{"id":"W2951725148","doi":"10.1371/journal.pone.0206409","title":"An open-source k-mer based machine learning tool for fast and accurate subtyping of HIV-1 genomes","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":99,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Genome Canada; Ontario Genomics; Canadian Institutes of Health Research; Government of Canada; Ontario Genomics Institute","keywords":"Subtyping; Computer science; Workflow; Software; Machine learning; Artificial intelligence; Data mining; False positive paradox; Database","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001238617,0.001559207,0.001030236,0.002359797,0.0008824756,0.000912762,0.002015997,0.001184639,0.00826052],"category_scores_gemma":[0.006561837,0.000681958,0.001173424,0.002061932,0.0003600674,0.001562163,0.001828733,0.001673725,0.007627783],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000440852,"about_ca_system_score_gemma":0.001280756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001662889,"about_ca_topic_score_gemma":0.003202203,"domain_scores_codex":[0.998861,0.0001730381,0.00011973,0.000308999,0.0004589666,0.0000782971],"domain_scores_gemma":[0.9982442,0.0008328583,0.0002387168,0.0003178709,0.0002830272,0.00008343966],"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":[0.001335134,0.000456591,0.01325378,0.001465008,0.000546654,0.0005394501,0.0005530255,0.01680686,0.06268402,0.003196309,0.1172938,0.7818694],"study_design_scores_gemma":[0.0004649711,0.0005018855,0.02512313,0.0003033595,0.0001992499,0.001635004,0.0001829464,0.7294793,0.1097838,0.01665376,0.1153528,0.0003198216],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03085258,0.001075843,0.6353412,0.0002350497,0.0002437862,0.0003230429,0.01632502,0.3124988,0.003104694],"genre_scores_gemma":[0.124023,0.0004978715,0.8312243,0.0002710409,0.00008309103,0.0007935947,0.02773483,0.01015509,0.005217189],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00826052,"threshold_uncertainty_score":0.0276342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03275651240184892,"score_gpt":0.2516375323218455,"score_spread":0.2188810199199966,"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."}}