{"id":"W3026996309","doi":"10.1038/s41467-020-16310-9","title":"A biochemically-interpretable machine learning classifier for microbial GWAS","year":2020,"lang":"en","type":"article","venue":"Nature Communications","topic":"Microbial Metabolic Engineering and Bioproduction","field":"Biochemistry, Genetics and Molecular Biology","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"National Institute of Allergy and Infectious Diseases; National Institute of General Medical Sciences; Novo Nordisk; Novo Nordisk Fonden; U.S. Department of Health and Human Services","keywords":"Genome-wide association study; Classifier (UML); Artificial intelligence; Computer science; Computational biology; Machine learning; Biology; Biochemistry; Single-nucleotide polymorphism","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":[0.00241271,0.0008862072,0.0009757469,0.001751201,0.0003542484,0.001176197,0.0007625529,0.00140809,0.001371373],"category_scores_gemma":[0.008460143,0.000187303,0.00080036,0.0008262824,0.0003122316,0.0005750574,0.0005056778,0.001207709,0.0007361436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005334342,"about_ca_system_score_gemma":0.0008215734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001310504,"about_ca_topic_score_gemma":0.001235583,"domain_scores_codex":[0.9992496,0.0002737992,0.00006944813,0.0001916572,0.0001533841,0.00006206262],"domain_scores_gemma":[0.9970483,0.001775087,0.0002666576,0.0003333264,0.0004896838,0.00008693075],"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":[0.001324433,0.0007777518,0.1112656,0.0003734289,0.0007228512,0.0007326293,0.0001020249,0.1875136,0.05182281,0.01353304,0.01285012,0.6189817],"study_design_scores_gemma":[0.00006505564,0.0001946332,0.005217603,0.00002904977,0.00007460053,0.0002054825,0.00001969095,0.9673834,0.008494912,0.01609103,0.002191625,0.0000328494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2048562,0.001670554,0.7793566,0.001624675,0.0002548152,0.0002095505,0.005073375,0.003951195,0.003003035],"genre_scores_gemma":[0.7545774,0.0003449839,0.2387421,0.0005774754,0.0002450909,0.0002922094,0.003788298,0.00008191202,0.001350592],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00241271,"threshold_uncertainty_score":0.01275975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0137034740997048,"score_gpt":0.2597353402035396,"score_spread":0.2460318661038348,"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."}}