{"id":"W3082897678","doi":"10.1158/1538-7445.am2020-2102","title":"Abstract 2102: Interpretable machine learning for perturbation biology","year":2020,"lang":"en","type":"article","venue":"Cancer Research","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Artificial intelligence; Machine learning; Computer science; Systems biology; Deep learning; Computational biology; Biology","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003412836,0.001560882,0.0008313796,0.0008590934,0.000319865,0.001620028,0.001560206,0.001391919,0.01236261],"category_scores_gemma":[0.008677839,0.0005559021,0.0009866275,0.0008890472,0.001123534,0.001830888,0.00189999,0.003326224,0.003803932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001061824,"about_ca_system_score_gemma":0.001193915,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001624578,"about_ca_topic_score_gemma":0.001663856,"domain_scores_codex":[0.998702,0.0005921124,0.00006532722,0.0002183257,0.0003802367,0.00004187007],"domain_scores_gemma":[0.9971097,0.001560809,0.0002025184,0.000558862,0.0004600069,0.0001080995],"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":[0.0003049097,0.0001611502,0.001653583,0.0008521285,0.0002149203,0.0002656245,0.000140472,0.3831043,0.0152989,0.2048447,0.1378246,0.2553347],"study_design_scores_gemma":[0.00002537484,0.00003036313,0.0002626656,0.00004889771,0.00001067821,0.00003194074,0.000007298132,0.8721318,0.002106681,0.1051006,0.02022613,0.0000176773],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002680133,0.001414259,0.9813918,0.003288433,0.0005328846,0.00009785888,0.002323485,0.004636363,0.003634739],"genre_scores_gemma":[0.1581845,0.003527601,0.8109897,0.001065781,0.001438456,0.001045463,0.01038704,0.001736544,0.0116249],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01236261,"threshold_uncertainty_score":0.04135704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.172936228928175,"score_gpt":0.4679638168406103,"score_spread":0.2950275879124352,"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."}}