{"id":"W4237627993","doi":"10.7287/peerj.preprints.27499v1","title":"ConFindr: Rapid detection of intraspecies and cross-species contamination in bacterial whole-genome sequence data","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Genomics and Phylogenetic Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Food Inspection Agency","funders":"","keywords":"Contamination; Computational biology; Biology; Whole genome sequencing; Genome; Computer science; Genetics; Gene","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01159179,0.002368846,0.001798679,0.002711103,0.001452193,0.003085132,0.003221654,0.001490902,0.004952],"category_scores_gemma":[0.01872624,0.00166346,0.002483991,0.002207972,0.001276526,0.002815939,0.004426661,0.003548143,0.005367964],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001126739,"about_ca_system_score_gemma":0.00249179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002364843,"about_ca_topic_score_gemma":0.003795781,"domain_scores_codex":[0.9931091,0.001274261,0.0005118858,0.002251942,0.00230197,0.0005508862],"domain_scores_gemma":[0.9929671,0.003162254,0.001181379,0.001464371,0.0008177105,0.0004071626],"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":[0.003388205,0.0006512388,0.04375739,0.00506613,0.00161424,0.001958022,0.002392384,0.0261018,0.3595574,0.0109758,0.2579962,0.2865412],"study_design_scores_gemma":[0.0007126569,0.001006548,0.04343922,0.0006675768,0.0003996557,0.002509242,0.0005114264,0.3680155,0.3919831,0.01992365,0.1699046,0.0009268019],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09269716,0.001107753,0.5151969,0.0009668221,0.0004024501,0.000863858,0.04815992,0.3344935,0.006111824],"genre_scores_gemma":[0.1367907,0.0005535005,0.7185062,0.001325992,0.0001088232,0.001680146,0.1075865,0.03084644,0.002601745],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01159179,"threshold_uncertainty_score":0.06130397,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04244409101550627,"score_gpt":0.2766416613452313,"score_spread":0.234197570329725,"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."}}