{"id":"W2081870567","doi":"10.1109/bigdata.2014.7004386","title":"Predicting a biological response of molecules from their chemical properties using diverse and optimized ensembles of stochastic gradient boosting machine","year":2014,"lang":"en","type":"article","venue":"","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Boosting (machine learning); Computer science; Gradient boosting; Artificial intelligence; Machine learning; Artificial neural network; Computation; Feed forward; Feature selection; Algorithm; Random forest; Engineering","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":[0.001454551,0.0008159361,0.001299621,0.0006438015,0.000270046,0.0004851165,0.0005514772,0.0006906497,0.0004199528],"category_scores_gemma":[0.001966049,0.0002983635,0.0009297269,0.0004456078,0.000243775,0.0005443543,0.0004546372,0.0007144514,0.0002005996],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003506601,"about_ca_system_score_gemma":0.0003999587,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001326776,"about_ca_topic_score_gemma":0.00178871,"domain_scores_codex":[0.9996161,0.0001556143,0.00001965732,0.00006829985,0.00009018366,0.00005003905],"domain_scores_gemma":[0.9994279,0.0002626891,0.00006764698,0.00008210655,0.000121016,0.00003861517],"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":[0.0001665021,0.0001170518,0.003466752,0.00003600748,0.0001189528,0.00004285968,0.00001993316,0.9174836,0.009925338,0.0005696749,0.0007397652,0.06731352],"study_design_scores_gemma":[0.000003495604,0.00002433587,0.000403289,0.000001252669,0.000008725541,0.000005452535,0.000001707556,0.9978535,0.001271121,0.000348206,0.00007582997,0.000003020293],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5051343,0.0009891221,0.4904859,0.0003097059,0.000116873,0.00007282969,0.0002081371,0.001274749,0.001408425],"genre_scores_gemma":[0.954567,0.0001728059,0.04433523,0.00008006049,0.00004288969,0.00005616117,0.0003078278,0.00003103727,0.0004070642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001454551,"threshold_uncertainty_score":0.007692456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05677704750939532,"score_gpt":0.2693980260167971,"score_spread":0.2126209785074017,"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."}}