{"id":"W4291288469","doi":"10.1038/s42256-022-00463-x","title":"The transformational role of GPU computing and deep learning in drug discovery","year":2022,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":260,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"Canadian Institutes of Health Research","keywords":"Drug discovery; Computer science; Deep learning; Data science; Artificial intelligence; Field (mathematics); Parallelizable manifold; Lead (geology); Machine learning; Bioinformatics; Algorithm","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":[0.001469608,0.0001155488,0.0001372097,0.0001364294,0.0003881243,0.00011627,0.0008499451,0.00003234377,0.00000617395],"category_scores_gemma":[0.0001722226,0.00009420687,0.00005432636,0.0006378309,0.00006859574,0.0004263998,0.0005691815,0.001120982,8.112655e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000610994,"about_ca_system_score_gemma":0.00007262564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008415789,"about_ca_topic_score_gemma":0.00006913773,"domain_scores_codex":[0.9982732,0.0004157319,0.0003483464,0.0002613115,0.0005100819,0.0001913343],"domain_scores_gemma":[0.9979496,0.001664494,0.0001309244,0.0001765707,0.00004831288,0.00003012567],"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":[0.00001805991,0.00003006307,0.001844212,0.000009389892,0.000007545528,0.000002707112,0.003168376,0.4281334,0.00008757067,0.2289567,0.000004260944,0.3377378],"study_design_scores_gemma":[0.00006733392,0.0000316779,0.008063192,0.00001140297,0.000001877353,0.00003446001,0.0005487255,0.9426109,0.001190361,0.0449525,0.0023753,0.0001123231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1451455,0.008383397,0.8434941,0.001283276,0.0003365916,0.0001937179,0.000007061233,0.00004813601,0.001108215],"genre_scores_gemma":[0.9892173,0.00006140909,0.01050578,0.0001342001,0.00002185055,0.000008212042,0.000006629206,0.00000622462,0.00003838975],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8440718,"threshold_uncertainty_score":0.4870171,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00461789881164311,"score_gpt":0.2761253986241451,"score_spread":0.2715074998125021,"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."}}