{"id":"W2178378573","doi":"10.1016/j.vascn.2015.11.002","title":"Drug–target interaction prediction from PSSM based evolutionary information","year":2015,"lang":"en","type":"article","venue":"Journal of Pharmacological and Toxicological Methods","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":86,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Drug target; Artificial intelligence; Feature selection; Machine learning; Sampling (signal processing); Interaction information; In silico; Data mining; Selection (genetic algorithm); Similarity (geometry); Feature (linguistics); Mathematics; Statistics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00294813,0.0001845301,0.0003639172,0.0002138651,0.0001052769,0.0001467236,0.0004847073,0.000149055,0.0001381742],"category_scores_gemma":[0.001483543,0.000125958,0.0001515913,0.0003831749,0.0001037304,0.002201147,0.0002639811,0.0005731735,0.00001076025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002095666,"about_ca_system_score_gemma":0.0002041856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003835286,"about_ca_topic_score_gemma":1.030156e-7,"domain_scores_codex":[0.9960048,0.002244726,0.0007959792,0.0002255376,0.000509401,0.000219595],"domain_scores_gemma":[0.9960179,0.002452933,0.0005599659,0.0001036433,0.000456772,0.0004087412],"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":[0.002295468,0.002239083,0.005318011,0.0000320707,0.0004394731,0.0001899108,0.001110958,0.2115266,0.02546207,0.01781946,0.0298092,0.7037576],"study_design_scores_gemma":[0.002304011,0.00124798,0.03649759,0.0000227217,0.00008694892,0.000144574,0.0001245888,0.7848879,0.007862866,0.1277181,0.03886211,0.0002406431],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1408255,0.0003307623,0.8532173,0.00280802,0.002012296,0.0001491771,0.00001263264,0.00007021375,0.0005740604],"genre_scores_gemma":[0.3206827,0.00002423299,0.6775541,0.001424874,0.0002889282,0.000009514486,0.000005777403,0.000002667259,0.000007191621],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.703517,"threshold_uncertainty_score":0.5136418,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07679987416263229,"score_gpt":0.4035093873956537,"score_spread":0.3267095132330214,"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."}}