{"id":"W2912546897","doi":"10.1101/533240","title":"Gene sharing networks to automate genome-based prokaryotic viral taxonomy","year":2019,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Bacteriophages and microbial interactions","field":"Environmental Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"U.S. National Library of Medicine; National Institute of Allergy and Infectious Diseases; Office of Science; Battelle; Joint Genome Institute; U.S. Department of Energy; Gordon and Betty Moore Foundation; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Metagenomics; Taxonomy (biology); Genome; Computational biology; Scalability; Biology; Archaea; Computer science; Taxonomic rank; Cluster analysis; Virus classification; Data science; Taxon; Artificial intelligence; Gene; Genetics; Ecology; Database","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002129189,0.00105756,0.0005763054,0.00491983,0.0009435455,0.002108203,0.001216958,0.0006569126,0.002155951],"category_scores_gemma":[0.009351035,0.0005708432,0.0007222284,0.002858125,0.0004727232,0.001725715,0.001913642,0.001308461,0.001239818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001837915,"about_ca_system_score_gemma":0.001462992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009790351,"about_ca_topic_score_gemma":0.01393226,"domain_scores_codex":[0.9986558,0.0002993569,0.0000840763,0.0004973901,0.000370162,0.0000932582],"domain_scores_gemma":[0.9965077,0.001322264,0.0004813155,0.0006357623,0.0008680175,0.0001848297],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0008035202,0.0003593808,0.09404001,0.001259555,0.0006039523,0.000344115,0.001507129,0.2697086,0.1335583,0.03270429,0.02512459,0.4399866],"study_design_scores_gemma":[0.00001913674,0.00004655427,0.008520672,0.00007993071,0.00004320682,0.0001001583,0.0001843775,0.9328697,0.02937547,0.01759654,0.01112589,0.00003839041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2043692,0.0008603364,0.7488747,0.0004703308,0.0001563038,0.0002838462,0.01215557,0.02736022,0.005469528],"genre_scores_gemma":[0.3873884,0.0004203706,0.5889759,0.0001230883,0.00005141481,0.0002217033,0.01940675,0.001695271,0.001717153],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009790351,"threshold_uncertainty_score":0.01946676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01318789920997631,"score_gpt":0.2037103019941839,"score_spread":0.1905224027842076,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}