{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007787666,0.0004924449,0.0003879292,0.0000688436,0.0004443737,0.0003637772,0.001211046,0.0007166607,0.00001567113],"category_scores_gemma":[0.000642476,0.0003820378,0.0002341608,0.00008232255,0.0001862411,0.0000115179,0.001116129,0.0004668205,0.00001111396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007217262,"about_ca_system_score_gemma":0.0002707938,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002366865,"about_ca_topic_score_gemma":0.000009836055,"domain_scores_codex":[0.9975567,0.0001943753,0.0004397484,0.001053214,0.0002682458,0.0004876889],"domain_scores_gemma":[0.9971502,0.00004207658,0.000636754,0.001770983,0.0002294544,0.000170513],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001182707,0.00003371312,0.005775531,0.00004602811,0.00009428776,0.000004060894,0.000007517319,0.0001465266,0.9898255,0.0001196474,0.003814387,0.00001445846],"study_design_scores_gemma":[0.001048684,0.0001212409,0.0152215,0.0003892584,0.00006325695,5.801002e-8,0.00001603557,0.0006335599,0.9396445,0.00003149145,0.04202132,0.0008091343],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9336984,0.002384862,0.06108015,0.0004201689,0.001493106,0.0006683847,0.00009760376,0.000103967,0.00005331431],"genre_scores_gemma":[0.9967288,0.000487557,0.001496564,0.000324519,0.0004641006,0.000379798,0.000004098672,0.000088266,0.00002626094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0630304,"threshold_uncertainty_score":0.9998631,"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."}}