{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T21:19:24Z","timestamp":1792790364989,"version":"4.5.0"},"posted":{"date-parts":[[2026,9,27]]},"group-title":"Bioinformatics","reference-count":105,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,27]],"date-time":"2026-09-27T00:00:00Z","timestamp":1790467200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"U.S. National Science Foundation","award":["2137424"],"award-info":[{"award-number":["2137424"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"crossref"}]},{"name":"U.S. National Science Foundation","award":["2149505"],"award-info":[{"award-number":["2149505"]}],"id":[{"id":"https:\/\/ror.org\/021nxhr62","id-type":"ROR","asserted-by":"crossref"}]},{"name":"University of Wisconsin-Madison","id":[{"id":"https:\/\/ror.org\/01y2jtd41","id-type":"ROR","asserted-by":"crossref"}]},{"id":[{"id":"https:\/\/ror.org\/03zbnzt98","id-type":"ROR","asserted-by":"publisher"}]},{"name":"National Institutes of Health","award":["R35GM143024"],"award-info":[{"award-number":["R35GM143024"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Viruses shape microbial metabolism through auxiliary viral genes (AVGs) that reprogram host metabolism, physiology, and gene regulation during infection. Identifying AVGs is complicated by ambiguous viral versus cellular assignment, inconsistent curation, and reliance on sequence homology that misses divergent functions. Here we present CheckAMG, which pairs annotation- based AVG prediction, curated with a per-gene viral scoring system and ontological mapping of metabolic function, with a finetuned genome-language model for annotation-independent discovery. Benchmarked against DRAM-V and VIBRANT across three ecosystems, CheckAMG produced more strongly supported auxiliary metabolic gene (AMG) calls, and uniquely among AMG tools reports auxiliary physiological (APGs) and regulatory (AReGs) genes. Applied to 1,005,980 fragmented or complete soil and human-gut viral genomes, CheckAMG identified 541,199 AVGs tracking biome-specific protein clusters and functions, including 109,107 proteins with no detectable sequence similarity to any reference database. CheckAMG thus provides a reproducible, scalable framework for identifying the genes through which viruses reprogram host biology.<\/jats:p>","DOI":"10.64898\/2026.09.23.753886","type":"posted-content","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:00:18Z","timestamp":1790571618000},"source":"Crossref","is-referenced-by-count":0,"title":["CheckAMG: Accurate Identification of Auxiliary Viral Genes with Genome- Language Models"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7070-5418","authenticated-orcid":false,"given":"James C.","family":"Kosmopoulos","sequence":"first","affiliation":[{"name":"Department of Bacteriology, University of Wisconsin-Madison, Madison, WI, USA"},{"name":"Microbiology Doctoral Training Program, University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7610-9537","authenticated-orcid":false,"given":"Cody","family":"Martin","sequence":"additional","affiliation":[{"name":"Department of Bacteriology, University of Wisconsin-Madison, Madison, WI, USA"},{"name":"Microbiology Doctoral Training Program, University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7233-4793","authenticated-orcid":false,"given":"James M.","family":"Wainaina","sequence":"additional","affiliation":[{"name":"Biology Department, Woods Hole Oceanographic Institution, Woods Hole, MA, USA"},{"name":"MIT-WHOI Joint Program, Massachusetts Institute of Technology, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2420-0755","authenticated-orcid":false,"given":"Benjamin","family":"Bolduc","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Ohio State University, Columbus, OH, USA"},{"name":"Center of Microbiome Science, Ohio State University, Columbus, OH, USA"},{"name":"EMERGE Biology Integration Institute, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7095-1835","authenticated-orcid":false,"given":"Marion","family":"Urvoy","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Ohio State University, Columbus, OH, USA"},{"name":"Center of Microbiome Science, Ohio State University, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8398-8234","authenticated-orcid":false,"given":"Matthew B.","family":"Sullivan","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Ohio State University, Columbus, OH, USA"},{"name":"Center of Microbiome Science, Ohio State University, Columbus, OH, USA"},{"name":"EMERGE Biology Integration Institute, Columbus, OH, USA"},{"name":"Department of Civil, Environmental and Geodetic Engineering, Ohio State University, Columbus, OH, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9584-2491","authenticated-orcid":false,"given":"Karthik","family":"Anantharaman","sequence":"additional","affiliation":[{"name":"Department of Bacteriology, University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026093017151717000_2026.09.23.753886v1.1","doi-asserted-by":"crossref","first-page":"2122","DOI":"10.1038\/s41564-025-02095-4","article-title":"A call for caution in the biological interpretation of viral auxiliary metabolic genes","volume":"10","year":"2025","journal-title":"Nature Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.2","unstructured":"Lindell, D. et al. Transfer of photosynthesis genes to and from Prochlorococcus viruses."},{"key":"2026093017151717000_2026.09.23.753886v1.3","doi-asserted-by":"crossref","unstructured":"Proceedings of the National Academy of Sciences 101, 11013\u201311018 (2004).","DOI":"10.1073\/pnas.0401526101"},{"key":"2026093017151717000_2026.09.23.753886v1.4","doi-asserted-by":"crossref","first-page":"135","DOI":"10.5670\/oceanog.2007.58","article-title":"Exploring the Vast Diversity of Marine Viruses","volume":"20","year":"2007","journal-title":"Oceanography"},{"key":"2026093017151717000_2026.09.23.753886v1.5","doi-asserted-by":"crossref","first-page":"754","DOI":"10.1038\/s41564-018-0166-y","article-title":"Phage puppet masters of the marine microbial realm","volume":"3","year":"2018","journal-title":"Nature Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.6","doi-asserted-by":"crossref","unstructured":"Forterre, P . Manipulation of cellular syntheses and the nature of viruses: The virocell concept. in Comptes Rendus Chimie vol. 14 392\u2013399 (Elsevier Masson SAS, 2011).","DOI":"10.1016\/j.crci.2010.06.007"},{"key":"2026093017151717000_2026.09.23.753886v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/j.tim.2026.05.019"},{"key":"2026093017151717000_2026.09.23.753886v1.8","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0003550"},{"key":"2026093017151717000_2026.09.23.753886v1.9","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1102164108"},{"key":"2026093017151717000_2026.09.23.753886v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/s41579-019-0270-x"},{"key":"2026093017151717000_2026.09.23.753886v1.11","doi-asserted-by":"publisher","DOI":"10.1111\/j.1462-2920.2006.01137.x"},{"key":"2026093017151717000_2026.09.23.753886v1.12","doi-asserted-by":"crossref","first-page":"3623","DOI":"10.1128\/aem.61.10.3623-3627.1995","article-title":"Fluorescently Labeled Virus Probes Show that Natural Virus Populations Can Control the Structure of Marine Microbial Communities","volume":"61","year":"1995","journal-title":"Applied and Environmental Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.13","doi-asserted-by":"crossref","unstructured":"Mann, N. H. , Cook, A. , Millard, A. , Bailey, S. & Clokie, M . Bacterial photosynthesis genes in a virus. Nature 424, 741 (2003).","DOI":"10.1038\/424741a"},{"key":"2026093017151717000_2026.09.23.753886v1.14","doi-asserted-by":"publisher","DOI":"10.1038\/nature04111"},{"key":"2026093017151717000_2026.09.23.753886v1.15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0040234"},{"key":"2026093017151717000_2026.09.23.753886v1.16","doi-asserted-by":"publisher","DOI":"10.1038\/nature11927"},{"key":"2026093017151717000_2026.09.23.753886v1.17","doi-asserted-by":"crossref","first-page":"5611","DOI":"10.1038\/s41598-023-32078-6","article-title":"CRISPR-resolved virus-host interactions in a municipal landfill include non-specific viruses, hyper-targeted viral populations, and interviral conflicts","volume":"13","year":"2023","journal-title":"Scientific Reports"},{"key":"2026093017151717000_2026.09.23.753886v1.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2022.10.020"},{"key":"2026093017151717000_2026.09.23.753886v1.19","doi-asserted-by":"publisher","DOI":"10.1128\/msphere.00297-22"},{"key":"2026093017151717000_2026.09.23.753886v1.20","doi-asserted-by":"crossref","first-page":"D801","DOI":"10.1093\/nar\/gkaf1283","article-title":"Meta-virus resource (MetaVR): expanding the frontiers of viral diversity with 24 million uncultivated virus genomes","volume":"54","year":"2026","journal-title":"Nucleic Acids Research"},{"key":"2026093017151717000_2026.09.23.753886v1.21","doi-asserted-by":"publisher","DOI":"10.1021\/acs.biochem.5c00349"},{"key":"2026093017151717000_2026.09.23.753886v1.22","doi-asserted-by":"crossref","unstructured":"Tian, F. et al. Prokaryotic-virus-encoded auxiliary metabolic genes throughout the global oceans. Microbiome 12, 159 (2024).","DOI":"10.1186\/s40168-024-01876-z"},{"key":"2026093017151717000_2026.09.23.753886v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-00774-7PMID-33349699"},{"key":"2026093017151717000_2026.09.23.753886v1.24","doi-asserted-by":"crossref","unstructured":"Garneau, J. R. et al. High-throughput identification of viral termini and packaging mechanisms in virome datasets using PhageTermVirome. Scientific Reports 11, 18319 (2021).","DOI":"10.1038\/s41598-021-97867-3"},{"key":"2026093017151717000_2026.09.23.753886v1.25","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac163"},{"key":"2026093017151717000_2026.09.23.753886v1.26","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.3817"},{"key":"2026093017151717000_2026.09.23.753886v1.27","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.11447"},{"key":"2026093017151717000_2026.09.23.753886v1.28","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa621"},{"key":"2026093017151717000_2026.09.23.753886v1.29","doi-asserted-by":"crossref","unstructured":"Kieft, K. , Zhou, Z. & Anantharaman, K . VIBRANT: automated recovery, annotation and curation of microbial viruses, and evaluation of viral community function from genomic sequences. Microbiome 8, 90 (2020).","DOI":"10.1186\/s40168-020-00867-0"},{"key":"2026093017151717000_2026.09.23.753886v1.30","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1038\/s41564-018-0190-y","article-title":"Host-linked soil viral ecology along a permafrost thaw gradient","volume":"3","year":"2018","journal-title":"Nature Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.virusres.2017.02.002"},{"key":"2026093017151717000_2026.09.23.753886v1.32","doi-asserted-by":"publisher","DOI":"10.1126\/science.ade2574"},{"key":"2026093017151717000_2026.09.23.753886v1.33","doi-asserted-by":"crossref","unstructured":"Mordret, E. et al. Protein and genomic language models uncover the unexplored diversity of bacterial immunity. Science 392, eadv8275 (2026).","DOI":"10.1126\/science.adv8275"},{"key":"2026093017151717000_2026.09.23.753886v1.34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-026-72028-0"},{"key":"2026093017151717000_2026.09.23.753886v1.35","doi-asserted-by":"crossref","unstructured":"Martin, C. , Gitter, A. & Anantharaman, K . Protein Set Transformer: a protein-based genome language model to power high-diversity viromics. Nature Communications 16, 11123 (2025).","DOI":"10.1038\/s41467-025-66049-4"},{"key":"2026093017151717000_2026.09.23.753886v1.36","unstructured":"Ke, G. et al. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. in Advances in Neural Information Processing Systems (eds Guyon, I. et al.) vol. 30 (Curran Associates, Inc., 2017)."},{"key":"2026093017151717000_2026.09.23.753886v1.37","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkv1070"},{"key":"2026093017151717000_2026.09.23.753886v1.38","doi-asserted-by":"publisher","DOI":"10.1093\/NAR\/GKAA913"},{"key":"2026093017151717000_2026.09.23.753886v1.39","doi-asserted-by":"crossref","first-page":"lqab067","DOI":"10.1093\/nargab\/lqab067","article-title":"PHROG: families of prokaryotic virus proteins clustered using remote homology","volume":"3","year":"2021","journal-title":"NAR Genomics and Bioinformatics"},{"key":"2026093017151717000_2026.09.23.753886v1.40","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-023-01953-y"},{"key":"2026093017151717000_2026.09.23.753886v1.41","first-page":"D760","article-title":"proGenomes3: approaching one million accurately and consistently annotated high-quality prokaryotic genomes","volume":"51","year":"2022","journal-title":"Nucleic Acids Research"},{"key":"2026093017151717000_2026.09.23.753886v1.42","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0293169"},{"key":"2026093017151717000_2026.09.23.753886v1.43","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkad328"},{"key":"2026093017151717000_2026.09.23.753886v1.44","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gku702"},{"key":"2026093017151717000_2026.09.23.753886v1.45","doi-asserted-by":"crossref","unstructured":"Zhou, Z. et al. METABOLIC: high-throughput profiling of microbial genomes for functional traits, metabolism, biogeochemistry, and community-scale functional networks. Microbiome 10, 33 (2022).","DOI":"10.1186\/s40168-021-01213-8"},{"key":"2026093017151717000_2026.09.23.753886v1.46","doi-asserted-by":"crossref","first-page":"1454","DOI":"10.1038\/s41564-024-01691-0","article-title":"Microbial polyphenol metabolism is part of the thawing permafrost carbon cycle","volume":"9","year":"2024","journal-title":"Nature Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.47","doi-asserted-by":"crossref","first-page":"D1779","DOI":"10.1093\/nar\/gkaf1292","article-title":"The Gene Ontology knowledgebase in 2026","volume":"54","author":"The Gene Ontology Consortium.","year":"2026","journal-title":"Nucleic Acids Research"},{"key":"2026093017151717000_2026.09.23.753886v1.48","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkm882"},{"key":"2026093017151717000_2026.09.23.753886v1.49","doi-asserted-by":"crossref","unstructured":"Guo, J. et al. VirSorter2: a multi-classifier, expert-guided approach to detect diverse DNA and RNA viruses. Microbiome 9, 37 (2021).","DOI":"10.1186\/s40168-020-00990-y"},{"key":"2026093017151717000_2026.09.23.753886v1.50","doi-asserted-by":"crossref","first-page":"1873","DOI":"10.1038\/s41564-024-01686-x","article-title":"A global atlas of soil viruses reveals unexplored biodiversity and potential biogeochemical impacts","volume":"9","year":"2024","journal-title":"Nature Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.51","doi-asserted-by":"crossref","first-page":"2561","DOI":"10.1038\/s41467-022-30269-9","article-title":"Systematic and quantitative view of the antiviral arsenal of prokaryotes","volume":"13","year":"2022","journal-title":"Nature Communications"},{"key":"2026093017151717000_2026.09.23.753886v1.52","doi-asserted-by":"publisher","DOI":"10.1111\/mmi.14117"},{"key":"2026093017151717000_2026.09.23.753886v1.53","doi-asserted-by":"crossref","first-page":"1589","DOI":"10.1038\/s41396-023-01470-5","article-title":"Extreme summers impact cropland and grassland soil microbiomes","volume":"17","year":"2023","journal-title":"The ISME Journal"},{"key":"2026093017151717000_2026.09.23.753886v1.54","doi-asserted-by":"crossref","unstructured":"Ibarra, J. A. , P\u00e9rez-Rueda, E. , Carroll, R. K. & Shaw, L. N . Global analysis of transcriptional regulators in Staphylococcus aureus. BMC Genomics 14, 126 (2013).","DOI":"10.1186\/1471-2164-14-126"},{"key":"2026093017151717000_2026.09.23.753886v1.55","first-page":"e00727","article-title":"Phylogenetic Distribution of WhiB- and Lsr2-Type Regulators in Actinobacteriophage Genomes","volume":"9","year":"2021","journal-title":"Microbiology Spectrum"},{"key":"2026093017151717000_2026.09.23.753886v1.56","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2958.2010.07235.x"},{"key":"2026093017151717000_2026.09.23.753886v1.57","doi-asserted-by":"crossref","unstructured":"Jamet, A. et al. A widespread family of polymorphic toxins encoded by temperate phages. BMC Biology 15, 75 (2017).","DOI":"10.1186\/s12915-017-0415-1"},{"key":"2026093017151717000_2026.09.23.753886v1.58","first-page":"38","article-title":"Discovery of an expansive bacteriophage family that includes the most abundant viruses from the human gut","volume":"3","year":"2018","journal-title":"Nature Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.59","doi-asserted-by":"crossref","unstructured":"Docherty, J. A. D. , et al. Diverse defense systems and prophages in human-associated Bifidobacterium species reveal coevolutionary \u201carms race\u201d dynamics. Cell Reports 44, (2025).","DOI":"10.1016\/j.celrep.2025.116542"},{"key":"2026093017151717000_2026.09.23.753886v1.60","doi-asserted-by":"crossref","unstructured":"Huang, X. et al. Genome-resolved metagenomics reveal soil and viral drivers of keystone bacterial traits shaping nutrient cycling and soybean yield across agroecosystems. Soil Ecology Letters 7, 250346 (2025).","DOI":"10.1007\/s42832-025-0346-7"},{"key":"2026093017151717000_2026.09.23.753886v1.61","doi-asserted-by":"crossref","unstructured":"Trubl, G. , et al. Soil Viruses Are Underexplored Players in Ecosystem Carbon Processing. mSystems 3, (2018).","DOI":"10.1128\/msystems.00076-18"},{"key":"2026093017151717000_2026.09.23.753886v1.62","doi-asserted-by":"crossref","unstructured":"Huang, X. et al. Soil nutrient conditions alter viral lifestyle strategy and potential function in phosphorous and nitrogen metabolisms. Soil Biology and Biochemistry 189, 109279 (2024).","DOI":"10.1016\/j.soilbio.2023.109279"},{"key":"2026093017151717000_2026.09.23.753886v1.63","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0207-y"},{"key":"2026093017151717000_2026.09.23.753886v1.64","doi-asserted-by":"crossref","first-page":"wraf097","DOI":"10.1093\/ismejo\/wraf097","article-title":"Independently evolved extracellular electron transfer pathways in ecologically diverse Desulfobacterota","volume":"19","year":"2025","journal-title":"The ISME Journal"},{"key":"2026093017151717000_2026.09.23.753886v1.65","doi-asserted-by":"crossref","unstructured":"Kieft, K. et al. Virus-associated organosulfur metabolism in human and environmental systems. Cell Reports 36, 109471 (2021).","DOI":"10.1016\/j.celrep.2021.109471"},{"key":"2026093017151717000_2026.09.23.753886v1.66","doi-asserted-by":"crossref","unstructured":"Wolf, P. G. et al. Diversity and distribution of sulfur metabolic genes in the human gut microbiome and their association with colorectal cancer. Microbiome 10, 64 (2022).","DOI":"10.1186\/s40168-022-01242-x"},{"key":"2026093017151717000_2026.09.23.753886v1.67","doi-asserted-by":"crossref","first-page":"1857","DOI":"10.1038\/s41467-024-46109-x","article-title":"Viral potential to modulate microbial methane metabolism varies by habitat","volume":"15","year":"2024","journal-title":"Nature Communications"},{"key":"2026093017151717000_2026.09.23.753886v1.68","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1038\/s41564-024-01876-7","article-title":"Unravelling viral ecology and evolution over 20 years in a freshwater lake","volume":"10","year":"2025","journal-title":"Nature Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.69","doi-asserted-by":"crossref","first-page":"3503","DOI":"10.1038\/s41467-021-23698-5","article-title":"Ecology of inorganic sulfur auxiliary metabolism in widespread bacteriophages","volume":"12","year":"2021","journal-title":"Nature Communications"},{"key":"2026093017151717000_2026.09.23.753886v1.70","doi-asserted-by":"publisher","DOI":"10.1126\/science.1252229"},{"key":"2026093017151717000_2026.09.23.753886v1.71","doi-asserted-by":"crossref","first-page":"4076","DOI":"10.1038\/s41467-025-59154-x","article-title":"Endemism shapes viral ecology and evolution in globally distributed hydrothermal vent ecosystems","volume":"16","year":"2025","journal-title":"Nature Communications"},{"key":"2026093017151717000_2026.09.23.753886v1.72","first-page":"142","article-title":"Ecosystem health shapes viral ecology in peatland soils","volume":"11","year":"2026","journal-title":"Nature Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.73","doi-asserted-by":"crossref","first-page":"5485","DOI":"10.1038\/s41467-022-32993-8","article-title":"Structural characterization of a soil viral auxiliary metabolic gene product \u2013 a functional chitosanase","volume":"13","year":"2022","journal-title":"Nature Communications"},{"key":"2026093017151717000_2026.09.23.753886v1.74","doi-asserted-by":"crossref","first-page":"gkaf1448","DOI":"10.1093\/nar\/gkaf1448","article-title":"Protein structure-informed bacteriophage genome annotation with Phold","volume":"54","year":"2026","journal-title":"Nucleic Acids Research"},{"key":"2026093017151717000_2026.09.23.753886v1.75","doi-asserted-by":"crossref","first-page":"eadv5109","DOI":"10.1126\/sciadv.adv5109","article-title":"Gaia: An AI-enabled genomic context\u2013aware platform for protein sequence annotation","volume":"11","year":"2025","journal-title":"Science Advances"},{"key":"2026093017151717000_2026.09.23.753886v1.76","doi-asserted-by":"crossref","first-page":"4296","DOI":"10.21105\/joss.04296","article-title":"Pyrodigal: Python bindings and interface to Prodigal, an efficient method for gene prediction in prokaryotes","volume":"7","year":"2022","journal-title":"Journal of Open Source Software"},{"key":"2026093017151717000_2026.09.23.753886v1.77","doi-asserted-by":"crossref","unstructured":"Hyatt, D. et al. Prodigal: prokaryotic gene recognition and translation initiation site identification. BMC Bioinformatics 11, 119 (2010).","DOI":"10.1186\/1471-2105-11-119"},{"key":"2026093017151717000_2026.09.23.753886v1.78","doi-asserted-by":"crossref","first-page":"e1002195","DOI":"10.1371\/journal.pcbi.1002195","article-title":"Accelerated Profile HMM Searches","volume":"7","year":"2011","journal-title":"PLoS Computational Biology"},{"key":"2026093017151717000_2026.09.23.753886v1.79","doi-asserted-by":"crossref","unstructured":"Larralde, M. & Zeller, G . PyHMMER: a Python library binding to HMMER for efficient sequence analysis. Bioinformatics 39, (2023).","DOI":"10.1093\/bioinformatics\/btad214"},{"key":"2026093017151717000_2026.09.23.753886v1.80","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1038\/s41564-020-00834-3","article-title":"Community-led, integrated, reproducible multi-omics with anvi\u2019o","volume":"6","year":"2020","journal-title":"Nature Microbiology"},{"key":"2026093017151717000_2026.09.23.753886v1.81","first-page":"vbaf039","article-title":"Adaptive adjustment of profile HMM significance thresholds improves functional and metabolic insights into microbial genomes","volume":"5","year":"2025","journal-title":"Bioinformatics Advances"},{"key":"2026093017151717000_2026.09.23.753886v1.82","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btae119"},{"key":"2026093017151717000_2026.09.23.753886v1.83","first-page":"D213","article-title":"The InterPro protein families database: the classification resource after 15 years","volume":"43","year":"2014","journal-title":"Nucleic Acids Research"},{"key":"2026093017151717000_2026.09.23.753886v1.84","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa1105"},{"key":"2026093017151717000_2026.09.23.753886v1.85","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.03125"},{"key":"2026093017151717000_2026.09.23.753886v1.86","doi-asserted-by":"publisher","DOI":"10.1038\/nbt.3988"},{"key":"2026093017151717000_2026.09.23.753886v1.87","doi-asserted-by":"publisher","DOI":"10.1137\/040608635http:\/\/epubs.siam.org\/doi\/10.1137\/040608635"},{"key":"2026093017151717000_2026.09.23.753886v1.88","doi-asserted-by":"crossref","unstructured":"Shi, Y. , Ke, G. , Chen, Z. , Zheng, S. & Liu, T.-Y. Quantized Training of Gradient Boosting Decision Trees. in Advances in Neural Information Processing Systems (eds Koyejo, S. et al.) vol. 35 18822\u201318833 (Curran Associates, Inc., 2022).","DOI":"10.52202\/068431-1367"},{"key":"2026093017151717000_2026.09.23.753886v1.89","unstructured":"Head, T. , Kumar, M. , Nahrstaedt, H. , Louppe, G. & Shcherbatyi, I. scikit-optimize."},{"key":"2026093017151717000_2026.09.23.753886v1.90","unstructured":"Buitinck, L. et al. API design for machine learning software: experiences from the scikit-learn project. in ECML PKDD Workshop: Languages for Data Mining and Machine Learning 108\u2013 122 (2013)."},{"key":"2026093017151717000_2026.09.23.753886v1.91","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1016\/j.chom.2019.09.009","article-title":"The Human Gut Virome Is Highly Diverse, Stable, and Individual Specific","volume":"26","year":"2019","journal-title":"Cell Host and Microbe"},{"key":"2026093017151717000_2026.09.23.753886v1.92","doi-asserted-by":"publisher","DOI":"10.1101\/2023.04.19.537559"},{"key":"2026093017151717000_2026.09.23.753886v1.93","doi-asserted-by":"publisher","DOI":"10.46936\/10.25585\/60008876"},{"key":"2026093017151717000_2026.09.23.753886v1.94","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac1037"},{"key":"2026093017151717000_2026.09.23.753886v1.95","doi-asserted-by":"crossref","first-page":"33","DOI":"10.12688\/f1000research.29032.2","article-title":"Sustainable data analysis with Snakemake","volume":"10","year":"2021","journal-title":"F1000Research"},{"key":"2026093017151717000_2026.09.23.753886v1.96","doi-asserted-by":"publisher","DOI":"10.21231\/GNT1-HW21"},{"key":"2026093017151717000_2026.09.23.753886v1.97","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"2026093017151717000_2026.09.23.753886v1.98","doi-asserted-by":"crossref","first-page":"5233","DOI":"10.1038\/s41598-019-41695-z","article-title":"From Louvain to Leiden: guaranteeing well- connected communities","volume":"9","year":"2019","journal-title":"Scientific Reports"},{"key":"2026093017151717000_2026.09.23.753886v1.99","unstructured":"Cs\u00e1rdi, G. & Nepusz, T . The igraph software package for complex network research. InterJournal Complex Systems, 1695 (2006)."},{"key":"2026093017151717000_2026.09.23.753886v1.100","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.3530844"},{"key":"2026093017151717000_2026.09.23.753886v1.101","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.3002083"},{"key":"2026093017151717000_2026.09.23.753886v1.102","doi-asserted-by":"crossref","unstructured":"Heinzinger, M. , et al. Bilingual language model for protein sequence and structure. NAR Genomics and Bioinformatics 6, lqae150 (2024).","DOI":"10.1093\/nargab\/lqae150"},{"key":"2026093017151717000_2026.09.23.753886v1.103","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1038\/s41592-025-02593-7","article-title":"Rapid and sensitive protein complex alignment with Foldseek-Multimer","volume":"22","year":"2025","journal-title":"Nature Methods"},{"key":"2026093017151717000_2026.09.23.753886v1.104","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkae1119"},{"key":"2026093017151717000_2026.09.23.753886v1.105","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06510-w"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.23.753886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:15:48Z","timestamp":1790813748000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.23.753886"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,27]]},"references-count":105,"URL":"https:\/\/doi.org\/10.64898\/2026.09.23.753886","relation":{},"subject":[],"published":{"date-parts":[[2026,9,27]]},"subtype":"preprint"}}