{"id":"W2811501037","doi":"10.1016/j.meegid.2018.06.029","title":"Towards better prediction of Mycobacterium tuberculosis lineages from MIRU-VNTR data","year":2018,"lang":"en","type":"article","venue":"Infection Genetics and Evolution","topic":"Tuberculosis Research and Epidemiology","field":"Medicine","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Genotyping; Set (abstract data type); Artificial intelligence; Machine learning; Typing; Mycobacterium tuberculosis; Training set; Data mining; Tuberculosis; Biology; Genotype; Genetics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003743681,0.001426671,0.001299158,0.004404713,0.0005803896,0.001551249,0.001502869,0.001496822,0.0006620299],"category_scores_gemma":[0.0123455,0.0004704828,0.0008972001,0.002297612,0.0003085604,0.001803269,0.001035809,0.001769049,0.001488858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005823678,"about_ca_system_score_gemma":0.00146494,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01034216,"about_ca_topic_score_gemma":0.01813993,"domain_scores_codex":[0.9984292,0.0005909285,0.0001453557,0.0004251729,0.0003017785,0.000107564],"domain_scores_gemma":[0.9934248,0.003310871,0.0007364433,0.0008891016,0.001387621,0.0002511887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005593218,0.001053,0.1423169,0.0003297581,0.0003044286,0.000407021,0.0004291122,0.188431,0.02330444,0.001638512,0.01539373,0.6258328],"study_design_scores_gemma":[0.00002344325,0.00006974115,0.005515328,0.00003950844,0.00002893602,0.00007415035,0.000103576,0.9859405,0.004417218,0.002097914,0.001668977,0.00002073474],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3975371,0.003188881,0.5815624,0.001402988,0.0001485784,0.0003394266,0.00517631,0.00814796,0.002496438],"genre_scores_gemma":[0.4034029,0.0007472814,0.5769086,0.0005088816,0.000113584,0.0001470762,0.01649767,0.0002217451,0.00145225],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01034216,"threshold_uncertainty_score":0.0205639,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04431531856062019,"score_gpt":0.3223620938385618,"score_spread":0.2780467752779416,"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."}}