{"id":"W2605952223","doi":"10.1186/s13321-017-0209-z","title":"SimBoost: a read-across approach for predicting drug–target binding affinities using gradient boosting machines","year":2017,"lang":"en","type":"article","venue":"Journal of Cheminformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":509,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cheminformatics; Benchmark (surveying); Computer science; Binding affinities; Binary number; Boosting (machine learning); Drug discovery; Drug target; Affinities; Gradient boosting; Machine learning; Binary classification; Artificial intelligence; Data mining; Bioinformatics; Support vector machine; Random forest; Mathematics; Chemistry; Biology","routes":{"ca_aff":true,"ca_fund":true,"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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002596968,0.0002055158,0.000396856,0.0001372718,0.0009208538,0.001087234,0.001423402,0.00005717106,0.000001123242],"category_scores_gemma":[0.00205195,0.0001788413,0.0002246725,0.0001053777,0.00009116451,0.003113128,0.0005214381,0.0002790877,5.413373e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001354026,"about_ca_system_score_gemma":0.0002050542,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004961287,"about_ca_topic_score_gemma":3.438979e-7,"domain_scores_codex":[0.9978514,0.00002256636,0.001036197,0.0001271898,0.000562957,0.000399713],"domain_scores_gemma":[0.995802,0.0008332785,0.002391178,0.0004203856,0.000420639,0.0001325185],"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":[0.0002459804,0.0005077032,0.0222003,0.00377555,0.0007814259,0.00006643806,0.1478195,0.6253841,0.002282974,0.01154064,0.001568731,0.1838266],"study_design_scores_gemma":[0.0005870513,0.00004643034,0.0002742142,0.0002312637,0.0000246637,0.0003204383,0.001403382,0.9899146,0.004450691,0.002140689,0.0004030989,0.0002034786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3312326,0.00006072224,0.6654793,0.0001009382,0.0005423938,0.0001443581,0.00001770241,0.00002470625,0.002397204],"genre_scores_gemma":[0.3024243,0.00000625333,0.6971593,0.00004924451,0.0002675636,0.000003234742,0.000004036769,0.00001329157,0.00007272822],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3645305,"threshold_uncertainty_score":0.9999498,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06109063848381403,"score_gpt":0.3506717947180562,"score_spread":0.2895811562342422,"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."}}