{"id":"W2810986024","doi":"10.1016/j.inffus.2018.09.012","title":"Machine learning for integrating data in biology and medicine: Principles, practice, and opportunities","year":2018,"lang":"en","type":"article","venue":"Information Fusion","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":642,"is_retracted":false,"has_abstract":false,"ca_institutions":"SickKids Foundation; Vector Institute; Princess Margaret Cancer Centre; University of Toronto","funders":"National Institute of Biomedical Imaging and Bioengineering; Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Data science; Computer science; Systems biology; Identification (biology); Epigenome; Systems medicine; Field (mathematics); Implementation; Data integration; Big data; Grand Challenges; Bioinformatics; Data mining; Biology","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":[0.0004453846,0.00005633412,0.00005686108,0.00007069419,0.00009483883,0.00001790336,0.00007218937,0.00006594018,0.000009179665],"category_scores_gemma":[0.0006734102,0.00004467635,0.000004002806,0.00003305444,0.00007433243,0.00004505575,0.0001509399,0.00004771382,7.54559e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005030548,"about_ca_system_score_gemma":0.00002841259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004043037,"about_ca_topic_score_gemma":0.00003734647,"domain_scores_codex":[0.9995562,0.00003759316,0.0001885225,0.0001078318,0.00004154373,0.00006826387],"domain_scores_gemma":[0.99957,0.00002560351,0.0001319227,0.00014755,0.00009630787,0.00002868224],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004181752,0.00002227195,0.006595132,0.00009975478,0.00001627231,1.941657e-7,0.00221534,0.000009040659,0.2642967,0.01351268,0.004701138,0.7081134],"study_design_scores_gemma":[0.0005257334,0.0002471496,0.001259019,0.00002972701,0.000004467597,0.000007899849,0.001554775,0.01337156,0.002157978,0.00008486604,0.9806926,0.00006424297],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7449164,0.005923825,0.1775756,0.01661188,0.0008633762,0.001592338,0.0001374312,0.00008371461,0.05229542],"genre_scores_gemma":[0.9927129,0.002431772,0.002030481,0.0008602506,0.0001298663,0.00001806542,0.001653005,0.000004150089,0.0001595815],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9759914,"threshold_uncertainty_score":0.1821849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.064718829608819,"score_gpt":0.3548165048564162,"score_spread":0.2900976752475972,"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."}}