{"id":"W2947383827","doi":"10.48550/arxiv.1905.12033","title":"Leveraging binding-site structure for drug discovery with point-cloud methods","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Leverage (statistics); Computer science; Drug discovery; Binding site; Ligand (biochemistry); Chemical space; Data mining; Protein ligand; Structural bioinformatics; Computational biology; Protein structure; Chemistry; Bioinformatics; Artificial intelligence; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009963003,0.0006525644,0.0007177693,0.0005582593,0.0002612065,0.0006546651,0.002554331,0.0002622961,0.00001669142],"category_scores_gemma":[0.0000951703,0.0006550826,0.0004095149,0.0008903244,0.000128304,0.001536074,0.002939166,0.0008680712,0.00003062303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004806457,"about_ca_system_score_gemma":0.0007539453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001049197,"about_ca_topic_score_gemma":0.00002847057,"domain_scores_codex":[0.9959198,0.0006919949,0.0003353122,0.002194835,0.0002240646,0.000633973],"domain_scores_gemma":[0.9957379,0.001415386,0.0005536925,0.001810219,0.0002933423,0.0001894376],"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":[0.0001043646,0.00004348204,0.001339781,0.0002293514,0.0002193743,0.00006248335,0.0006895245,0.9281253,0.0001354819,0.067359,0.0006171561,0.001074735],"study_design_scores_gemma":[0.00106497,0.00007236404,0.0009778568,0.0002483023,0.0001572069,0.00001992795,0.0001266175,0.8872184,0.0009496034,0.1067917,0.001336231,0.00103686],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3019421,0.00005787421,0.6948238,0.0001732973,0.00162256,0.0007012755,0.0001466113,0.0001847963,0.0003476921],"genre_scores_gemma":[0.703833,0.00001908318,0.2926874,0.0001719263,0.0001940643,0.000002878274,0.000127496,0.00005556664,0.002908526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4021364,"threshold_uncertainty_score":0.99959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06017913191449761,"score_gpt":0.2455665488642669,"score_spread":0.1853874169497693,"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."}}