{"id":"W2810326626","doi":"10.1101/362780","title":"An open-source <i>k</i> -mer based machine learning tool for fast and accurate subtyping of HIV-1 genomes","year":2018,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Western University","funders":"","keywords":"Subtyping; Computer science; Workflow; Software; Machine learning; Artificial intelligence; Intrusion detection system; Human immunodeficiency virus (HIV); Data mining; Biology; Virology; Database; Operating system; Programming language","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":[0.001569206,0.001684195,0.0009290215,0.002188285,0.000793043,0.001165109,0.002661535,0.001289914,0.01000036],"category_scores_gemma":[0.00732292,0.0007887107,0.001353587,0.001662775,0.0004378018,0.001568697,0.001916717,0.001663749,0.008731857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004818683,"about_ca_system_score_gemma":0.001231136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00165744,"about_ca_topic_score_gemma":0.002079015,"domain_scores_codex":[0.9986832,0.0001800565,0.000149539,0.0004019757,0.000488364,0.00009690466],"domain_scores_gemma":[0.9971343,0.001236821,0.0003562353,0.0006014659,0.0005164364,0.000154665],"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":[0.001791672,0.00072081,0.01533596,0.001532412,0.0006106824,0.0007153194,0.0005537642,0.01944398,0.1013073,0.004222355,0.1488412,0.7049246],"study_design_scores_gemma":[0.0003882973,0.0003844422,0.01463799,0.0002548848,0.0001515832,0.001018502,0.0001088421,0.7391191,0.1638291,0.009426234,0.07037419,0.0003068042],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"software","genre_scores_codex":[0.02108039,0.0003487729,0.5374341,0.0001888543,0.0002033375,0.0002493859,0.009594105,0.4287005,0.002200552],"genre_scores_gemma":[0.1241282,0.0002300008,0.8176537,0.0002902061,0.0001022592,0.0007065955,0.0256211,0.0268478,0.004420084],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01000036,"threshold_uncertainty_score":0.03345448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01389568952157513,"score_gpt":0.2340852693346608,"score_spread":0.2201895798130856,"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."}}