{"id":"W2407258532","doi":"10.1142/9789814447973_0005","title":"PROTEIN-CHEMICAL INTERACTION PREDICTION VIA KERNELIZED SPARSE LEARNING SVM","year":2012,"lang":"en","type":"article","venue":"","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Support vector machine; Artificial intelligence; Computer science; Machine learning; Classifier (UML); Feature vector; Pattern recognition (psychology); Feature selection; Multiple kernel learning; Similarity (geometry); Kernel (algebra); Kernel method; Data mining; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005836476,0.0001167371,0.0001103571,0.0000900669,0.00007579776,0.00009693166,0.0002617387,0.00005497169,0.00009417039],"category_scores_gemma":[0.0001668836,0.0001087153,0.00006535886,0.0002580773,0.00002020069,0.001612028,0.0002258089,0.0002404584,0.0002445469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001045089,"about_ca_system_score_gemma":0.00003091437,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002326513,"about_ca_topic_score_gemma":4.515175e-7,"domain_scores_codex":[0.9987174,0.0002280431,0.0002251501,0.0002553515,0.000308872,0.0002652059],"domain_scores_gemma":[0.9993386,0.0001723105,0.0000878535,0.0002114787,0.000069008,0.000120764],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000148941,0.0008304431,0.009048496,0.00006131069,0.0001123409,0.000007135365,0.002879043,0.04080754,0.3917661,0.1515208,0.001662185,0.4011557],"study_design_scores_gemma":[0.0003559826,0.000047247,0.004246147,0.00002220624,0.000006719444,0.00006108017,0.00003429177,0.9110421,0.07276469,0.004232503,0.006988758,0.0001982966],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2315769,0.00001950736,0.762706,0.0001992468,0.0005045099,0.0001523867,2.733154e-7,0.0002906209,0.004550595],"genre_scores_gemma":[0.8402184,9.118392e-7,0.1589714,0.00007291095,0.0002355508,0.00003042946,0.000006168679,0.000008197617,0.0004560025],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8702345,"threshold_uncertainty_score":0.4433282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02905198272514498,"score_gpt":0.3007938541414656,"score_spread":0.2717418714163206,"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."}}