{"id":"W2743821210","doi":"10.1101/173146","title":"chewBBACA: A complete suite for gene-by-gene schema creation and strain identification","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":100,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Public Health Agency; Public Health Agency of Canada","keywords":"Computer science; Suite; Genome; File format; Software suite; Software; Directory; Source code; Computational biology; Database; Gene; Biology; Genetics; Programming language; Operating system","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004737569,0.0004187083,0.0003851845,0.00006774799,0.0003566877,0.0002542374,0.0004150545,0.0004677234,0.000002286586],"category_scores_gemma":[0.0001865346,0.0004799606,0.0001339102,0.00004211993,0.0001786068,0.000003270588,0.0004488688,0.0001595662,0.000003864545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004395341,"about_ca_system_score_gemma":0.0001884211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002993883,"about_ca_topic_score_gemma":0.000005529638,"domain_scores_codex":[0.9980298,0.00004899754,0.0004013934,0.001008027,0.0001459644,0.0003657985],"domain_scores_gemma":[0.9978029,0.00001884439,0.0005040218,0.001110548,0.0004191651,0.0001445477],"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":[0.00003499448,0.00004164554,0.002274121,0.0001601619,0.0002129776,9.545348e-7,0.00000679566,0.00001284461,0.9967183,0.00007687406,0.0004497144,0.00001062311],"study_design_scores_gemma":[0.0005914392,0.00007535396,0.08372305,0.00004036702,0.0001259288,3.073329e-8,0.000002105483,0.000113407,0.9024562,0.00001168354,0.01232622,0.0005342105],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841754,0.005071155,0.00551699,0.0001840254,0.0004442486,0.0009709636,0.0036124,0.0000197331,0.00000504145],"genre_scores_gemma":[0.9915408,0.001744565,0.005516593,0.00008403177,0.000563201,0.0004037195,0.00002883649,0.00008802181,0.00003026366],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09426209,"threshold_uncertainty_score":0.9997652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02003474481077103,"score_gpt":0.2438190952378011,"score_spread":0.22378435042703,"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."}}