{"id":"W2292188326","doi":"10.1186/s12863-015-0315-8","title":"Machine learning and data mining in complex genomic data—a review on the lessons learned in Genetic Analysis Workshop 19","year":2016,"lang":"en","type":"article","venue":"BMC Genetics","topic":"Genetic Associations and Epidemiology","field":"Biochemistry, Genetics and Molecular Biology","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"National Institute of General Medical Sciences; National Human Genome Research Institute; National Institutes of Health; Bundesministerium für Bildung und Forschung","keywords":"Computer science; Data science; Data mining; Machine learning; Domain (mathematical analysis); Artificial intelligence; Data analysis","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":[0.001577218,0.0002031054,0.0003864434,0.0001162067,0.0000923301,0.00001942679,0.0008943229,0.0001451944,0.00006100372],"category_scores_gemma":[0.001686551,0.0001379208,0.00005125018,0.0003578362,0.0001041214,0.000003138352,0.001197109,0.0001460151,0.00001033947],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002615254,"about_ca_system_score_gemma":0.00009285899,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000071645,"about_ca_topic_score_gemma":0.004606441,"domain_scores_codex":[0.9974765,0.0007021925,0.0004986698,0.0008368532,0.000116165,0.0003696853],"domain_scores_gemma":[0.9976901,0.0003856662,0.0002031141,0.001614525,0.00002887069,0.00007770292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002375194,0.00004501649,0.960061,0.00004487509,0.000140089,0.000002576491,0.00003357184,0.002016161,0.00508753,0.00001373091,0.0024675,0.03006424],"study_design_scores_gemma":[0.0007542326,0.0000949491,0.8950601,0.0001356959,0.0002697758,0.000007224795,0.0001368242,0.02903832,0.0000342613,0.00008673724,0.07402353,0.0003582939],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9338292,0.05294506,0.005187672,0.007150194,0.00004258253,0.0003984961,0.0002543291,0.000009168121,0.0001832808],"genre_scores_gemma":[0.8882146,0.09999312,0.009228118,0.0009649202,0.00007849949,0.00001976542,0.001098248,0.00002613392,0.0003766125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07155603,"threshold_uncertainty_score":0.5624246,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1998776137197517,"score_gpt":0.3931610038036311,"score_spread":0.1932833900838793,"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."}}