{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009346697,0.000107322,0.0001055064,0.00002010366,0.0001264259,0.00002090191,0.0004554979,0.0002472081,0.000007589619],"category_scores_gemma":[0.0004212047,0.0001051537,0.00009167828,0.0001109651,0.00004912367,0.000003036179,0.0001983291,0.0004293949,0.000006816445],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007540701,"about_ca_system_score_gemma":0.00002697632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004160939,"about_ca_topic_score_gemma":0.000014405,"domain_scores_codex":[0.9994221,0.00003622218,0.0001375403,0.0002290093,0.00003841849,0.0001366589],"domain_scores_gemma":[0.999247,0.000009141379,0.0000500766,0.0005297462,0.0001023262,0.00006177144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004404526,0.00002675702,0.00008799291,0.00001311898,0.00003296408,3.436001e-8,0.00004137657,0.00004816522,0.985695,0.0002033939,0.01320957,0.0005975618],"study_design_scores_gemma":[0.0001934761,0.00005154583,0.00002539297,0.000005313371,0.00001753529,0.000003847781,0.0000093689,0.0009880954,0.3583697,0.000003464126,0.6402347,0.00009753831],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6870832,0.1089596,0.09474469,0.09556906,0.002432841,0.003181201,0.0009235369,0.000788492,0.006317406],"genre_scores_gemma":[0.9805927,0.000590839,0.01609108,0.0009470719,0.0004010093,0.00002889213,0.0008314007,0.00002259592,0.0004944549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6273253,"threshold_uncertainty_score":0.4288044,"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."}}