{"id":"W4380684099","doi":"10.1093/jacamr/dlad066.004","title":"O04 Understanding the key role of accessory genes in AMR phenotype through interpretable machine learning techniques","year":2023,"lang":"en","type":"article","venue":"JAC-Antimicrobial Resistance","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Phenotype; Gene; Biology; Genotype; Computational biology; Genotype-phenotype distinction; C4.5 algorithm; Phenotypic trait; Genome; Genetics; Bioinformatics; Computer science; Machine learning; Naive Bayes classifier","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":[0.000265592,0.000165406,0.0002304129,0.00005356842,0.0001565705,0.00002990451,0.0003290356,0.00009866103,0.000007110651],"category_scores_gemma":[0.00008479907,0.0001373417,0.00009009842,0.000281795,0.0001468753,0.000003140109,0.0002619363,0.0001362148,0.000004185104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003257021,"about_ca_system_score_gemma":0.0000473663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001358235,"about_ca_topic_score_gemma":0.0008557967,"domain_scores_codex":[0.9989247,0.00008518265,0.0002817587,0.0003157499,0.00009641399,0.0002961555],"domain_scores_gemma":[0.9994538,0.00004725692,0.0001443164,0.0002862614,0.00004888971,0.00001947694],"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":[0.0001500837,0.00001947391,0.006424814,0.00004821381,0.00005300284,0.000001669715,0.0006152393,0.0004971973,0.9906909,0.0004828424,0.000692023,0.0003245753],"study_design_scores_gemma":[0.0003565646,0.00009071214,0.005102823,0.0001302552,0.0000295296,0.000002176677,0.0007862383,0.0001294224,0.9166377,0.002617325,0.07379031,0.0003269652],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9848461,0.006431884,0.001150774,0.0004297225,0.0001527862,0.0003018579,0.00005418097,0.00002572269,0.00660697],"genre_scores_gemma":[0.9932371,0.004148236,0.001373908,0.000124523,0.00008155947,0.00001711576,0.00002321153,0.00002989186,0.0009644852],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07405319,"threshold_uncertainty_score":0.5600633,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02044645330604268,"score_gpt":0.254888187003087,"score_spread":0.2344417336970443,"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."}}