537 genes. Core-genome phylogeny, gene flow estimates, and overall gene content divergence consistently supported the within-species divergence into two major populations. While isolation by distance partially explained the within-population divergence, the factors driving divergence between populations remain unclear. Nevertheless, this species likely has a closed pan-genome comprising approximately 3030 genes, with our sampling providing sufficient coverage of its genomic diversity. To investigate the divergence and potential adaptations, we identified genomic regions with significantly lower nucleotide diversity, indicating loci that may have undergone selective sweeps within each population. We identified 149 and 289 genes within these regions in populations A and B, respectively. Only 16 genes were common to both populations, suggesting that selective sweeps primarily targeted different genes in the two populations. Key genes related to functions such as photosynthesis, motility, and ion transport were highlighted.

CONCLUSIONS: This work provides a population genomics perspective on a hot spring cyanobacterial species in Taiwan. Beyond advancing our understanding of microbial genomics and evolution, the strains collected and genome sequences generated in this work provide valuable materials for future development and utilization of biological resources.},
}

@article {pmid39604736,
year = {2024},
author = {Jiao, C and Xie, X and Hao, C and Chen, L and Xie, Y and Garg, V and Zhao, L and Wang, Z and Zhang, Y and Li, T and Fu, J and Chitikineni, A and Hou, J and Liu, H and Dwivedi, G and Liu, X and Jia, J and Mao, L and Wang, X and Appels, R and Varshney, RK and Guo, W and Zhang, X},
title = {Pan-genome bridges wheat structural variations with habitat and breeding.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {39604736},
issn = {1476-4687},
abstract = {Wheat is the second largest food crop with a very good breeding system and pedigree record in China. Investigating the genomic footprints of wheat cultivars will unveil potential avenues for future breeding efforts[1,2]. Here we report chromosome-level genome assemblies of 17 wheat cultivars that chronicle the breeding history of China. Comparative genomic analysis uncovered a wealth of structural rearrangements, identifying 249,976 structural variations with 49.03% (122,567) longer than 5 kb. Cultivars developed in 1980s displayed significant accumulations of structural variations, a pattern linked to the extensive incorporation of European and American varieties into breeding programmes of that era. We further proved that structural variations in the centromere-proximal regions are associated with a reduction of crossover events. We showed that common wheat evolved from spring to winter types via mutations and duplications of the VRN-A1 gene as an adaptation strategy to a changing environment. We confirmed shifts in wheat cultivars linked to dietary preferences, migration and cultural integration in Northwest China. We identified large presence or absence variations of pSc200 tandem repeats on the 1RS terminal, suggesting its own rapid evolution in the wheat genome. The high-quality genome assemblies of 17 representatives developed and their good complementarity to the 10+ pan-genomes offer a robust platform for future genomics-assisted breeding in wheat.},
}