{"id":"W2113239687","doi":"10.2174/1381612820666140306104823","title":"Predicting Protein-Ligand Interactions Based on Chemical Preference Features with its Application to New D-Amino Acid Oxidase Inhibitor Discovery","year":2014,"lang":"en","type":"article","venue":"Current Pharmaceutical Design","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Biological Sciences","funders":"","keywords":"Support vector machine; D-amino acid oxidase; In silico; Ligand (biochemistry); Feature selection; Drug discovery; Computational biology; Fingerprint (computing); Artificial intelligence; Computer science; Quantitative structure–activity relationship; Oxidase test; Amino acid; Chemical space; Chemistry; Machine learning; Biology; Biochemistry; Enzyme; Gene","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005351263,0.0003223504,0.000235567,0.0001706525,0.0001376077,0.000373434,0.0007465844,0.00005602755,0.00000677043],"category_scores_gemma":[0.0005103904,0.000268459,0.00007289625,0.0006214544,0.00005053547,0.0008641654,0.0002185254,0.0005550729,0.00007823604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001522141,"about_ca_system_score_gemma":0.0002740685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001751203,"about_ca_topic_score_gemma":5.129386e-7,"domain_scores_codex":[0.9972538,0.0004063311,0.0003289213,0.0008879647,0.0006956908,0.000427345],"domain_scores_gemma":[0.9978291,0.0008927199,0.0001205598,0.0004978457,0.0001414046,0.0005183124],"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":[0.0008965631,0.0009827155,0.0001559623,0.0001718728,0.00003629901,0.000004314771,0.0003048232,0.07696999,0.4079125,0.02215506,0.001444201,0.4889657],"study_design_scores_gemma":[0.0006494542,0.0001967567,0.0003880541,0.0002266164,0.000019322,0.000005691205,0.000001708626,0.533965,0.4617088,0.001028943,0.001547367,0.000262273],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04880095,0.00005459991,0.9476467,0.001361644,0.0003863366,0.001343201,0.000008695021,0.0002227246,0.0001751355],"genre_scores_gemma":[0.9101611,0.000001389844,0.08847635,0.0004958054,0.0004166065,0.0003272021,0.00001553257,0.00002296246,0.00008307057],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8613601,"threshold_uncertainty_score":0.9999768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08307738992299077,"score_gpt":0.361995623888142,"score_spread":0.2789182339651513,"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."}}