{"id":"W3160021293","doi":"10.1093/bib/bbab159","title":"Utilizing graph machine learning within drug discovery and development","year":2021,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"","keywords":"Drug repositioning; Repurposing; Computer science; Drug discovery; Pipeline (software); Context (archaeology); Data science; Identification (biology); Drug development; Machine learning; Artificial intelligence; Key (lock); Drug; Bioinformatics; Engineering; Medicine; Pharmacology; 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":[0.0008423902,0.0001679214,0.0002057489,0.0001826077,0.0001739524,0.0005307464,0.0003127744,0.0000414001,0.000002778822],"category_scores_gemma":[0.0002983941,0.0001700177,0.00003350645,0.0005647808,0.00004993044,0.001608939,0.0007068947,0.0002821097,0.000008225008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006194988,"about_ca_system_score_gemma":0.0003083996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004505246,"about_ca_topic_score_gemma":0.0000574444,"domain_scores_codex":[0.9984778,0.00009409195,0.0005719877,0.0002399181,0.0003515011,0.0002647113],"domain_scores_gemma":[0.9991344,0.0003319702,0.0001784913,0.0002200459,0.00006442949,0.00007067053],"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":[0.00002835105,0.0002713816,0.02585485,0.0009551399,0.0001248829,0.0002273784,0.1066077,0.1355795,0.0002525726,0.32372,0.0006131576,0.4057651],"study_design_scores_gemma":[0.0005996447,0.00001391833,0.01008353,0.0002060513,0.000003955349,0.0001651604,0.0008857413,0.9691797,0.003723295,0.007017006,0.00768824,0.0004337572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1586056,0.000507661,0.8380101,0.0008475318,0.0002189478,0.0001089484,0.000002104565,0.0001169549,0.001582203],"genre_scores_gemma":[0.1264164,0.00006188513,0.8720194,0.001269923,0.00001215924,0.00000709193,0.00002011195,0.00001090223,0.0001821606],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8336002,"threshold_uncertainty_score":0.6933119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02108290369665256,"score_gpt":0.2570484905692298,"score_spread":0.2359655868725773,"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."}}