{"id":"W2767799647","doi":"10.1101/217695","title":"Mining the forest: uncovering biological mechanisms by interpreting Random Forests","year":2017,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"BC Cancer Agency; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Cancer Research UK","keywords":"Random forest; Computer science; Ranking (information retrieval); Interpretation (philosophy); Biological data; Artificial intelligence; Futures studies; Machine learning; Exploit; Data mining; Bioinformatics; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003017674,0.0009510575,0.001014626,0.003295231,0.0006295335,0.001757864,0.001173489,0.001065327,0.001272148],"category_scores_gemma":[0.009171836,0.0004270898,0.001525136,0.001805263,0.001110559,0.001821689,0.0008050742,0.00117943,0.0004337392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005374205,"about_ca_system_score_gemma":0.0007679497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001868312,"about_ca_topic_score_gemma":0.002261171,"domain_scores_codex":[0.9991392,0.0004063715,0.00004317075,0.0001722088,0.0001568596,0.00008226644],"domain_scores_gemma":[0.9944436,0.003782113,0.0006794044,0.0006073032,0.0003251506,0.00016245],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005062324,0.0003500296,0.06540699,0.0007953087,0.0004536964,0.001527953,0.0005187471,0.5968413,0.02454679,0.1237648,0.01132541,0.1739627],"study_design_scores_gemma":[0.00001989972,0.00003514793,0.00236119,0.00004583236,0.0000334026,0.0001497973,0.00005506444,0.857165,0.002441195,0.1361701,0.001502015,0.00002139041],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1129869,0.001336836,0.8794934,0.001221886,0.00006390357,0.00009351377,0.001631349,0.001617598,0.001554559],"genre_scores_gemma":[0.757427,0.0006531331,0.2384489,0.0002836354,0.0001309945,0.0001213265,0.00227155,0.0001408446,0.0005225899],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003295231,"threshold_uncertainty_score":0.0159592,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01499947089287178,"score_gpt":0.2413839260935517,"score_spread":0.2263844552006799,"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."}}