{"id":"W3090915092","doi":"10.1021/acs.jcim.0c00833","title":"<tt>OptiMol</tt> : Optimization of Binding Affinities in Chemical Space for Drug Discovery","year":2020,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":66,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Agence Nationale de la Recherche; Natural Sciences and Engineering Research Council of Canada; Government of Canada","keywords":"Chemical space; Computer science; Drug discovery; Docking (animal); Leverage (statistics); Oracle; Graph; Autoencoder; Artificial intelligence; Theoretical computer science; Bioinformatics; Deep learning; 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":[],"consensus_categories":[],"category_scores_codex":[0.0004354641,0.0000922715,0.0002277201,0.000154392,0.00002014311,0.0001430717,0.0002345339,0.00004711159,0.000001347437],"category_scores_gemma":[0.0004029892,0.00008513172,0.00008385577,0.0002095973,0.00002271546,0.003518281,0.0001097427,0.0001529804,2.86545e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004393237,"about_ca_system_score_gemma":0.0001212904,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002157706,"about_ca_topic_score_gemma":5.240177e-8,"domain_scores_codex":[0.9987836,0.00002365007,0.0007353952,0.0000787301,0.0002630703,0.0001154948],"domain_scores_gemma":[0.9990198,0.0002377829,0.0003780801,0.0000585346,0.0002230907,0.00008271004],"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":[0.00007349379,0.00001537912,0.00001193491,0.00008417212,0.000008900527,3.30526e-7,0.002674519,0.9863989,0.004326765,0.004149186,0.00004818954,0.002208202],"study_design_scores_gemma":[0.0006526914,0.00002312255,9.397887e-7,0.00007958252,0.000006567965,0.00001037209,0.0003159793,0.9719715,0.02547184,0.001343377,0.0000373169,0.00008669143],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3162847,0.00003565857,0.6822261,0.001262779,0.00004983787,0.00006545419,0.000003255516,0.000007292688,0.00006493171],"genre_scores_gemma":[0.7001474,0.00002458461,0.2995704,0.000204453,0.00004083897,0.000001812728,0.000006384884,0.000003154781,9.435963e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3838627,"threshold_uncertainty_score":0.3471571,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04022574581930739,"score_gpt":0.2862528614148656,"score_spread":0.2460271155955582,"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."}}