{"id":"W2941864079","doi":"10.7717/peerj.6995","title":"ConFindr: rapid detection of intraspecies and cross-species contamination in bacterial whole-genome sequence data","year":2019,"lang":"en","type":"article","venue":"PeerJ","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":147,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Food Inspection Agency","funders":"Canadian Food Inspection Agency","keywords":"Contamination; Computational biology; Whole genome sequencing; Genome; Biology; Computer science; Genetics; Data mining; Gene","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":[0.0001673695,0.00008246103,0.0001326531,0.00003174158,0.00002540494,0.00002298885,0.0001441956,0.00006747891,0.0000255996],"category_scores_gemma":[0.00005225505,0.0000823932,0.00001643382,0.00003681858,0.0001083754,0.00000267471,0.0001810262,0.00003696636,0.000002723891],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008168269,"about_ca_system_score_gemma":0.00002234751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003710345,"about_ca_topic_score_gemma":0.0001597274,"domain_scores_codex":[0.999391,0.00002293359,0.0001642249,0.0002509519,0.00006268892,0.0001081752],"domain_scores_gemma":[0.9995487,0.00001420918,0.0000683691,0.0002852191,0.00006530483,0.00001821909],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00005213476,0.00001109705,0.02441171,0.0000190844,0.00001780788,2.908715e-7,0.0000976864,0.000009119274,0.9731857,0.00003922782,0.00001121233,0.002144921],"study_design_scores_gemma":[0.0006443652,0.0001979134,0.6700303,0.000005418276,0.000006794335,0.000005204296,0.000123207,0.00005905934,0.2596061,0.00002464802,0.0691806,0.0001164328],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9978189,0.0009220569,0.00006478543,0.0000508763,0.0002562436,0.0001418083,0.0003142022,0.000001452065,0.0004296932],"genre_scores_gemma":[0.9984479,0.0005365792,0.00007519733,0.00001836926,0.0001015765,0.000004238247,0.0003128148,0.000006746382,0.0004965889],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7135797,"threshold_uncertainty_score":0.3359897,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02802214653020833,"score_gpt":0.2611038732426098,"score_spread":0.2330817267124014,"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."}}