@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.},
}

@article {pmid39604663,
year = {2024},
author = {Bortoluzzi, C and Mapel, XM and Neuenschwander, S and Janett, F and Pausch, H and Leonard, AS},
title = {Genome assembly of wisent (Bison bonasus) uncovers a deletion that likely inactivates the THRSP gene.},
journal = {Communications biology},
volume = {7},
number = {1},
pages = {1580},
pmid = {39604663},
issn = {2399-3642},
support = {204654//Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (Swiss National Science Foundation)/ ; },
mesh = {Animals ; *Bison/genetics ; *Genome ; Sequence Deletion ; Cattle/genetics ; },
abstract = {The wisent (Bison bonasus) is Europe's largest land mammal. We produced a HiFi read-based wisent assembly with a contig N50 value of 91 Mb containing 99.7% of the highly conserved single copy mammalian genes which improves contiguity a thousand-fold over an existing assembly. Extended runs of homozygosity in the wisent genome compromised the separation of the HiFi reads into parental-specific read sets, which resulted in inferior haplotype assemblies. A bovine super-pangenome built with assemblies from wisent, bison, gaur, yak, taurine and indicine cattle identified a 1580 bp deletion removing the protein-coding sequence of THRSP encoding thyroid hormone-responsive protein from the wisent and bison genomes. Analysis of 725 sequenced samples across the Bovinae subfamily showed that the deletion is fixed in both Bison species but absent in Bos and Bubalus. The THRSP transcript is abundant in adipose, fat, liver, muscle, and mammary gland tissue of Bos and Bubalus, but absent in bison. This indicates that the deletion likely inactivates THRSP in bison. We show that super-pangenomes can reveal potentially trait-associated variation across phylogenies, but also demonstrate that haplotype assemblies from species that went through population bottlenecks warrant scrutiny, as they may have accumulated long runs of homozygosity that complicate phasing.},
}

Animals
*Bison/genetics
*Genome
Sequence Deletion
Cattle/genetics

@article {pmid39602797,
year = {2024},
author = {Zhang, J and Nie, F and Luo, F and Wang, J},
title = {Phasing Nanopore genome assembly by integrating heterozygous variations and Hi-C data.},
journal = {Bioinformatics (Oxford, England)},
volume = {},
number = {},
pages = {},
doi = {10.1093/bioinformatics/btae712},
pmid = {39602797},
issn = {1367-4811},
abstract = {MOTIVATION: Haplotype-resolved genome assemblies serve as vital resources in various research domains, including genomics, medicine, and pangenomics. Algorithms employing Hi-C data to generate haplotype-resolved assemblies are particularly advantageous due to its ready availability. Existing methods primarily depend on mapping quality to filter out uninformative Hi-C alignments which may be susceptible to sequencing errors. Setting a high mapping quality threshold filters out numerous informative Hi-C alignments, whereas a low mapping quality threshold compromises the accuracy of Hi-C alignments. Maintaining high accuracy while retaining a maximum number of Hi-C alignments can be challenging.

RESULTS: In our experiments, heterozygous variations play an important role in filtering uninformative Hi-C alignments. Here, we introduce Diphase, a novel phasing tool that harnesses heterozygous variations to accurately identify the informative Hi-C alignments for phasing and to extend primary/alternate assemblies. Diphase leverages mapping quality and heterozygous variations to filter uninformative Hi-C alignments, thereby enhancing the accuracy of phasing and the detection of switches. To validate its performance, we conducted a comparative analysis of Diphase, FALCON-Phase, and GFAse on various human datasets. The results demonstrate that Diphase achieves a longer phased block N50 and exhibits higher phasing accuracy while maintaining a lower hamming error rate.

AVAILABILITY: The source code of Diphase is available at https://github.com/zhangjuncsu/Diphase.

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

@article {pmid39601883,
year = {2024},
author = {Mankoti, M and Pandit, NK and Meena, SS and Mohanty, A},
title = {Investigating the genomic and metabolic abilities of PGPR Pseudomonas fluorescens in promoting plant growth and fire blight management.},
journal = {Molecular genetics and genomics : MGG},
volume = {299},
number = {1},
pages = {110},
pmid = {39601883},
issn = {1617-4623},
mesh = {*Pseudomonas fluorescens/genetics/metabolism ; *Plant Diseases/microbiology ; *Molecular Docking Simulation ; *Rhizosphere ; *Plant Development ; *Erwinia amylovora/genetics/metabolism ; Genome, Bacterial ; Soil Microbiology ; Phenazines/metabolism ; RNA, Ribosomal, 16S/genetics ; },
abstract = {Pseudomonas fluorescens is commonly found in diverse environments and is well known for its metabolic and antagonistic properties. Despite its remarkable attributes, its potential role in promoting plant growth remains unexplored. This study examines these traits across 14 strains residing in diverse rhizosphere environments through pangenome and comparative genome analysis, alongside molecular docking studies against Erwinia amylovora to combat fire blight. Whole genome analysis revealed circular chromosome (6.01-7.07 Mb) with GC content averaging 59.95-63.39%. Predicted genes included 16S rRNA and protein-coding genes ranging from 4435 to 6393 bp and 1527 to 1541 bp, respectively. Pangenome analysis unveiled an open pangenome, shedding light on genetic factors influencing plant growth promotion and biocontrol, including nitrogen fixation, phosphorus solubilization, siderophore production, stress tolerance, flagella biosynthesis, and induced systemic resistance. Furthermore, pyrrolnitrin, phenazine-1-carboxylic acid, pyoluteorin, lokisin, 2,4-diacetylpholoroglucinol and pseudomonic acid were identified. Molecular docking against key proteins of E. amylovora highlighted the high binding affinities of 2,4-diacetylphloroglucinol, pseudomonic acid, and lokisin. These findings underscore the multifaceted role of P. fluorescens in plant growth promotion and biocontrol, with key biomolecules showing promising applications in plant growth and defense against pathogens.},
}

*Pseudomonas fluorescens/genetics/metabolism
*Plant Diseases/microbiology
*Molecular Docking Simulation
*Rhizosphere
*Plant Development
*Erwinia amylovora/genetics/metabolism
Genome, Bacterial
Soil Microbiology
Phenazines/metabolism
RNA, Ribosomal, 16S/genetics

@article {pmid39600872,
year = {2024},
author = {Song, JM and Long, HB and Ye, M and Yang, BR and Wu, GJ and He, HC and Wang, JL and Li, HW and Li, XG and Deng, DY and Li, B and Yuan, WL},
title = {Genomic characterization of a bla KPC-2-producing IncM2 plasmid harboring transposon ΔTn6296 in Klebsiella michiganensis.},
journal = {Frontiers in cellular and infection microbiology},
volume = {14},
number = {},
pages = {1492700},
pmid = {39600872},
issn = {2235-2988},
mesh = {*beta-Lactamases/genetics ; *Plasmids/genetics ; Humans ; *Whole Genome Sequencing ; China ; *Genome, Bacterial ; *Klebsiella Infections/microbiology ; *DNA Transposable Elements/genetics ; *Klebsiella/genetics/enzymology ; Drug Resistance, Multiple, Bacterial/genetics ; Anti-Bacterial Agents/pharmacology ; Microbial Sensitivity Tests ; Escherichia coli/genetics ; Bacterial Proteins/genetics/metabolism ; Conjugation, Genetic ; },
abstract = {Klebsiella michiganensis is an emerging hospital-acquired bacterial pathogen, particularly strains harboring plasmid-mediated carbapenemase genes. Here, we recovered and characterized a multidrug-resistant strain, bla KPC-2-producing Klebsiella michiganensis LS81, which was isolated from the abdominal drainage fluid of a clinical patient in China, and further characterized the co-harboring plasmid. K. michiganensis LS81 tested positive for the bla KPC-2 genes by PCR sequencing, with bla KPC-2 located on a plasmid as confirmed by S1 nuclease pulsed-field gel electrophoresis combined with Southern blotting. In the transconjugants, the bla KPC-2 genes were successfully transferred to the recipient strain E. coli EC600. Whole-genome sequencing and bioinformatics analysis confirmed that this strain belongs to sequence type 196 (ST196), with a complete genome comprising a 5,926,662bp circular chromosome and an 81,451bp IncM2 plasmid encoding bla KPC-2 (designated pLS81-KPC). The IncM2 plasmid carried multiple β-lactamase genes such as bla TEM-1B, bla CTX-M-3, and bla KPC-2 inserted in truncated Tn6296 with the distinctive core structure ISKpn27-bla KPC-2-ISKpn6. A comparison with 46 K. michiganensis genomes available in the NCBI database revealed that the closest phylogenetic relative of K. michiganensis LS81 is a clinical isolate from a wound swab in the United Kingdom. Ultimately, the pan-genomic analysis unveiled a substantial accessory genome within the strain, alongside significant genomic plasticity within the K. michiganensis species, emphasizing the necessity for continuous surveillance of this pathogen in clinical environments.},
}

*beta-Lactamases/genetics
*Plasmids/genetics
Humans
*Whole Genome Sequencing
China
*Genome, Bacterial
*Klebsiella Infections/microbiology
*DNA Transposable Elements/genetics
*Klebsiella/genetics/enzymology
Drug Resistance, Multiple, Bacterial/genetics
Anti-Bacterial Agents/pharmacology
Microbial Sensitivity Tests
Escherichia coli/genetics
Bacterial Proteins/genetics/metabolism
Conjugation, Genetic

@article {pmid39597765,
year = {2024},
author = {Diabankana, RGC and Zhamalbekova, AA and Shakirova, AE and Vasiuk, VI and Filimonova, MN and Validov, SZ and Safin, RI and Afordanyi, DM},
title = {Genomic Insights of Wheat Root-Associated Lysinibacillus fusiformis Reveal Its Related Functional Traits for Bioremediation of Soil Contaminated with Petroleum Products.},
journal = {Microorganisms},
volume = {12},
number = {11},
pages = {},
doi = {10.3390/microorganisms12112377},
pmid = {39597765},
issn = {2076-2607},
support = {075-15-2021-1395, 25.10.2021 (15.IP.21.0020)//Ministry of Science and Higher Education of the Russian Federation/ ; },
abstract = {The negative ecological impact of industrialization, which involves the use of petroleum products and dyes in the environment, has prompted research into effective, sustainable, and economically beneficial green technologies. For green remediation primarily based on active microbial metabolites, these microbes are typically from relevant sources. Active microbial metabolite production and genetic systems involved in xenobiotic degradation provide these microbes with the advantage of survival and proliferation in polluted ecological niches. In this study, we evaluated the ability of wheat root-associated L. fusiformis MGMM7 to degrade xenobiotic contaminants such as crude oil, phenol, and azo dyes. We sequenced the whole genome of MGMM7 and provided insights into the genomic structure of related strains isolated from contaminated sources. The results revealed that influenced by its isolation source, L. fusiformis MGMM7 demonstrated remediation and plant growth-promoting abilities in soil polluted with crude oil. Lysinibacillus fusiformis MGMM7 degraded up to 44.55 ± 5.47% crude oil and reduced its toxicity in contaminated soil experiments with garden cress (Lepidium sativum L.). Additionally, L. fusiformis MGMM7 demonstrated a significant ability to degrade Congo Red azo dye (200 mg/L), reducing its concentration by over 60% under both static and shaking cultivation conditions. However, the highest degradation efficiency was observed under shaking conditions. Genomic comparison among L. fusiformis strains revealed almost identical genomic profiles associated with xenobiotic assimilation. Genomic relatedness using Average Nucleotide Identity (ANI) and digital DNA-DNA hybridization (DDH) revealed that MGMM7 is distantly related to TZA38, Cu-15, and HJ.T1. Furthermore, subsystem distribution and pangenome analysis emphasized the distinctive features of MGMM7, including functional genes in its chromosome and plasmid, as well as the presence of unique genes involved in PAH assimilation, such as phnC/T/E, which is involved in phosphonate biodegradation, and nemA, which is involved in benzoate degradation and reductive degradation of N-ethylmaleimide. These findings highlight the potential properties of petroleum-degrading microorganisms isolated from non-contaminated rhizospheres and offer genomic insights into their functional diversity for xenobiotic remediation.},
}

@article {pmid39596184,
year = {2024},
author = {Wang, Z and Wu, Y and Liu, M and Chen, L and Xiao, K and Huang, Z and Zhao, Y and Wang, H and Ding, Y and Lin, X and Zeng, J and Peng, F and Zhang, J and Wang, J and Wu, Q},
title = {The Gene Cluster Cj0423-Cj0425 Negatively Regulates Biofilm Formation in Campylobacter jejuni.},
journal = {International journal of molecular sciences},
volume = {25},
number = {22},
pages = {},
doi = {10.3390/ijms252212116},
pmid = {39596184},
issn = {1422-0067},
support = {2023YFD1801000//National Key Research and Development Program of China/ ; 2020B0301030005//Guangdong Major Project of Basic and Applied Basic Research/ ; 2021TQ06N119//Talent Support Project of Guangdong/ ; 2022GDASZH-2022020402-1//Guangdong Academy of Sciences Project/ ; },
mesh = {*Biofilms/growth & development ; *Campylobacter jejuni/genetics/physiology/growth & development/metabolism ; *Multigene Family ; *Bacterial Proteins/genetics/metabolism ; *Gene Expression Regulation, Bacterial ; Quorum Sensing/genetics ; Flagella/genetics/metabolism ; Fatty Acids/metabolism ; },
abstract = {Campylobacter jejuni (C. jejuni) is a zoonotic foodborne pathogen that is widely distributed worldwide. Its optimal growth environment is microaerophilic conditions (5% O2, 10% CO2), but it can spread widely in the atmospheric environment. Biofilms are thought to play an important role in this process. However, there are currently relatively few research works on the regulatory mechanisms of C. jejuni biofilm formation. In this study, a pan-genome analysis, combined with the analysis of biofilm phenotypic information, revealed that the gene cluster Cj0423-Cj0425 is associated with the negative regulation of biofilm formation in C. jejuni. Through gene knockout experiments, it was observed that the Cj0423-Cj0425 mutant strain significantly increased biofilm formation and enhanced flagella formation. Furthermore, pull-down assay revealed that Cj0424 interacts with 93 proteins involved in pathways such as fatty acid synthesis and amino acid metabolism, and it also contains the quorum sensing-related gene luxS. This suggests that Cj0423-Cj0425 affects fatty acid synthesis and amino acid metabolism, influencing quorum sensing and strain motility, ultimately inhibiting biofilm formation.},
}

*Biofilms/growth & development
*Campylobacter jejuni/genetics/physiology/growth & development/metabolism
*Multigene Family
*Bacterial Proteins/genetics/metabolism
*Gene Expression Regulation, Bacterial
Quorum Sensing/genetics
Flagella/genetics/metabolism
Fatty Acids/metabolism

@article {pmid39593788,
year = {2024},
author = {Liu, H and Lin, J and Huang, Y and Duan, Y and Zhu, X},
title = {Genomic Comparisons Revealed the Key Genotypes of Streptomyces sp. CB03234-GS26 to Optimize Its Growth and Relevant Production of Tiancimycins.},
journal = {Bioengineering (Basel, Switzerland)},
volume = {11},
number = {11},
pages = {},
pmid = {39593788},
issn = {2306-5354},
support = {2023SK2071//the science and technology innovation Program of Hunan Province/ ; CX20210112//the Hunan Provincial Innovation Foundation for Postgraduate/ ; 2021zzts0330//the Fundamental Research Funds for the Central Universities of Central South University (CSU)/ ; 81872779//the National Natural Science Foundation of China Grants/ ; 82204256//the National Natural Science Foundation of China Grants/ ; BP0820034//he Chinese Ministry of Education 111 Project/ ; },
abstract = {Strain robustness and titer improvement are major challenges faced in the industrial development of natural products from Streptomyces. Tiancimycins (TNMs) produced by Streptomyces sp. CB03234 are promising anticancer payloads for antibody-drug conjugates, but further development is severely limited by the low titer of TNMs. Despite many efforts to generate various TNMs overproducers, the mechanisms underlying high TNMs production remain to be explored. Herein, genome resequencing and genomic comparisons of different TNMs overproducers were conducted to explore the unique genotypes in CB03234-GS26. Four target genes were selected for further bioinformatic analyses and genetic validations. The results indicated that the inactivation of histidine ammonia-lyase (HAL) showed the most significant effect by blocking the intracellular degradation of histidine to facilitate relevant enzymatic catalysis and thus improve the production of TNMs. Additionally, the potassium/proton antiporter (P/PA) was crucial for intracellular pH homeostasis, and its deficiency severely impaired the alkaline tolerance of the cells. Subsequent pan-genomic analysis suggested that HAL and P/PA are core enzymes that are highly conserved in Streptomyces. Therefore, HAL and P/PA represented novel targets to regulate secondary metabolism and enhance strain robustness and could become potential synthetic biological modules to facilitate development of natural products and strain improvement in Streptomyces.},
}

@article {pmid39591974,
year = {2024},
author = {Peng, Y and Zhu, J and Wang, S and Liu, Y and Liu, X and DeLeon, O and Zhu, W and Xu, Z and Zhang, X and Zhao, S and Liang, S and Li, H and Ho, B and Ching, JY and Cheung, CP and Leung, TF and Tam, WH and Leung, TY and Chang, EB and Chan, FKL and Zhang, L and Ng, SC and Tun, HM},
title = {A metagenome-assembled genome inventory for children reveals early-life gut bacteriome and virome dynamics.},
journal = {Cell host & microbe},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.chom.2024.10.017},
pmid = {39591974},
issn = {1934-6069},
abstract = {Existing microbiota databases are biased toward adult samples, hampering accurate profiling of the infant gut microbiome. Here, we generated a metagenome-assembled genome inventory for children (MAGIC) from a large collection of bulk and viral-like particle-enriched metagenomes from 0 to 7 years of age, encompassing 3,299 prokaryotic and 139,624 viral species-level genomes, 8.5% and 63.9% of which are unique to MAGIC. MAGIC improves early-life microbiome profiling, with the greatest improvement in read mapping observed in Africans. We then identified 54 candidate keystone species, including several Bifidobacterium spp. and four phages, forming guilds that fluctuated in abundance with time. Their abundances were reduced in preterm infants and were associated with childhood allergies. By analyzing the B. longum pangenome, we found evidence of phage-mediated evolution and quorum sensing-related ecological adaptation. Together, the MAGIC database recovers genomes that enable characterization of the dynamics of early-life microbiomes, identification of candidate keystone species, and strain-level study of target species.},
}

@article {pmid39589236,
year = {2024},
author = {Granada, M and Cook, E and Sherlock, G and Rosenzweig, F},
title = {Microbe Profile: Candida glabrata - a master of deception.},
journal = {Microbiology (Reading, England)},
volume = {170},
number = {11},
pages = {},
doi = {10.1099/mic.0.001518},
pmid = {39589236},
issn = {1465-2080},
mesh = {*Candida glabrata/genetics/classification ; Humans ; *Phylogeny ; *Candidiasis/microbiology ; Genome, Fungal ; Antifungal Agents/pharmacology ; Drug Resistance, Fungal/genetics ; Animals ; },
abstract = {Candida glabrata is a fungal microbe associated with multiple vertebrate microbiomes and their terrestrial environments. In humans, the species has emerged as an opportunistic pathogen that now ranks as the second-leading cause of candidiasis in Europe and North America (Beardsley et al. Med Mycol 2024, 62). People at highest risk of infection include the elderly, immunocompromised individuals and/or long-term residents of hospital and assisted-living facilities. C. glabrata is intrinsically drug-resistant, metabolically versatile and able to avoid detection by the immune system. Analyses of its 12.3 Mb genome indicate a stable pangenome Marcet-Houben et al. (BMC Biol 2022, 20) and phylogenetic affinity with Saccharomyces cerevisiae. Recent phylogenetic analyses suggest reclassifying C. glabrata as Nakaseomyces glabratus Lakashima and Sugita (Med Mycol J 2022, 63: 119-132).},
}

*Candida glabrata/genetics/classification
Humans
*Phylogeny
*Candidiasis/microbiology
Genome, Fungal
Antifungal Agents/pharmacology
Drug Resistance, Fungal/genetics
Animals

@article {pmid39587228,
year = {2024},
author = {Balakrishnan, B and Johnson, S and Luckey, D and Marietta, E and Murray, J and Taneja, V},
title = {Small intestinal derived Prevotella histicola simulates biologic as a therapeutic agent.},
journal = {Scientific reports},
volume = {14},
number = {1},
pages = {29217},
pmid = {39587228},
issn = {2045-2322},
support = {W81XWH-10-1-0257//Congressionally Directed Medical Research Programs/ ; },
mesh = {Animals ; *Prevotella/drug effects/genetics ; Mice ; *Arthritis, Rheumatoid/drug therapy/microbiology ; *Gastrointestinal Microbiome/drug effects ; Humans ; Arthritis, Experimental/drug therapy/microbiology ; Intestine, Small/microbiology/drug effects ; Tumor Necrosis Factor Inhibitors/pharmacology/therapeutic use ; HLA-DQ Antigens/genetics ; Disease Models, Animal ; Male ; },
abstract = {A role of gut microbiome in pathogenesis as well as response to treatment is documented in rheumatoid arthritis. Using a novel duodenal derived Prevotella histicola strain MCI 001, we have shown that it suppresses disease progression in a collagen-induced arthritis (CIA), a model for rheumatoid arthritis (RA) using humanized mice expressing HLA-DQ8 gene in the absence of endogenous class II genes. Here we compared efficacy of P. histicola MCI 001 with tumor necrosis factor inhibitor (TNFi) for treating arthritis. DQ8 arthritic mice treated with P. histicola by oral gavage or TNFi, were compared for disease onset, incidence and severity. We demonstrate that oral treatment with P. histicola mimics treatment with TNFi in arthritic DQ8 mice. A pangenome comparison of our P. histicola MCI 001 with its closest available neighbors depicted it as a novel strain with unique gene sequences that may contribute to immune modulatory effects. Notably, it possesses a unique sequence of an outer membrane protein, BtuB, which is involved in vitamin B12 transport. Our data indicate that P. histicola MC001 is an attractive candidate to prevent the progression of disease in RA patients with ongoing disease.},
}

Animals
*Prevotella/drug effects/genetics
Mice
*Arthritis, Rheumatoid/drug therapy/microbiology
*Gastrointestinal Microbiome/drug effects
Humans
Arthritis, Experimental/drug therapy/microbiology
Intestine, Small/microbiology/drug effects
Tumor Necrosis Factor Inhibitors/pharmacology/therapeutic use
HLA-DQ Antigens/genetics
Disease Models, Animal
Male

@article {pmid39579164,
year = {2024},
author = {Karmakar, M and Sur, S},
title = {Unlocking the Mycobacteroides abscessus pan-genome using computational tools: insights into evolutionary dynamics and lifestyle.},
journal = {Antonie van Leeuwenhoek},
volume = {118},
number = {1},
pages = {30},
pmid = {39579164},
issn = {1572-9699},
mesh = {*Genome, Bacterial ; *Mycobacterium abscessus/genetics/drug effects ; *Phylogeny ; Evolution, Molecular ; Computational Biology/methods ; Bacterial Proteins/genetics/metabolism ; Virulence/genetics ; Virulence Factors/genetics ; Genomics ; },
abstract = {Mycobacteroides abscessus is a non-tuberculous mycobacteria implicated in causing lung infections. It is difficult to control owing to resistance to antibiotics and disinfectants. This work was aimed at comprehending: the pan-genome architecture, evolutionary dynamics, and functionalities of pan-genome components linked to COGs and KEGG. Around 2802 core genes were present in each strain of the M. abscessus genome. The number of accessory genes ranged from 1615 to 2481. The open pan-genome of M. abscessus was attributed to the accessory genes underlining its adaptability in the host. Phylogenetic analysis revealed cluster-based relationships and highlighted factors shaping variability and adaptive capabilities. Transcription, metabolism, and pathogenic genes were vital for M. abscessus lifestyle. The accessory genes contributed to the diverse metabolic capability. The incidence of a significant portion of secondary metabolite biosynthesis genes provided insights for investigating their biosynthetic gene clusters. Additionally, a high proportion of xenobiotic biodegradation genes highlighted potential metabolic capabilities. In silico screening identified a potential vaccine candidate among hypothetical proteins in COGs. Functional analysis of M. abscessus pan-genome components unveiled factors associated with virulence, pathogenicity, infection establishment, persistence, and resistance. Notable amongst them were: MMPL family transporters, PE-PPE domain-containing proteins, TetR family transcriptional regulators, ABC transporters, Type-I, II, III, VII secretion proteins, DUF domain-containing proteins, cytochrome P450, VapC family toxin, virulence factor Mce family protein, type II toxin-antitoxin system. Overall, these results enhanced understanding of the metabolism, host-pathogen dynamics, pathogenic lifestyle, and adaptations. This will facilitate further investigations for combating infections and designing suitable therapies.},
}

*Genome, Bacterial
*Mycobacterium abscessus/genetics/drug effects
*Phylogeny
Evolution, Molecular
Computational Biology/methods
Bacterial Proteins/genetics/metabolism
Virulence/genetics
Virulence Factors/genetics
Genomics

@article {pmid39577948,
year = {2024},
author = {Sheng, H and Zhao, L and Suo, J and Yang, Q and Cao, C and Chen, J and Cui, G and Fan, Y and Ma, Y and Huo, S and Wu, X and Yang, T and Cui, X and Chen, S and Cui, S and Yang, B},
title = {Niche-specific evolution and gene exchange of Salmonella in retail pork and chicken.},
journal = {Food research international (Ottawa, Ont.)},
volume = {197},
number = {Pt 2},
pages = {115299},
doi = {10.1016/j.foodres.2024.115299},
pmid = {39577948},
issn = {1873-7145},
mesh = {Animals ; *Chickens/microbiology ; *Salmonella/genetics ; Swine ; *Food Microbiology ; China ; *Pork Meat/microbiology ; Anti-Bacterial Agents/pharmacology ; Gene Transfer, Horizontal ; Meat/microbiology ; Drug Resistance, Bacterial/genetics ; Genetic Variation ; Red Meat/microbiology ; },
abstract = {Salmonella exhibits extensive genetic diversity, facilitated by horizontal gene transfer occurring within and between species, playing a pivotal role in this diversification. Nevertheless, most studies focus on clinical and farm animal isolates, and research on the pangenome dynamics of Salmonella isolates from retail stage of the animal food supply chain is limited. Here, we investigated the genomes of 950 Salmonella isolates recovered from retail chicken and pork meats in seven provinces and one municipality of China in 2018. We observed a strong correlation between Salmonella sublineage diversity and the accessory genome with meat type, revealing reduced diversity associated with increased resistance. Importantly, genes associated with antibiotic, biocide, and heavy metal resistance were unevenly distributed in Salmonella from retail chicken and pork. Pork Salmonella isolates showed a higher prevalence of copper and silver resistance genes, while chicken Salmonella isolates displayed a significant predominance of genetic determinants associated with cephalosporin and ciprofloxacin resistance. Moreover, co-occurrence patterns of resistance determinants and their interaction with mobile genetic elements also correlated with meat type. In summary, our findings shed light on how Salmonella achieves their ecological niche success driven by evolution and gene changes in the retail stage of the animal food supply chain.},
}

Animals
*Chickens/microbiology
*Salmonella/genetics
Swine
*Food Microbiology
China
*Pork Meat/microbiology
Anti-Bacterial Agents/pharmacology
Gene Transfer, Horizontal
Meat/microbiology
Drug Resistance, Bacterial/genetics
Genetic Variation
Red Meat/microbiology

@article {pmid39576463,
year = {2024},
author = {Frederico, TD and Cunha-Ferreira, IC and Vizzotto, CS and de Sousa, JF and Portugal, MM and Tótola, MR and Krüger, RH and Peixoto, J},
title = {Genomic and taxonomic characterization of the Comamonas sp. nov., a bacterium isolated from Brazilian Cerrado soil.},
journal = {Brazilian journal of microbiology : [publication of the Brazilian Society for Microbiology]},
volume = {},
number = {},
pages = {},
pmid = {39576463},
issn = {1678-4405},
support = {Conselho Nacional de Desenvolvimento Científico e Tecnológico//Conselho Nacional de Desenvolvimento Científico e Tecnológico/ ; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior//Coordenação de Aperfeiçoamento de Pessoal de Nível Superior/ ; Fundação de Apoio à Pesquisa do Distrito Federal//Fundação de Apoio à Pesquisa do Distrito Federal/ ; },
abstract = {A novel strain identified as Comamonas sp. was isolated from the soil of the Brazilian savanna-like Cerrado biome, a global hotspot for biodiversity. Phylogenetic analysis based on 16 S rRNA gene sequences showed that this strain is classified as Betaproteobacteria from the family Comamonadaceae. The digital DNA-DNA hybridization (dDDH) and Average Nucleotide Identity (ANI) results, of respectively 48.6% and < 93%, indicated that Comamonas sp. consists in a new species with Comamonas testosteroni as its closest strain. Comamonas sp. is a Gram-negative, rod-shaped, and non-spore-forming bacterium. Its colonies typically exhibit a round, convex, and irregular shape with a clear color and spotted edges. It is characterized as non-fermenting, aerobic, and motile, presenting both oxidase and catalase activities. The optimal growth parameters for this bacterial strain are 30 °C, a pH range of 5-8, and 0% NaCl. In addition, its fatty acid profile included palmitic acid (C16:0) at 26.94%, 13-Methyltetradecanoic Acid (iso-C15:0) at 10.94%, myristic acid (C14:0) at 8.94%, and a summed feature comprising 16:1 ω7c, 16:1 ω6c, or 16:1 at 15.8%. Genomic analysis of Comamonas sp. revealed a GC content of 62.1% across its 5.6 Mb genome. Phylogenomic and pangenome analyses, along with in silico phenotypic characterization indicate that this strain represents a novel species within the Comamonas genus, which we propose to name Comamonas brasiliensis nov.},
}

@article {pmid39576133,
year = {2024},
author = {Kim, H and Ahn, J and Kim, J and Kang, H-S},
title = {Metagenomic insights and biosynthetic potential of Candidatus Entotheonella symbiont associated with Halichondria marine sponges.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0235524},
doi = {10.1128/spectrum.02355-24},
pmid = {39576133},
issn = {2165-0497},
abstract = {Korea, being surrounded by the sea, provides a rich habitat for marine sponges, which have been a prolific source of bioactive natural products. Although a diverse array of structurally novel natural products has been isolated from Korean marine sponges, their biosynthetic origins remain largely unknown. To explore the biosynthetic potential of Korean marine sponges, we conducted metagenomic analyses of sponges inhabiting the East Sea of Korea. This analysis revealed a symbiotic association of Candidatus Entotheonella bacteria with Halichondria sponges. Here, we report a new chemically rich Entotheonella variant, which we named Ca. Entotheonella halido. Remarkably, this symbiont makes up 69% of the microbial community in the sponge Halichondira dokdoensis. Genome-resolved metagenomics enabled us to obtain a high-quality Ca. E. halido genome, which represents the largest (12 Mb) and highest quality among previously reported Entotheonella genomes. We also identified the biosynthetic gene cluster (BGC) of the known sponge-derived Halicylindramides from the Ca. E. halido genome, enabling us to determine their biosynthetic origin. This new symbiotic association expands the host diversity and biosynthetic potential of metabolically talented bacterial genus Ca. Entotheonella symbionts.IMPORTANCEOur study reports the discovery of a new bacterial symbiont Ca. Entotheonella halido associated with the Korean marine sponge Halichondria dokdoensis. Using genome-resolved metagenomics, we recovered a high-quality Ca. E. halido MAG (Metagenome-Assembled Genome), which represents the largest and most complete Ca. Entotheonella MAG reported to date. Pangenome and BGC network analyses revealed a remarkably high BGC diversity within the Ca. Entotheonella pangenome, with almost no overlapping BGCs between different MAGs. The cryptic and genetically unique BGCs present in the Ca. Entotheonella pangenome represents a promising source of new bioactive natural products.},
}

@article {pmid39575183,
year = {2024},
author = {Alnaimat, SM and Abushattal, S and Dmour, SM},
title = {Comparative genomic characterization of Cellulosimicrobium funkei isolate RVMD1 from Ma'an desert rock varnish challenges Cellulosimicrobium systematics.},
journal = {Frontiers in microbiology},
volume = {15},
number = {},
pages = {1445943},
pmid = {39575183},
issn = {1664-302X},
abstract = {Desert environments harbor unique microbial communities. This study focuses on Cellulosimicrobium funkei isolate RVMD1, isolated from rock varnish in the Ma'an Desert. Initial identification was achieved using 16S rRNA gene sequencing, followed by whole-genome sequencing (WGS) for comprehensive characterization. The genome comprises 4,264,015 base pairs (857 contigs) with a high G + C content of 74.59%. A total of 4,449 proteins were predicted. Comparative analysis utilizing OrthoANI, ANI, AAI, and dDDH metrics suggests that RVMD1 belongs to the C. cellulans group, with the highest similarity to C. funkei (97.71% ANI). Phylogenomic analysis of 43 Cellulosimicrobium genomes revealed significant heterogeneity within the genus. Our results challenge current systematics, with C. cellulans potentially representing up to 9 distinct genomospecies. Isolate RVMD1 shows genetic adaptations to its desert environment, including genes for denitrification, oxygen and sulfur cycling, and diverse hydrogen metabolism. Pangenomic analysis uncovered a considerable number of unique genes within RVMD1, highlighting its genetic distinctiveness. Gene family expansions suggest evolution in response to stressors like UV radiation and nutrient limitation. This study represents the first whole-genome analysis of a bacterium isolated from Jordanian rock varnish, emphasizing the value of WGS in understanding microbial diversity and adaptation in extreme environments.},
}

@article {pmid39574409,
year = {2024},
author = {Sun, B and Pashkova, L and Pieters, PA and Harke, AS and Mohite, OS and Santos, A and Zielinski, DC and Palsson, BO and Phaneuf, PV},
title = {PanKB: An interactive microbial pangenome knowledgebase for research, biotechnological innovation, and knowledge mining.},
journal = {Nucleic acids research},
volume = {},
number = {},
pages = {},
doi = {10.1093/nar/gkae1042},
pmid = {39574409},
issn = {1362-4962},
support = {//Novo Nordisk Foundation/ ; NNF20CC0035580//Technical University of Denmark/ ; },
abstract = {The exponential growth of microbial genome data presents unprecedented opportunities for unlocking the potential of microorganisms. The burgeoning field of pangenomics offers a framework for extracting insights from this big biological data. Recent advances in microbial pangenomic research have generated substantial data and literature, yielding valuable knowledge across diverse microbial species. PanKB (pankb.org), a knowledgebase designed for microbial pangenomics research and biotechnological applications, was built to capitalize on this wealth of information. PanKB currently includes 51 pangenomes from 8 industrially relevant microbial families, comprising 8402 genomes, over 500 000 genes and over 7M mutations. To describe this data, PanKB implements four main components: (1) Interactive pangenomic analytics to facilitate exploration, intuition, and potential discoveries; (2) Alleleomic analytics, a pangenomic-scale analysis of variants, providing insights into intra-species sequence variation and potential mutations for applications; (3) A global search function enabling broad and deep investigations across pangenomes to power research and bioengineering workflows; (4) A bibliome of 833 open-access pangenomic papers and an interface with an LLM that can answer in-depth questions using its knowledge. PanKB empowers researchers and bioengineers to harness the potential of microbial pangenomics and serves as a valuable resource bridging the gap between pangenomic data and practical applications.},
}

@article {pmid39565199,
year = {2024},
author = {Mudge, JM and Carbonell-Sala, S and Diekhans, M and Martinez, JG and Hunt, T and Jungreis, I and Loveland, JE and Arnan, C and Barnes, I and Bennett, R and Berry, A and Bignell, A and Cerdán-Vélez, D and Cochran, K and Cortés, LT and Davidson, C and Donaldson, S and Dursun, C and Fatima, R and Hardy, M and Hebbar, P and Hollis, Z and James, BT and Jiang, Y and Johnson, R and Kaur, G and Kay, M and Mangan, RJ and Maquedano, M and Gómez, LM and Mathlouthi, N and Merritt, R and Ni, P and Palumbo, E and Perteghella, T and Pozo, F and Raj, S and Sisu, C and Steed, E and Sumathipala, D and Suner, MM and Uszczynska-Ratajczak, B and Wass, E and Yang, YT and Zhang, D and Finn, RD and Gerstein, M and Guigó, R and Hubbard, TJP and Kellis, M and Kundaje, A and Paten, B and Tress, ML and Birney, E and Martin, FJ and Frankish, A},
title = {GENCODE 2025: reference gene annotation for human and mouse.},
journal = {Nucleic acids research},
volume = {},
number = {},
pages = {},
doi = {10.1093/nar/gkae1078},
pmid = {39565199},
issn = {1362-4962},
support = {U24HG007234/HG/NHGRI NIH HHS/United States ; /NH/NIH HHS/United States ; WT222155/Z/20/Z/WT_/Wellcome Trust/United Kingdom ; //European Molecular Biology Laboratory/ ; 2021/42/E/NZ2/00434//National Science Center/ ; },
abstract = {GENCODE produces comprehensive reference gene annotation for human and mouse. Entering its twentieth year, the project remains highly active as new technologies and methodologies allow us to catalog the genome at ever-increasing granularity. In particular, long-read transcriptome sequencing enables us to identify large numbers of missing transcripts and to substantially improve existing models, and our long non-coding RNA catalogs have undergone a dramatic expansion and reconfiguration as a result. Meanwhile, we are incorporating data from state-of-the-art proteomics and Ribo-seq experiments to fine-tune our annotation of translated sequences, while further insights into function can be gained from multi-genome alignments that grow richer as more species' genomes are sequenced. Such methodologies are combined into a fully integrated annotation workflow. However, the increasing complexity of our resources can present usability challenges, and we are resolving these with the creation of filtered genesets such as MANE Select and GENCODE Primary. The next challenge is to propagate annotations throughout multiple human and mouse genomes, as we enter the pangenome era. Our resources are freely available at our web portal www.gencodegenes.org, and via the Ensembl and UCSC genome browsers.},
}

@article {pmid39565095,
year = {2024},
author = {Bulka, O and Mahadevan, R and Edwards, EA},
title = {Pangenomic insights into Dehalobacter evolution and acquisition of functional genes for bioremediation.},
journal = {Microbial genomics},
volume = {10},
number = {11},
pages = {},
doi = {10.1099/mgen.0.001324},
pmid = {39565095},
issn = {2057-5858},
mesh = {*Biodegradation, Environmental ; *Phylogeny ; *Genome, Bacterial ; Evolution, Molecular ; Bacterial Proteins/genetics/metabolism ; Genomics ; Gene Transfer, Horizontal ; Metagenome ; },
abstract = {Dehalobacter is a genus of organohalide-respiring bacteria that is recognized for its fastidious growth using reductive dehalogenases (RDases). In the SC05 culture, however, a Dehalobacter population also mineralizes dichloromethane (DCM) produced by chloroform dechlorination using the mec cassette, just downstream of its active RDase. A closed genome of this DCM-mineralizing lineage has previously evaded assembly. Here, we present the genomes of two novel Dehalobacter strains, each of which was assembled from the metagenome of a distinct subculture from SC05. A pangenomic analysis of the Dehalobacter genus, including RDase synteny and phylogenomics, reveals at least five species of Dehalobacter based on average nucleotide identity, RDase and core gene synteny, as well as differential functional genes. An integration hotspot is also pinpointed in the Dehalobacter genome, in which many recombinase islands have accumulated. This nested recombinase island encodes the active RDase and mec cassette in both SC05 Dehalobacter genomes, indicating the transfer of key functional genes between species of Dehalobacter. Horizontal gene transfer between these two novel Dehalobacter strains has implications for the evolutionary history within the SC05 subcultures and of the Dehalobacter genus as a whole, especially regarding adaptation to anthropogenic chemicals.},
}

*Biodegradation, Environmental
*Phylogeny
*Genome, Bacterial
Evolution, Molecular
Bacterial Proteins/genetics/metabolism
Genomics
Gene Transfer, Horizontal
Metagenome

@article {pmid39565084,
year = {2024},
author = {Yu, H and Wang, S and Wang, L and Wu, W and Xu, W and Wu, S and Li, X and Xu, W and Huang, Z and Lin, Y and Wang, H},
title = {Pan-genomic characterization and structural variant analysis reveal insights into spore development and species diversity in Ganoderma.},
journal = {Microbial genomics},
volume = {10},
number = {11},
pages = {},
doi = {10.1099/mgen.0.001328},
pmid = {39565084},
issn = {2057-5858},
mesh = {*Ganoderma/genetics/classification ; *Spores, Fungal/genetics ; *Genome, Fungal ; Phylogeny ; Genomics ; Genetic Variation ; Fungal Proteins/genetics ; },
abstract = {Understanding the genomic diversity and functional implications of Ganoderma species is crucial for elucidating their evolutionary history and biotechnological potential. Here, we present the first pan-genomic analysis of Ganoderma spp., combining five newly sequenced genomes with ten publicly available genomes. Our comprehensive comparative study unveiled a rich genomic landscape, identifying core genes shared among all Ganoderma strains and species-specific gene sets. Additionally, we identified structural variants impacting the expression of key genes, including insights into the MSH4 gene involved in DNA repair and recombination processes, which exhibits a 440 bp insertion in the promoter region and a leucine-to-serine mutation in the gene body, potentially increasing spore production in the S3 strain. Overall, our study provides valuable insights into the genomic architecture and functional diversity of Ganoderma, paving the way for further research on its evolutionary dynamics, biotechnological applications and pharmaceutical potential.},
}

*Ganoderma/genetics/classification
*Spores, Fungal/genetics
*Genome, Fungal
Phylogeny
Genomics
Genetic Variation
Fungal Proteins/genetics

@article {pmid39558187,
year = {2024},
author = {Hamilton, JP and Li, C and Buell, CR},
title = {The rice genome annotation project: an updated database for mining the rice genome.},
journal = {Nucleic acids research},
volume = {},
number = {},
pages = {},
doi = {10.1093/nar/gkae1061},
pmid = {39558187},
issn = {1362-4962},
support = {//University of Georgia/ ; //Georgia Research Alliance/ ; //Georgia Seed Development/ ; },
abstract = {Rice (Oryza sativa L.) is a major cereal crop that provides calories across the world. With a small genome, rice has been used extensively as a model for genetic and genomic studies in the Poaceae. Since the release of the first rice genome sequence in 2002, an improved reference genome assembly, multiple whole genome assemblies, extensive gene expression profiles, and resequencing data from over 3000 rice accessions have been generated. To facilitate access to the rice genome for plant biologists, we updated the Rice Genome Annotation Project database (RGAP; https://rice.uga.edu) with new datasets including 16 whole genome rice assemblies and sequence variants generated from multiple rice pan-genome projects including the 3000 Rice Genomes Project. We updated gene expression abundance data with 80 RNA-sequencing datasets and to facilitate gene function discovery, performed gene coexpression resulting in 39 coexpression modules that capture highly connected sets of co-regulated genes. To facilitate comparative genome analyses, 32 335 syntelogs were identified between the Nipponbare reference genome and other rice genomes and 19 371 syntelogs were identified between Nipponbare and four other Poaceae genomes. Infrastructure improvements to the RGAP database include an upgraded genome browser and data access portals, enhanced website security and increased performance of the website.},
}

@article {pmid39557856,
year = {2024},
author = {Long, W and He, Q and Wang, Y and Wang, Y and Wang, J and Yuan, Z and Wang, M and Chen, W and Luo, L and Luo, L and Xu, W and Li, Y and Li, W and Yan, L and Cai, Y and Du, H and Xie, H},
title = {Genome evolution and diversity of wild and cultivated rice species.},
journal = {Nature communications},
volume = {15},
number = {1},
pages = {9994},
pmid = {39557856},
issn = {2041-1723},
support = {CARS-01-08//Earmarked Fund for China Agriculture Research System/ ; 31960400//National Natural Science Foundation of China (National Science Foundation of China)/ ; },
mesh = {*Oryza/genetics ; *Genome, Plant ; *Evolution, Molecular ; *Genetic Variation ; *Crops, Agricultural/genetics ; Domestication ; Disease Resistance/genetics ; Phylogeny ; Plant Breeding ; Multigene Family/genetics ; Genes, Plant/genetics ; },
abstract = {Wild species of crops serve as a valuable germplasm resource for breeding of modern cultivars. Rice (Oryza sativa L.) is a vital global staple food. However, research on genome evolution and diversity of wild rice species remains limited. Here, we present nearly complete genomes of 13 representative wild rice species. By integrating with four previously published genomes for pangenome analysis, a total of 101,723 gene families are identified across the genus, including 9834 (9.67%) core gene families. Additionally, 63,881 gene families absent in cultivated rice species but present in wild rice species are discovered. Extensive structural rearrangements, sub-genomes exchanges, widespread allelic variations, and regulatory sequence variations are observed in wild rice species. Interestingly, expanded but less diverse disease resistance genes in the genomes of cultivated rice, likely due to the loss of some resistance genes and the fixing and amplification of genes encoding resistance genes to specific diseases during domestication and artificial selection. This study not only reveals natural variations valuable for gene-level studies and breeding selection but also enhances our understanding on rice evolution and domestication.},
}

*Oryza/genetics
*Genome, Plant
*Evolution, Molecular
*Genetic Variation
*Crops, Agricultural/genetics
Domestication
Disease Resistance/genetics
Phylogeny
Plant Breeding
Multigene Family/genetics
Genes, Plant/genetics

@article {pmid39555885,
year = {2024},
author = {Benarroch, L},
title = {[The pangenome integrates the vast genetic diversity of the human population].},
journal = {Medecine sciences : M/S},
volume = {40 Hors série n° 1},
number = {},
pages = {75},
doi = {10.1051/medsci/2024126},
pmid = {39555885},
issn = {1958-5381},
}

@article {pmid39554176,
year = {2024},
author = {Dobhal, S and Hugouvieux-Cotte-Pattat, N and Arizala, D and Sari, GB and Chuang, SC and Alvarez, AM and Arif, M},
title = {Dickeya ananae sp. nov., pectinolytic bacterium isolated from pineapple (Ananas comosus).},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.10.29.620964},
pmid = {39554176},
issn = {2692-8205},
abstract = {Recently, species clustering within Dickeya zeae has been identified as complex, encompassing validly published names, including D. oryzae and D. parazeae , with some strains potentially delineating new species. In this study, genomes of strains isolated from a bacterial heart rot outbreak in pineapple (Ananas comosus var. comosus) on Oahu, Hawaii, along with two strains from pineapple in Malaysia, were sequenced. Orthologous average nucleotide identity (ANI) and digital DNA-DNA hybridization (dDDH) values among the sequenced genomes ranged from 98.93-99.9% and 91.8-99.9%, respectively, supporting the classification of seven strains within the same species. Comparisons of ANI and dDDH values between these seven strains and type strains of D. zeae, D. parazeae, and D. oryzae ranged from 94.4-95.9% and 57.2-66.5%, respectively. These values fall below the proposed boundaries for new species designation, supporting the delineation of a novel species. Phylogenetic analyses, including 16S rRNA, gapA , multi-locus sequence analysis (MLSA) of 10 housekeeping genes, whole-genome, and pangenome analyses, were concordant and revealed a distinct monophyletic clade, separating these strains from other members of the D. zeae complex, with D. oryzae as the closest relative. Notably, a nitrogen fixation gene cluster comprising 28 genes, similar to the Klebsiella spp. nitrogenase gene cluster, was found in the genome of the seven pineapple strains. Based on polyphasic approaches, including ANI, dDDH, biochemical, physiological, and phylogenomic analyses, we propose the reclassification in a new species of the five pineapple strains from Hawaii A5391, A5410 [T] , A5611, A6136, and A6137, together with the two pineapple strains from Malaysia CFBP 1272 and CFBP 1278, previously classified as D. zeae . We propose the name Dickeya ananae sp. nov. for this taxon, represented by the type strain A5410 [T] (= ICMP 25020 [T] = LMG 33197 [T]).},
}

@article {pmid39554168,
year = {2024},
author = {Chandra, G and Hossen, MH and Scholz, S and Dilthey, AT and Gibney, D and Jain, C},
title = {Integer programming framework for pangenome-based genome inference.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.10.27.620212},
pmid = {39554168},
issn = {2692-8205},
abstract = {UNLABELLED: Affordable genotyping methods are essential in genomics. Commonly used genotyping methods primarily support single nucleotide variants and short indels but neglect structural variants. Additionally, accuracy of read alignments to a reference genome is unreliable in highly polymorphic and repetitive regions, further impacting genotyping performance. Recent works highlight the advantage of haplotype-resolved pangenome graphs in addressing these challenges. Building on these developments, we propose a rigorous alignment-free genotyping framework. Our formulation seeks a path through the pangenome graph that maximizes the matches between the path and substrings of sequencing reads (e.g., k -mers) while minimizing recombination events (haplotype switches) along the path. We prove that this problem is NP-Hard and develop efficient integer-programming solutions. We benchmarked the algorithm using downsampled short-read datasets from homozygous human cell lines with coverage ranging from 0.1× to 10×. Our algorithm accurately estimates complete major histocompatibility complex (MHC) haplotype sequences with small edit distances from the ground-truth sequences, providing a significant advantage over existing methods on low-coverage inputs. Although our algorithm is designed for haploid samples, we discuss future extensions to diploid samples.

IMPLEMENTATION: https://github.com/at-cg/PHI.},
}

@article {pmid39554056,
year = {2024},
author = {Brown, NK and Shivakumar, VS and Langmead, B},
title = {Improved pangenomic classification accuracy with chain statistics.},
journal = {bioRxiv : the preprint server for biology},
volume = {},
number = {},
pages = {},
doi = {10.1101/2024.10.29.620953},
pmid = {39554056},
issn = {2692-8205},
abstract = {Compressed full-text indexes enable efficient sequence classification against a pangenome or tree-of-life index. Past work on compressed-index classification used matching statistics or pseudo-matching lengths to capture the fine-grained co-linearity of exact matches. But these fail to capture coarse-grained information about whether seeds appear co-linearly in the reference. We present a novel approach that additionally obtains coarse-grained co-linearity ("chain") statistics. We do this without using a chaining algorithm, which would require superlinear time in the number of matches. We start with a collection of strings, avoiding the multiple-alignment step required by graph approaches. We rapidly compute multi-maximal unique matches (multi-MUMs) and identify BWT sub-runs that correspond to these multi-MUMs. From these, we select those that can be "tunneled," and mark these with the corresponding multi-MUM identifiers. This yields an ℴ(r + n/d)-space index for a collection of d sequences having a length- n BWT consisting of r maximal equal-character runs. Using the index, we simultaneously compute fine-grained matching statistics and coarse-grained chain statistics in linear time with respect to query length. We found that this substantially improves classification accuracy compared to past compressed-indexing approaches and reaches the same level of accuracy as less efficient alignmentbased methods.},
}

@article {pmid39552065,
year = {2024},
author = {Matthews, CA and Watson-Haigh, NS and Burton, RA and Sheppard, AE},
title = {A gentle introduction to pangenomics.},
journal = {Briefings in bioinformatics},
volume = {25},
number = {6},
pages = {},
doi = {10.1093/bib/bbae588},
pmid = {39552065},
issn = {1477-4054},
mesh = {*Genomics/methods ; Humans ; Genome ; },
abstract = {Pangenomes have emerged in response to limitations associated with traditional linear reference genomes. In contrast to a traditional reference that is (usually) assembled from a single individual, pangenomes aim to represent all of the genomic variation found in a group of organisms. The term 'pangenome' is currently used to describe multiple different types of genomic information, and limited language is available to differentiate between them. This is frustrating for researchers working in the field and confusing for researchers new to the field. Here, we provide an introduction to pangenomics relevant to both prokaryotic and eukaryotic organisms and propose a formalization of the language used to describe pangenomes (see the Glossary) to improve the specificity of discussion in the field.},
}

*Genomics/methods
Humans
Genome

@article {pmid39548374,
year = {2024},
author = {Heppert, JK and Awori, RM and Cao, M and Chen, G and McLeish, J and Goodrich-Blair, H},
title = {Analyses of Xenorhabdus griffiniae genomes reveal two distinct sub-species that display intra-species variation due to prophages.},
journal = {BMC genomics},
volume = {25},
number = {1},
pages = {1087},
pmid = {39548374},
issn = {1471-2164},
mesh = {*Xenorhabdus/genetics/classification ; *Prophages/genetics ; *Genome, Bacterial ; *Phylogeny ; Symbiosis ; Animals ; Genomics/methods ; Genetic Variation ; },
abstract = {BACKGROUND: Nematodes of the genus Steinernema and their Xenorhabdus bacterial symbionts are lethal entomopathogens that are useful in the biocontrol of insect pests, as sources of diverse natural products, and as research models for mutualism and parasitism. Xenorhabdus play a central role in all aspects of the Steinernema lifecycle, and a deeper understanding of their genomes therefore has the potential to spur advances in each of these applications.

RESULTS: Here, we report a comparative genomics analysis of Xenorhabdus griffiniae, including the symbiont of Steinernema hermaphroditum nematodes, for which genetic and genomic tools are being developed. We sequenced and assembled circularized genomes for three Xenorhabdus strains: HGB2511, ID10 and TH1. We then determined their relationships to other Xenorhabdus and delineated their species via phylogenomic analyses, concluding that HGB2511 and ID10 are Xenorhabdus griffiniae while TH1 is a novel species. These additions to the existing X. griffiniae landscape further allowed for the identification of two subspecies within the clade. Consistent with other Xenorhabdus, the analysed X. griffiniae genomes each encode a wide array of antimicrobials and virulence-related proteins. Comparative genomic analyses, including the creation of a pangenome, revealed that a large amount of the intraspecies variation in X. griffiniae is contained within the mobilome and attributable to prophage loci. In addition, CRISPR arrays, secondary metabolite potential and toxin genes all varied among strains within the X. griffiniae species.

CONCLUSIONS: Our findings suggest that phage-related genes drive the genomic diversity in closely related Xenorhabdus symbionts, and that these may underlie some of the traits most associated with the lifestyle and survival of entomopathogenic nematodes and their bacteria: virulence and competition. This study establishes a broad knowledge base for further exploration of not only the relationships between X. griffiniae species and their nematode hosts but also the molecular mechanisms that underlie their entomopathogenic lifestyle.},
}

*Xenorhabdus/genetics/classification
*Prophages/genetics
*Genome, Bacterial
*Phylogeny
Symbiosis
Animals
Genomics/methods
Genetic Variation

@article {pmid39547942,
year = {2024},
author = {Zhang, LJ and Wang, N and Huang, W and Wu, LY and Song, B and Wang, SL and Sheng, JD and Wang, W},
title = {Genome-based analysis of biosynthetic potential from antimycotic Streptomyces rochei strain A144.},
journal = {FEMS microbiology letters},
volume = {},
number = {},
pages = {},
doi = {10.1093/femsle/fnae097},
pmid = {39547942},
issn = {1574-6968},
abstract = {Streptomyces rochei is a species of Streptomyces with a diverse range of biological activities. S. rochei strain A144 was isolated from desert soils and exhibits antagonistic activity against several plant pathogenic fungi. The genome of S. rochei A144 was sequenced and revealed the presence of one linear chromosome and one plasmid. The chromosome length was found to be 8,085,429 bp, with a GC content of 72.62%, while the Plas1 length was 177,399 bp, with a GC content of 69.08%. Comparative genomics was employed to analyse the S. rochei group. There is a high degree of collinearity between the genomes of S. rochei strains. Based on pan-genome analysis, S. rochei has 10,315 gene families, including 4051 core and 2322 unique genes. AntiSMASH was used to identify the gene clusters for secondary metabolites, identifying 33 secondary metabolite genes on the A144 genome. Among them, 18 clusters were found to be >70% identical to known biosynthetic gene clusters (BGCs), indicating that A144 has the potential to synthesize secondary metabolites. The majority of the BGCs were found to be conserved within the S. rochei group, including those encoding polyketide synthases (PKS), terpenes, non-ribosomal peptide synthetases (NRPS), other ribosomally synthesised and post-translationally modified peptides (RiPP), nicotianamine-iron transporters, lanthipeptides, and a few other types. The S. rochei group can be a potential genetic source of useful secondary metabolites with applications in medicine and biotechnology.},
}

@article {pmid39546548,
year = {2024},
author = {Foo, A and Brettell, LE and Nichols, HL and , and Medina Muñoz, M and Lysne, JA and Dhokiya, V and Hoque, AF and Brackney, DE and Caragata, EP and Hutchinson, ML and Jacobs-Lorena, M and Lampe, DJ and Martin, E and Valiente Moro, C and Povelones, M and Short, SM and Steven, B and Xu, J and Paustian, TD and Rondon, MR and Hughes, GL and Coon, KL and Heinz, E},
title = {MosAIC: An annotated collection of mosquito-associated bacteria with high-quality genome assemblies.},
journal = {PLoS biology},
volume = {22},
number = {11},
pages = {e3002897},
doi = {10.1371/journal.pbio.3002897},
pmid = {39546548},
issn = {1545-7885},
abstract = {Mosquitoes transmit medically important human pathogens, including viruses like dengue virus and parasites such as Plasmodium spp., the causative agent of malaria. Mosquito microbiomes are critically important for the ability of mosquitoes to transmit disease-causing agents. However, while large collections of bacterial isolates and genomic data exist for vertebrate microbiomes, the vast majority of work in mosquitoes to date is based on 16S rRNA gene amplicon data that provides limited taxonomic resolution and no functional information. To address this gap and facilitate future studies using experimental microbiome manipulations, we generated a bacterial Mosquito-Associated Isolate Collection (MosAIC) consisting of 392 bacterial isolates with extensive metadata and high-quality draft genome assemblies that are publicly available, both isolates and sequence data, for use by the scientific community. MosAIC encompasses 142 species spanning 29 bacterial families, with members of the Enterobacteriaceae comprising 40% of the collection. Phylogenomic analysis of 3 genera, Enterobacter, Serratia, and Elizabethkingia, reveal lineages of mosquito-associated bacteria isolated from different mosquito species in multiple laboratories. Investigation into species' pangenomes further reveals clusters of genes specific to these lineages, which are of interest for future work to test for functions connected to mosquito host association. Altogether, we describe the generation of a physical collection of mosquito-associated bacterial isolates, their genomic data, and analyses of selected groups in context of genome data from closely related isolates, providing a unique, highly valuable resource for research on bacterial colonisation and adaptation within mosquito hosts. Future efforts will expand the collection to include broader geographic and host species representation, especially from individuals collected from field populations, as well as other mosquito-associated microbes, including fungi, archaea, and protozoa.},
}

@article {pmid39545504,
year = {2024},
author = {Bird, KA and Brock, JR and Grabowski, PP and Harder, AM and Healy, A and Shu, S and Barry, K and Boston, L and Daum, C and Guo, J and Lipzen, A and Walstead, R and Grimwood, J and Schmutz, J and Lu, C and Comai, L and McKay, JK and Pires, JC and Edger, PP and Lovell, JT and Kliebenstein, DJ},
title = {Allopolyploidy expanded gene content but not pangenomic variation in the hexaploid oilseed Camelina sativa.},
journal = {Genetics},
volume = {},
number = {},
pages = {},
doi = {10.1093/genetics/iyae183},
pmid = {39545504},
issn = {1943-2631},
abstract = {Ancient whole-genome duplications (WGDs) are believed to facilitate novelty and adaptation by providing the raw fuel for new genes. However, it is unclear how recent WGDs may contribute to evolvability within recent polyploids. Hybridization accompanying some WGDs may combine divergent gene content among diploid species. Some theory and evidence suggest that polyploids have a greater accumulation and tolerance of gene presence-absence and genomic structural variation, but it is unclear to what extent either is true. To test how recent polyploidy may influence pangenomic variation, we sequenced, assembled, and annotated twelve complete, chromosome-scale genomes of Camelina sativa, an allohexaploid biofuel crop with three distinct subgenomes. Using pangenomic comparative analyses, we characterized gene presence-absence and genomic structural variation both within and between the subgenomes. We found over 75% of ortholog gene clusters are core in Camelina sativa and <10% of sequence space was affected by genomic structural rearrangements. In contrast, 19% of gene clusters were unique to one subgenome, and the majority of these were Camelina-specific (no ortholog in Arabidopsis). We identified an inversion that may contribute to vernalization requirements in winter-type Camelina, and an enrichment of Camelina-specific genes with enzymatic processes related to seed oil quality and Camelina's unique glucosinolate profile. Genes related to these traits exhibited little presence-absence variation. Our results reveal minimal pangenomic variation in this species, and instead show how hybridization accompanied by WGD may benefit polyploids by merging diverged gene content of different species.},
}

@article {pmid39544963,
year = {2024},
author = {Wong, HL and Bulzu, PA and Ghai, R and Chiriac, MC and Salcher, MM},
title = {Ubiquitous genome streamlined Acidobacteriota in freshwater environments.},
journal = {ISME communications},
volume = {4},
number = {1},
pages = {ycae124},
pmid = {39544963},
issn = {2730-6151},
abstract = {Acidobacteriota are abundant in soil, peatlands, and sediments, but their ecology in freshwater environments remains understudied. UBA12189, an Acidobacteriota genus, is an uncultivated, genome-streamlined lineage with a small genome size found in aquatic environments where detailed genomic analyses are lacking. Here, we analyzed 66 MAGs of UBA12189 (including one complete genome) from freshwater lakes and rivers in Europe, North America, and Asia. UBA12189 has small genome sizes (<1.4 Mbp), low GC content, and a highly diverse pangenome. In freshwater lakes, this bacterial lineage is abundant from the surface waters (epilimnion) down to a 300-m depth (hypolimnion). UBA12189 appears to be free-living from CARD-FISH analysis. When compared to other genome-streamlined bacteria such as Nanopelagicales and Methylopumilus, genome reduction has caused UBA12189 to have a more limited metabolic repertoire in carbon, sulfur, and nitrogen metabolisms, limited numbers of membrane transporters, as well as a higher degree of auxotrophy for various amino acids, vitamins, and reduced sulfur. Despite having reduced genomes, UBA12189 encodes proteorhodopsin, complete biosynthesis pathways for heme and vitamin K2, cbb3-type cytochrome c oxidases, and heme-requiring enzymes. These genes may give a selective advantage during the genome streamlining process. We propose the new genus Acidiparvus, with two new species named "A. lacustris" and "A. fluvialis". Acidiparvus is the first described genome-streamlined lineage under the phylum Acidobacteriota, which is a free-living, slow-growing scavenger in freshwater environments.},
}

@article {pmid39537924,
year = {2024},
author = {Jayakodi, M and Lu, Q and Pidon, H and Rabanus-Wallace, MT and Bayer, M and Lux, T and Guo, Y and Jaegle, B and Badea, A and Bekele, W and Brar, GS and Braune, K and Bunk, B and Chalmers, KJ and Chapman, B and Jørgensen, ME and Feng, JW and Feser, M and Fiebig, A and Gundlach, H and Guo, W and Haberer, G and Hansson, M and Himmelbach, A and Hoffie, I and Hoffie, RE and Hu, H and Isobe, S and König, P and Kale, SM and Kamal, N and Keeble-Gagnère, G and Keller, B and Knauft, M and Koppolu, R and Krattinger, SG and Kumlehn, J and Langridge, P and Li, C and Marone, MP and Maurer, A and Mayer, KFX and Melzer, M and Muehlbauer, GJ and Murozuka, E and Padmarasu, S and Perovic, D and Pillen, K and Pin, PA and Pozniak, CJ and Ramsay, L and Pedas, PR and Rutten, T and Sakuma, S and Sato, K and Schüler, D and Schmutzer, T and Scholz, U and Schreiber, M and Shirasawa, K and Simpson, C and Skadhauge, B and Spannagl, M and Steffenson, BJ and Thomsen, HC and Tibbits, JF and Nielsen, MTS and Trautewig, C and Vequaud, D and Voss, C and Wang, P and Waugh, R and Westcott, S and Rasmussen, MW and Zhang, R and Zhang, XQ and Wicker, T and Dockter, C and Mascher, M and Stein, N},
title = {Structural variation in the pangenome of wild and domesticated barley.},
journal = {Nature},
volume = {},
number = {},
pages = {},
pmid = {39537924},
issn = {1476-4687},
abstract = {Pangenomes are collections of annotated genome sequences of multiple individuals of a species[1]. The structural variants uncovered by these datasets are a major asset to genetic analysis in crop plants[2]. Here we report a pangenome of barley comprising long-read sequence assemblies of 76 wild and domesticated genomes and short-read sequence data of 1,315 genotypes. An expanded catalogue of sequence variation in the crop includes structurally complex loci that are rich in gene copy number variation. To demonstrate the utility of the pangenome, we focus on four loci involved in disease resistance, plant architecture, nutrient release and trichome development. Novel allelic variation at a powdery mildew resistance locus and population-specific copy number gains in a regulator of vegetative branching were found. Expansion of a family of starch-cleaving enzymes in elite malting barleys was linked to shifts in enzymatic activity in micro-malting trials. Deletion of an enhancer motif is likely to change the developmental trajectory of the hairy appendages on barley grains. Our findings indicate that allelic diversity at structurally complex loci may have helped crop plants to adapt to new selective regimes in agricultural ecosystems.},
}

@article {pmid39535885,
year = {2024},
author = {Du, H and Zhuo, Y and Lu, S and Li, W and Zhou, L and Sun, F and Liu, G and Liu, JF},
title = {Pangenome Reveals Gene Content Variations and Structural Variants Contributing to Pig Characteristics.},
journal = {Genomics, proteomics & bioinformatics},
volume = {},
number = {},
pages = {},
doi = {10.1093/gpbjnl/qzae081},
pmid = {39535885},
issn = {2210-3244},
abstract = {Pigs are among the most essential sources of high-quality protein in human diets. Structural variants (SVs) are a major source of genetic variants associated with diverse traits and evolutionary events. However, the current linear reference genome of pigs limits the presentation of position information for SVs. In this study, we generated a pangenome of pigs and a genome variation map of 599 deep-sequenced genomes across Eurasia. Moreover, a section-wide gene repertoire was constructed, which indicated that core genes were more evolutionarily conserved than variable genes. Subsequently, we identified 546,137 SVs, their enrichment regions, and relationships with genomic features and found significant divergence across Eurasian pigs. More importantly, the pangenome-detected SVs could complement heritability estimates and genome-wide association studies based only on single nucleotide polymorphisms. Among the SVs shaped by selection, we identified an insertion in the promoter region of the TBX19 gene, which may be related to the development, growth, and timidity traits of Asian pigs and may affect the gene expression. Our constructed pig pangenome and the identified SVs provide rich resources for future functional genomic research on pigs.},
}

@article {pmid39535230,
year = {2024},
author = {van Westerhoven, AC and Dijkstra, J and Aznar Palop, JL and Wissink, K and Bell, J and Kema, GHJ and Seidl, MF},
title = {Frequent genetic exchanges revealed by a pan-mitogenome graph of a fungal plant pathogen.},
journal = {mBio},
volume = {},
number = {},
pages = {e0275824},
doi = {10.1128/mbio.02758-24},
pmid = {39535230},
issn = {2150-7511},
abstract = {Mitochondria are present in almost all eukaryotic lineages. The mitochondrial genomes (mitogenomes) evolve separately from nuclear genomes, and they can therefore provide relevant insights into the evolution of their host species. Fusarium oxysporum is a major fungal plant pathogen that is assumed to reproduce clonally. However, horizontal chromosome transfer between strains can occur through heterokaryon formation, and recently, signs of sexual recombination have been observed. Similarly, signs of recombination in F. oxysporum mitogenomes challenged the prevailing assumption of clonal reproduction in this species. Here, we construct, to our knowledge, the first fungal pan-mitogenome graph of nearly 500 F. oxysporum mitogenome assemblies to uncover the variation and evolution. In general, the gene order of fungal mitogenomes is not well conserved, yet the mitogenome of F. oxysporum and related species are highly colinear. We observed two strikingly contrasting regions in the F. oxysporum pan-mitogenome, comprising a highly conserved core mitogenome and a long variable region (6-16 kb in size), of which we identified three distinct types. The pan-mitogenome graph reveals that only five intron insertions occurred in the core mitogenome and that the long variable regions drive the difference between mitogenomes. Moreover, we observed that their evolution is neither concurrent with the core mitogenome nor with the nuclear genome. Our large-scale analysis of long variable regions uncovers frequent recombination between mitogenomes, even between strains that belong to different taxonomic clades. This challenges the common assumption of incompatibility between genetically diverse F. oxysporum strains and provides new insights into the evolution of this fungal species.IMPORTANCEInsights into plant pathogen evolution is essential for the understanding and management of disease. Fusarium oxysporum is a major fungal pathogen that can infect many economically important crops. Pathogenicity can be transferred between strains by the horizontal transfer of pathogenicity chromosomes. The fungus has been thought to evolve clonally, yet recent evidence suggests active sexual recombination between related isolates, which could at least partially explain the horizontal transfer of pathogenicity chromosomes. By constructing a pan-genome graph of nearly 500 mitochondrial genomes, we describe the genetic variation of mitochondria in unprecedented detail and demonstrate frequent mitochondrial recombination. Importantly, recombination can occur between genetically diverse isolates from distinct taxonomic clades and thus can shed light on genetic exchange between fungal strains.},
}

@article {pmid39535198,
year = {2024},
author = {Davis, SC and Cerra, J and Williams, LE},
title = {Comparative genomics of obligate predatory bacteria belonging to phylum Bdellovibrionota highlights distribution and predicted functions of lineage-specific protein families.},
journal = {mSphere},
volume = {},
number = {},
pages = {e0068024},
doi = {10.1128/msphere.00680-24},
pmid = {39535198},
issn = {2379-5042},
abstract = {Comparative genomics of predatory bacteria is important to understand their ecology and evolution and explore their potential to treat drug-resistant infections. We compared chromosomes of 18 obligate predators from phylum Bdellovibrionota (16 intraperiplasmic, two epibiotic) and 15 non-predatory bacteria. Phylogenetics of conserved single-copy genes and analysis of genome-wide average amino acid identity provide evidence for at least five Bdellovibrio species and support recent reclassifications of predatory taxa. To define shared and differential genome content, we grouped predicted protein sequences into gene clusters based on sequence similarity. Few gene clusters are shared by all 33 bacteria or all 18 predatory bacteria; however, we identified gene clusters conserved within lineages, such as intraperiplasmic Bdellovibrio, and not found in other bacteria. Many of these are predicted to function in cell envelope biogenesis, signal transduction, and other roles important for predatory lifestyles. Among intraperiplasmic Bdellovibrio, we detected high abundance of gene clusters predicted to encode transglycosylases, endopeptidases, and lysozymes, and we identified six gene clusters (amidase, L,D-transpeptidase, four transglycosylases) with evidence of recent gene duplication and gene family expansion. Focusing on peptidoglycan metabolism, we defined a suite of gene clusters that include peptidoglycan-degrading and -modifying enzymes and occur only in predatory bacteria, suggesting these proteins may have evolved activities specific to predation. Our analyses highlight key genome content differences between obligate predatory bacteria and non-predatory relatives and identify gene clusters that may encode enzymes adapted to predatory lifestyles. These lineage-specific proteins are strong candidates for functional characterization to clarify their role in predation.IMPORTANCEEvolution of predation as a bacterial lifestyle involves selective pressure on and adaptation of enzymes that contribute to killing and digestion of prey bacteria, in some cases from within the prey itself. Such enzymes are a hallmark of obligate predatory bacteria belonging to phylum Bdellovibrionota, which includes the well-studied predator Bdellovibrio. By comparing protein sequences of obligate predatory bacteria and their non-predatory relatives, we define key genome content differences that distinguish bacterial predators and identify lineage-specific enzymes that may have evolved unique activities due to selective pressures related to a predatory lifestyle. In addition to providing insights into the ecology and evolution of predatory bacteria, comparative genomics studies, like this, can inform efforts to develop predatory bacteria and/or their enzymes as potential biocontrol agents to combat drug-resistant bacterial infections.},
}

@article {pmid39513706,
year = {2024},
author = {Lawal, OU and Bryan, N and Parreira, VR and Anderson, R and Chen, Y and Precious, M and Goodridge, L},
title = {Phylogenomics of novel clones of Aeromonas veronii recovered from a freshwater lake reveals unique biosynthetic gene clusters.},
journal = {Microbiology spectrum},
volume = {},
number = {},
pages = {e0117124},
doi = {10.1128/spectrum.01171-24},
pmid = {39513706},
issn = {2165-0497},
abstract = {UNLABELLED: Aquatic ecosystems serve as crucial reservoirs for pathogens and antimicrobial resistance genes, thus presenting a significant global health risk. Here, we investigated the phylogenomics of Aeromonas veronii from Lake Wilcox in Ontario. Among the 11 bacterial isolates, nine were identified as A. veronii. Notably, 67% of A. veronii isolates were potential human pathogens. Considerable genetic diversity was noted among the A. veronii isolates, suggesting the lake as a reservoir for multiple human pathogenic strains. Comparison of the A. veronii sequenced with global A. veronii genomes highlighted significant genetic diversity and suggests widespread dissemination of strains. All the isolates carried chromosomal genes encoding resistance to β-lactams. Although virulence gene content differed between human and non-human pathogenic strains, type III secretion systems was associated with human pathogenic isolates. The assessment of AMR genes in global isolates showed that β-lactam and tetracycline resistance genes were predominant. Although the machine learning-based pangenome-wide association approach performed did not yield any source-based genes, some genes were enriched in a few isolates from different sources. The mrkABCDF operon that mediates biofilm formation and genes encoding resistance to colistin, chloramphenicol, trimethoprim, and tetracycline were enriched in animal products, whereas macrolide resistance genes and Inc plasmid-types were linked to the aquatic environment. Novel biosynthetic gene clusters were identified, suggesting that A. veronii with varying pathogenic potential could produce unique secondary metabolites. There is a need for continuous tracking of pathogens in aquatic ecosystems to contribute to our understanding of their evolutionary dynamics and the ecological roles of their genetic elements.

IMPORTANCE: Lakes and other aquatic ecosystems can harbor harmful bacteria that can make people sick and resist antibiotics, posing a significant global health risk. In this study, we investigated Aeromonas veronii, a Gram-negative bacteria found in Lake Wilcox in Ontario. We used various techniques, including whole-genome sequencing (WGS), to analyze the bacteria and found that many of the isolates had the potential to cause human disease. We also discovered significant genetic diversity among the isolates, indicating that the lake may be a reservoir for multiple human pathogenic strains. All isolates carried genes that confer resistance to antibiotics, and some virulence genes were associated with human pathogenic isolates. This study highlights the importance of monitoring aquatic ecosystems for harmful bacteria to better understand their evolution, potential for human pathogenicity, and the ecological roles of their genetic elements. This knowledge can inform strategies for preventing the spread of antibiotic-resistant bacteria and protecting public health.},
}

@article {pmid39512798,
year = {2024},
author = {Verma, D and Satyanarayana, T and Dias, PJ},
title = {Editorial: Microbial comparative genomics and pangenomics: new tools, approaches and insights into gene and genome evolution.},
journal = {Frontiers in genetics},
volume = {15},
number = {},
pages = {1490645},
pmid = {39512798},
issn = {1664-8021},
}

@article {pmid39512589,
year = {2024},
author = {Podbielski, A and Köller, T and Warnke, P and Barrantes, I and Kreikemeyer, B},
title = {Whole genome sequencing distinguishes skin colonizing from infection-associated Cutibacterium acnes isolates.},
journal = {Frontiers in cellular and infection microbiology},
volume = {14},
number = {},
pages = {1433783},
pmid = {39512589},
issn = {2235-2988},
mesh = {Humans ; *Whole Genome Sequencing ; *Genome, Bacterial ; *Skin/microbiology ; *Phylogeny ; Propionibacterium acnes/genetics/isolation & purification/classification ; Prospective Studies ; Male ; Genotype ; Adult ; Female ; Polymorphism, Single Nucleotide ; Gram-Positive Bacterial Infections/microbiology ; },
abstract = {INTRODUCTION: Cutibacterium acnes can both be a helpful colonizer of the human skin as well as the causative agent of acne and purulent infections. Until today, it is a moot point whether there are C. acnes strains exclusively devoted to be part of the skin microbiome and others, that carry special features enabling them to cause disease. So far, the search for the molecular background of such diverse behavior has led to inconsistent results.

METHODS: In the present study, we prospectively collected C. acnes strains from 27 infected persons and 18 healthy controls employing rigid selection criteria to ensure their role as infectious agent or colonizer. The genome sequences from these strains were obtained and carefully controlled for quality.

RESULTS: Deduced traditional phylotyping assigned almost all superficial isolates to type IA1, while the clinical strains were evenly distributed between types IA1, IB, and II. Single locus sequence typing (SLST) showed a predominance of A1 type for the control strains, whereas 56% of the clinical isolates belonged to types A1, H1 and K8. Pangenome analysis from all the present strains and 30 published genomes indicated the presence of an open pangenome. Except for three isolates, the colonizing strains clustered in clades separate from the majority of clinical strains, while 4 clinical strains clustered with the control strains. Identical results were obtained by a single nucleotide polymorphism (SNP) analysis. However, there were no significant differences in virulence gene contents in both groups.

DISCUSSION: Genome-wide association studies (GWAS) from both the pangenome and SNP data consistently showed genomic differences between both groups located in metabolic pathway and DNA repair genes. Thus, the different behavior of colonizing and infectious C. acnes strains could be due to special metabolic capacities or flexibilities rather than specific virulence traits.},
}

Humans
*Whole Genome Sequencing
*Genome, Bacterial
*Skin/microbiology
*Phylogeny
Propionibacterium acnes/genetics/isolation & purification/classification
Prospective Studies
Male
Genotype
Adult
Female
Polymorphism, Single Nucleotide
Gram-Positive Bacterial Infections/microbiology

@article {pmid39510980,
year = {2024},
author = {Mohamedikbal, S and Al-Mamun, HA and Marsh, JI and Upadhyaya, S and Danilevicz, MF and Nguyen, HT and Valliyodan, B and Mahan, A and Batley, J and Edwards, D},
title = {Local haplotyping reveals insights into the genetic control of flowering time variation in wild and domesticated soybean.},
journal = {The plant genome},
volume = {},
number = {},
pages = {e20528},
doi = {10.1002/tpg2.20528},
pmid = {39510980},
issn = {1940-3372},
support = {//Australian Government and the Government of Western Australia/ ; DP200100762//Australian Research Council/ ; DP210100296//Australian Research Council/ ; //USDA Evans Allen Project/ ; },
abstract = {The timing of flowering in soybean [Glycine max (L.) Merr.], a key legume crop, is influenced by many factors, including daylight length or photoperiodic sensitivity, that affect crop yield, productivity, and geographical adaptation. Despite its importance, a comprehensive understanding of the local linkage landscape and allelic diversity within regions of the genome influencing flowering and contributing to phenotypic variation in subpopulations has been limited. This study addresses these gaps by conducting an in-depth trait association and linkage analysis coupled with local haplotyping using advanced bioinformatics tools, including crosshap, to characterize genomic variation using a pangenome dataset representing 915 domesticated and wild-type individuals. The association analysis identified eight significant loci on seven chromosomes. Moving beyond traditional association analysis, local haplotyping of targeted regions on chromosomes 6 and 20 identified distinct haplotype structures, variation patterns, and genomic candidates influencing flowering in subpopulations. These results suggest the action of a network of genomic candidates influencing flowering time and an untapped reservoir of genomic variation for this trait in wild germplasm. Notably, GlymaLee.20G147200 on chromosome 20 was identified as a candidate gene that may cause delayed flowering in soybean, potentially through histone modifications of floral repressor loci as seen in Arabidopsis thaliana (L.) Heynh. These findings support future functional validation of haplotype-based alleles for marker-assisted breeding and genomic selection to enhance latitude adaptability of soybean without compromising yield.},
}

@article {pmid39510408,
year = {2024},
author = {Ren, J and Kou, W and Xu, Y and Lu, M and Gong, M and Wang, X and Zhang, X and Liu, Z and Li, H and Yang, Q and Shah, AM and Zhu, F and Hou, ZC and Xu, N and Jiang, Y and Wang, F},
title = {Pan-genome analyses add ∼1000 genes to the "complete" genome assembly of chicken.},
journal = {Journal of genetics and genomics = Yi chuan xue bao},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jgg.2024.10.009},
pmid = {39510408},
issn = {1673-8527},
}

@article {pmid39510377,
year = {2024},
author = {Liu, F and Ma, XB and Han, B and Wang, B and Xu, JP and Cao, B and Ling, ZL and He, MQ and Zhu, XY and Zhao, RL},
title = {Pan-genome analysis reveals genomic variations during enoki mushroom domestication, with emphasis on genetic signatures of cap color and stipe length.},
journal = {Journal of advanced research},
volume = {},
number = {},
pages = {},
doi = {10.1016/j.jare.2024.11.005},
pmid = {39510377},
issn = {2090-1224},
abstract = {INTRODUCTION: The domestication of edible mushrooms, including Flammulina filiformis, offers valuable insights into the genetic changes driven by artificial selection. Understanding these changes is crucial for uncovering the mechanisms behind genome evolution in domesticated mushrooms.

OBJECTIVES: This study aims to investigate the population structure, genetic diversity, and domestication-related genomic changes in F. filiformis. By comparing the genome sequences of 199 wild and cultivated strains, we aim to elucidate the impact of domestication on F. filiformis.

METHODS: We performed de novo genome assembly and gene-based pan-genome analysis on the 199 strains, which included both wild and cultivated strains. We also conducted genome-wide association studies (GWAS) using presence-absence variation (PAV) and SNP data, combined with RNA sequencing, to identify genes associated with domestication traits, such as cap color and stipe length. Gene functional confirmation was achieved through genetic transformation experiments.

RESULTS: Our analysis grouped the strains into four distinct populations, which correlated with varying intensities of artificial selection. The three cultivated populations exhibited smaller genome sizes, fewer genes, lower genetic variation, reduced gene expression diversity, and lower heterozygosity compared to the wild population. The analysis revealed the loss of genes related to the beta-lactam antibiotic catabolic process and specific MAPK pathway genes during domestication, rendering domesticated strains more susceptible to diseases. Four genes closely associated with cap color and stipe length were identified, but genetic transformation experiments confirmed the functional relevance of only two (FfB and FfD) identified through PAV-based GWAS.

CONCLUSION: This study uncovered significant genomic variations between cultivated and wild F. filiformis populations, including the loss of pathogen resistance genes during domestication. We also identified key genes linked to cap color and stipe length, demonstrating for the first time the important role of PAV variation in mushroom domestication. These insights provide a foundation for future mushroom breeding and evolutionary research.},
}

@article {pmid39508593,
year = {2024},
author = {Tran, TH and F Escapa, I and Roberts, AQ and Gao, W and Obawemimo, AC and Segre, JA and Kong, HH and Conlan, S and Kelly, MS and Lemon, KP},
title = {Metabolic capabilities are highly conserved among human nasal-associated Corynebacterium species in pangenomic analyses.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0113224},
doi = {10.1128/msystems.01132-24},
pmid = {39508593},
issn = {2379-5077},
abstract = {UNLABELLED: Corynebacterium species are globally ubiquitous in human nasal microbiota across the lifespan. Moreover, nasal microbiota profiles typified by higher relative abundances of Corynebacterium are often positively associated with health. Among the most common human nasal Corynebacterium species are C. propinquum, C. pseudodiphtheriticum, C. accolens, and C. tuberculostearicum. To gain insight into the functions of these four species, we identified genomic, phylogenomic, and pangenomic properties and estimated the metabolic capabilities of 87 distinct human nasal Corynebacterium strain genomes: 31 from Botswana and 56 from the United States. C. pseudodiphtheriticum had geographically distinct clades consistent with localized strain circulation, whereas some strains from the other species had wide geographic distribution spanning Africa and North America. All species had similar genomic and pangenomic structures. Gene clusters assigned to all COG metabolic categories were overrepresented in the persistent versus accessory genome of each species indicating limited strain-level variability in metabolic capacity. Based on prevalence data, at least two Corynebacterium species likely coexist in the nasal microbiota of 82% of adults. So, it was surprising that core metabolic capabilities were highly conserved among the four species indicating limited species-level metabolic variation. Strikingly, strains in the U.S. clade of C. pseudodiphtheriticum lacked genes for assimilatory sulfate reduction present in most of the strains in the Botswana clade and in the other studied species, indicating a recent, geographically related loss of assimilatory sulfate reduction. Overall, the minimal species and strain variability in metabolic capacity implies coexisting strains might have limited ability to occupy distinct metabolic niches.

IMPORTANCE: Pangenomic analysis with estimation of functional capabilities facilitates our understanding of the full biologic diversity of bacterial species. We performed systematic genomic, phylogenomic, and pangenomic analyses with qualitative estimation of the metabolic capabilities of four common human nasal Corynebacterium species, along with focused experimental validations, generating a foundational resource. The prevalence of each species in human nasal microbiota is consistent with the common coexistence of at least two species. We identified a notably high level of metabolic conservation within and among species indicating limited options for species to occupy distinct metabolic niches, highlighting the importance of investigating interactions among nasal Corynebacterium species. Comparing strains from two continents, C. pseudodiphtheriticum had restricted geographic strain distribution characterized by an evolutionarily recent loss of assimilatory sulfate reduction in U.S. strains. Our findings contribute to understanding the functions of Corynebacterium within human nasal microbiota and to evaluating their potential for future use as biotherapeutics.},
}

@article {pmid39533060,
year = {2024},
author = {Aguirre-Sánchez, JR and Chaidez, C and Castro-Del Campo, N},
title = {The pangenome analysis of the environmental source Salmonella enterica highlights a diverse accessory genome and a distinct serotype clustering.},
journal = {FEMS microbiology letters},
volume = {},
number = {},
pages = {},
doi = {10.1093/femsle/fnae090},
pmid = {39533060},
issn = {1574-6968},
abstract = {Salmonella remains the leading cause of foodborne infections globally. Environmental reservoirs, particularly aquatic bodies, serve as conduits for the fecal-oral transmission of this pathogen. While the gastrointestinal tract is traditionally considered the primary habitat of Salmonella, mounting evidence suggests the bacterium's capacity for survival in external environments. The application of advanced technological platforms, such as next-generation sequencing (NGS), facilitates a comprehensive analysis of Salmonella's genomic features. This study aims to characterize the genomic composition of Salmonella isolates from river water, contributing to a potential paradigm shift and advancing public health protection. A total of 25 river water samples were collected and processed, followed by microbiological isolation of Salmonella strains, which were then sequenced. Genomic characterization revealed adaptive mechanisms, including gene duplication. Furthermore, an open pangenome, predisposed to incorporating foreign genetic material, was identified. Notably, antibiotic resistance genes were found to be part of the core genome, challenging previous reports that placed them in the accessory genome.},
}

@article {pmid39532890,
year = {2024},
author = {Zhang, M and Adroub, S and Ummels, R and Asaad, M and Song, L and Pain, A and Bitter, W and Guan, Q and Abdallah, AM},
title = {Comprehensive pan-genome analysis of Mycobacterium marinum: insights into genomic diversity, evolution, and pathogenicity.},
journal = {Scientific reports},
volume = {14},
number = {1},
pages = {27723},
pmid = {39532890},
issn = {2045-2322},
support = {2024B20//The Bethune Project of Jilin University/ ; 23YQ10//Science and Technology Development Project/ ; 04045970001//Research start-up funds/ ; },
mesh = {*Mycobacterium marinum/genetics/pathogenicity ; *Genome, Bacterial ; *Phylogeny ; *Genetic Variation ; *Evolution, Molecular ; Humans ; Genomics/methods ; Virulence Factors/genetics ; Whole Genome Sequencing/methods ; Virulence/genetics ; Mycobacterium Infections, Nontuberculous/microbiology ; },
abstract = {Mycobacteria is a diverse genus that includes both innocuous environmental species and serious pathogens like Mycobacterium tuberculosis, Mycobacterium leprae, and Mycobacterium ulcerans, the causative agents of tuberculosis, leprosy, and Buruli ulcer, respectively. This study focuses on Mycobacterium marinum, a closely related species known for its larger genome and ability to infect ectothermic species and cooler human extremities. Utilizing whole-genome sequencing, we conducted a comprehensive pan-genome analysis of 100 M. marinum strains, exploring genetic diversity and its impact on pathogenesis and host specificity. Our findings highlight significant genomic diversity, with clear distinctions in core, dispensable, and unique genes among the isolates. Phylogenetic analysis revealed a broad distribution of genetic lineages, challenging previous classifications into distinct clusters. Additionally, we examined the synteny and diversity of the virulence factor CpnT, noting a wide range of C-terminal domain variations across strains, which points to potential adaptations in pathogenic mechanisms. This study enhances our understanding of M. marinum's genomic architecture and its evolutionary relationship with other mycobacterial pathogens, providing insights that could inform disease control strategies for M. tuberculosis and other mycobacteria.},
}

*Mycobacterium marinum/genetics/pathogenicity
*Genome, Bacterial
*Phylogeny
*Genetic Variation
*Evolution, Molecular
Humans
Genomics/methods
Virulence Factors/genetics
Whole Genome Sequencing/methods
Virulence/genetics
Mycobacterium Infections, Nontuberculous/microbiology

@article {pmid39531493,
year = {2024},
author = {Fang, B and Edwards, SV},
title = {Fitness consequences of structural variation inferred from a House Finch pangenome.},
journal = {Proceedings of the National Academy of Sciences of the United States of America},
volume = {121},
number = {47},
pages = {e2409943121},
doi = {10.1073/pnas.2409943121},
pmid = {39531493},
issn = {1091-6490},
support = {n/a//Harvard University (Harvard College)/ ; n/a//Harvard China Fund/ ; n/a//Harvard Global Institute (HGI)/ ; },
mesh = {Animals ; *Finches/genetics ; *Genomic Structural Variation ; *Genome/genetics ; Genetic Fitness/genetics ; Polymorphism, Single Nucleotide ; Evolution, Molecular ; Chromosome Inversion/genetics ; Haplotypes ; },
abstract = {Genomic structural variants (SVs) play a crucial role in adaptive evolution, yet their average fitness effects and characterization with pangenome tools are understudied in wild animal populations. We constructed a pangenome for House Finches (Haemorhous mexicanus), a model for studies of host-pathogen coevolution, using long-read sequence data on 16 individuals (32 de novo-assembled haplotypes) and one outgroup. We identified 887,118 SVs larger than 50 base pairs, mostly (60%) involving repetitive elements, with reduced SV diversity in the eastern US as a result of its introduction by humans. The distribution of fitness effects of genome-wide SVs was estimated using maximum likelihood approaches and revealed that SVs in both coding and noncoding regions were on average more deleterious than smaller indels or single nucleotide polymorphisms. The reference-free pangenome facilitated identification of a > 10-My-old, 11-megabase-long pericentric inversion on chromosome 1. We found that the genotype frequencies of the inversion, estimated from 135 birds widely sampled temporally and geographically, increased steadily over the 25 y since House Finches were first exposed to the bacterial pathogen Mycoplasma gallisepticum and showed signatures of balancing selection, capturing genes related to immunity and telomerase activity. We also observed shorter telomeres in populations with a greater number of years exposure to Mycoplasma. Our study illustrates the utility of long-read sequencing and pangenome methods for understanding wild animal populations, estimating fitness effects of genome-wide SVs, and advancing our understanding of adaptive evolution through structural variation.},
}

Animals
*Finches/genetics
*Genomic Structural Variation
*Genome/genetics
Genetic Fitness/genetics
Polymorphism, Single Nucleotide
Evolution, Molecular
Chromosome Inversion/genetics
Haplotypes

@article {pmid39530695,
year = {2024},
author = {Jin, Y and Gao, C and Teng, G and Zhou, Z and Zhou, W and Huang, M},
title = {Dissecting the genetic features and evolution of Staphylococcus aureus sequence type 88: a global perspective.},
journal = {mSystems},
volume = {},
number = {},
pages = {e0114224},
doi = {10.1128/msystems.01142-24},
pmid = {39530695},
issn = {2379-5077},
abstract = {Staphylococcus aureus sequence type (ST) 88, encompassing both methicillin-resistant S. aureus (MRSA) and methicillin-sensitive S. aureus (MSSA) phenotypes, is globally prevalent and commonly associated with skin and soft tissue infections. Despite its widespread occurrence, comprehensive genomic studies on this clone remain scarce. In this study, we performed detailed genomic analyses on 130 ST88 isolates derived from severe bloodstream infections alongside 275 publicly available ST88 sequences. Our phylogenetic analysis identified four distinct clades, with evidence suggesting independent evolution and significant clonal expansion of ST88 in China, particularly within clade I, which appeared to have emerged circa 1964. We documented notable interregional, international, and even intercontinental transmission of ST88 isolates. Variability in the distribution of SCCmec and spa types was observed across clades. Our in silico analyses indicated distinct patterns in the distribution of resistance genes, virulence genes, and mobile genetic elements among the clades, with clade I notably harboring the highest prevalence of the intact sraP gene and an independently acquired novel prophage, φST88-1. Conversely, clade IV exhibited deletions within the sasC gene, with certain sub-clades lacking the sdrDE and fnbB genes, underscoring the superior adhesive capabilities of clade I. In vitro experiments confirmed enhanced biofilm formation in clade I isolates, although the levels of hemolysis and cytotoxicity were similar across clades. Pan-genome-wide association study revealed that core SNPs, rather than the accessory genome, are the primary contributors to the diversification of the ST88 clades. These findings enrich our understanding of the genetic foundations underpinning the transmission dynamics and phenotypic diversity of ST88 clones globally.IMPORTANCEUnderstanding the evolution and transmission of Staphylococcus aureus ST88 clones is critically important due to their spread within food, hospital, and community environments, leading to significant health issues. Despite its prevalence, detailed genomic insights into ST88, particularly regarding its diversity and evolutionary dynamics, have been lacking. Our comprehensive genomic analysis of 130 ST88 isolates from severe bloodstream infections, alongside 275 sequences from public databases, significantly advances our understanding of this pathogen. We identified four distinct evolutionary clades, demonstrating the independent evolution and substantial clonal expansion of ST88 in China, as well as its ability to spread across regions and continents. The diversity among the isolates was evident in their unique profiles of SCCmec elements, antibiotic resistance genes, virulence genes, and mobile genetic elements. Our findings underscore the critical role of core genomic variations over accessory elements in driving the diversification of ST88. This enhanced understanding provides new insights that could inform more effective control strategies, crucial for developing interventions to combat the global spread of this formidable pathogen.},
}

@article {pmid39528738,
year = {2024},
author = {Snoeck, S and Johanndrees, O and Nürnberger, T and Zipfel, C},
title = {Plant pattern recognition receptors: from evolutionary insight to engineering.},
journal = {Nature reviews. Genetics},
volume = {},
number = {},
pages = {},
pmid = {39528738},
issn = {1471-0064},
abstract = {The plant immune system relies on germline-encoded pattern recognition receptors (PRRs) that sense foreign and plant-derived molecular patterns, and signal health threats. Genomic and pangenomic data sets provide valuable insights into the evolution of PRRs and their molecular triggers, which is furthering our understanding of plant-pathogen co-evolution and convergent evolution. Moreover, in silico and in vivo methods of PRR identification have accelerated the characterization of receptor-ligand complexes, and advances in protein structure prediction algorithms are revealing novel PRR sensor functions. Harnessing these recent advances to engineer PRRs presents an opportunity to enhance plant disease resistance against a broad spectrum of pathogens, enabling more sustainable agricultural practices. This Review summarizes both established and innovative approaches to leverage genomic data and translate resulting evolutionary insights into engineering PRR recognition specificities.},
}

@article {pmid39526372,
year = {2024},
author = {Liu, Z and Shen, S and Li, C and Zhang, C and Chen, X and Fu, Y and Yu, T and Zhou, R and Liu, D and Yang, QY and Song, X},
title = {SoIR: a comprehensive Solanaceae information resource for comparative and functional genomic study.},
journal = {Nucleic acids research},
volume = {},
number = {},
pages = {},
doi = {10.1093/nar/gkae1040},
pmid = {39526372},
issn = {1362-4962},
support = {C2022209010//Natural Science Fund for Distinguished Young Scholars of Hebei Province/ ; 2023YFF1002000//National Key Research and Development Program of China/ ; 32172583//National Natural Science Foundation of China/ ; 23372505D//S&T Program of Hebei/ ; H2023209084//Hebei Natural Science Foundation/ ; },
abstract = {The Solanaceae family, which includes economically important crops such as tomatoes, potatoes and peppers, has experienced a rapid expansion in genomic data due to advancements in sequencing technologies. However, existing databases are limited by incomplete species representation, a lack of comprehensive comparative genomic tools and the absence of systematic pan-genomic analyses. To address these gaps, we developed the Solanaceae Information Resource (SoIR, https://soir.bio2db.com), a comprehensive genomics database for the Solanaceae family. SoIR integrates genomic data from 81 species and transcriptomic data from 41 species, encompassing a total of 3 908 408 gene annotations derived from Gene Ontology, nonredundant protein, Pfam, Swiss-Prot and TrEMBL databases. The resource also includes 3 437 115 CRISPR guide sequences, 212 395 transcription factors and 19 086 genes associated with methylation modification. In addition to species-specific analyses, SoIR provides extensive bioinformatics tools for investigating gene family evolution, phylogenetic relationships and karyotype reconstruction across 25 fully sequenced genomes. With advanced tools such as Blast, Synteny and Sequence Alignment, the platform provides users with interactive and intuitive visualizations for conducting cross-species comparative genomics. As the first comprehensive pan-genomic resource for the entire Solanaceae family, SoIR facilitates in-depth cross-species analysis, supporting global research initiatives in plant evolution, functional genomics and crop improvement.},
}

@article {pmid39526133,
year = {2024},
author = {Binsker, U and Deneke, C and Hamid, HM and Gadicherla, AK and Göhler, A and Käsbohrer, A and Hammerl, JA},
title = {Genomic dissection of Escherichia marmotae provides insights into diversity and pathogenic potential.},
journal = {ISME communications},
volume = {4},
number = {1},
pages = {ycae126},
pmid = {39526133},
issn = {2730-6151},
abstract = {Anthropogenic activities enhance the interconnection of human, animal, and environmental habitats and drive the evolution and inter-niche transmission of bacteria. Clear identification of emerging bacteria and pathogen control is therefore a public health priority. In 2015, the novel Escherichia species Escherichia marmotae was assigned, but due to the lack of appropriate detection and typing technologies, the One Health impact of this species is still being unraveled. E. marmotae represents a missing link in the impact of Escherichia spp. Here, we report 25 E. marmotae identified by next-generation sequencing that were previously phenotypically characterized as Escherichia coli during national zoonosis monitoring of food-producing animals. Applying fastANI to 153 738 published Escherichia spp. genome assemblies, we identified further 124 E. marmotae, originally classified as E. coli. Phylogenomics of all 149 isolates reveals an undefined population structure that is independent of the ecological niche. We highlight the phenotypic, genomic, and plasmid diversity of E. marmotae and provide evidence for gene flow across the species. The latter is illustrated by the acquisition of antibiotic resistance plasmids and pathogenicity islands, such as the type III secretion system. Thus, our comprehensive genomic overview of an emerging potential opportunistic pathogen underlines the importance of improved detection and characterization.},
}

@article {pmid39525087,
year = {2024},
author = {Provatas, K and Chantzi, N and Patsakis, M and Nayak, A and Mouratidis, I and Georgakopoulos-Soares, I},
title = {Microsatellites explorer: A database of short tandem repeats across genomes.},
journal = {Computational and structural biotechnology journal},
volume = {23},
number = {},
pages = {3817-3826},
pmid = {39525087},
issn = {2001-0370},
abstract = {Short tandem repeats (STRs) are widespread, repetitive elements, with a number of biological functions and are among the most rapidly mutating regions in the genome. Their distribution varies significantly between taxonomic groups in the tree of life and are highly polymorphic within the human population. Advances in sequencing technologies coupled with decreasing costs have enabled the generation of an ever-growing number of complete genomes. Additionally, the arrival of accurate long reads has facilitated the generation of Telomere-to-Telomere (T2T) assemblies of complete genomes. Nevertheless, there is no comprehensive database that encompasses the STRs found per genome across different organisms and for different human genomes across diverse ancestries. Here we introduce Microsatellites Explorer, a database of STRs found in the genomes of 117,253 organisms across all major taxonomic groups, 15 T2T genome assemblies of different organisms, and 94 human haplotypes from the human pangenome. The database currently hosts 406,758,798 STR sequences, serving as a centralized user-friendly repository to perform searches, interactive visualizations, and download existing STR data for independent analysis. Microsatellites Explorer is implemented as a web-portal for browsing, analyzing and downloading STR data. Microsatellites Explorer is publicly available at https://www.microsatellitesexplorer.com.},
}