{"id":"W4409226021","doi":"10.1016/j.xpro.2025.103733","title":"AMRLearn: Protocol for a machine learning pipeline for characterization of antimicrobial resistance determinants in microbial genomic data","year":2025,"lang":"en","type":"article","venue":"STAR Protocols","topic":"Metabolomics and Mass Spectrometry Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University; Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada; Gordon and Betty Moore Foundation","keywords":"Pipeline (software); Protocol (science); Antimicrobial; Antibiotic resistance; Computer science; Computational biology; Data science; Biology; Microbiology; Genetics; Bacteria; Medicine; Operating system","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004798744,0.0001631237,0.0003177786,0.0001029913,0.00008978478,0.00002274581,0.0003598315,0.0001021505,0.00000487577],"category_scores_gemma":[0.0002677547,0.0001593403,0.00006597359,0.0001281292,0.00006046656,0.00000818886,0.0002805028,0.0000746078,3.194328e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001803692,"about_ca_system_score_gemma":0.0001405564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009094371,"about_ca_topic_score_gemma":0.0002505011,"domain_scores_codex":[0.99872,0.00005626298,0.0004594278,0.0004634862,0.00004862752,0.0002522271],"domain_scores_gemma":[0.9991639,0.00001954599,0.000253163,0.0004202842,0.0001235506,0.00001954514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.002671805,0.0001198178,0.001897866,0.0009285091,0.00002663863,2.749441e-7,0.00001507847,0.000003076257,0.9920278,0.000103555,0.0008417757,0.001363814],"study_design_scores_gemma":[0.003997448,0.0001693195,0.0006890752,0.0001679044,0.00001060731,4.148559e-7,0.00000470098,0.0004514597,0.5457101,0.00004909363,0.4486109,0.0001389268],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"protocol","genre_gemma":"protocol","genre_scores_codex":[0.05527574,0.00001383026,0.02490928,0.000180574,0.00005151907,0.9181978,0.00129505,0.0000120776,0.00006419539],"genre_scores_gemma":[0.01113577,0.000008316032,0.007922152,0.00008240424,0.0001341663,0.9774382,0.0006963154,0.0000307737,0.00255196],"genre_candidate":"protocol","genre_consensus":"protocol","teacher_disagreement_score":0.4477692,"threshold_uncertainty_score":0.649771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0322901045997836,"score_gpt":0.3519667828803839,"score_spread":0.3196766782806003,"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."}}