{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03127309,0.00134769,0.002347266,0.00513162,0.0009899833,0.009751108,0.003384365,0.004306385,0.001781828],"category_scores_gemma":[0.03434939,0.0009447473,0.001229078,0.00613843,0.009644618,0.01742116,0.005195647,0.007396892,0.001042406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002539437,"about_ca_system_score_gemma":0.003154663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00129588,"about_ca_topic_score_gemma":0.001029659,"domain_scores_codex":[0.9894714,0.006427625,0.0006352743,0.00082157,0.002443916,0.0002001635],"domain_scores_gemma":[0.9547186,0.03762462,0.0008905623,0.004033224,0.001986875,0.0007460734],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001018205,0.0001673407,0.00364319,0.001188037,0.0001601855,0.0001509831,0.0006626052,0.008136914,0.0008359053,0.6536917,0.007190786,0.3240706],"study_design_scores_gemma":[0.00001917198,0.00004532659,0.0004068391,0.0006652429,0.00002170455,0.0002001594,0.0002201283,0.03760991,0.0007595002,0.9400825,0.0199247,0.00004491886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.005751457,0.08371989,0.8479134,0.05249601,0.0004534345,0.0001827478,0.0001719013,0.000554799,0.008756286],"genre_scores_gemma":[0.161372,0.05955782,0.7695403,0.003309715,0.00293123,0.0004423459,0.0002488675,0.0001605105,0.002437292],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.03127309,"threshold_uncertainty_score":0.1653899,"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."}}