{"id":"W3132689447","doi":"10.1093/bib/bbac404","title":"A review of biomedical datasets relating to drug discovery: a knowledge graph perspective","year":2022,"lang":"en","type":"review","venue":"Briefings in Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":118,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"University of Cambridge; AstraZeneca","keywords":"Drug discovery; Computer science; Drug repositioning; Repurposing; Data science; Field (mathematics); Prioritization; Key (lock); Knowledge extraction; Domain knowledge; Construct (python library); Domain (mathematical analysis); Pipeline (software); Perspective (graphical); Identification (biology); Drug; Artificial intelligence; Bioinformatics; Medicine; Management science; Pharmacology","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":[0.003236568,0.000527771,0.002046129,0.001155732,0.0001244804,0.0001632703,0.002699698,0.0001234045,0.00002856286],"category_scores_gemma":[0.002892608,0.0004775534,0.0005542796,0.004933504,0.0001229748,0.001186423,0.003415957,0.0008432748,0.00004327001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006912003,"about_ca_system_score_gemma":0.001605314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001638651,"about_ca_topic_score_gemma":0.000008340631,"domain_scores_codex":[0.9951815,0.0006101302,0.002292215,0.0005867061,0.0008586143,0.000470844],"domain_scores_gemma":[0.9949321,0.002349674,0.001239228,0.001193716,0.0001062211,0.0001791213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001434579,0.0001353531,1.32457e-7,0.1013997,0.00006744358,0.00001079418,0.00267001,0.00002986615,8.936596e-9,0.0349455,0.03511763,0.8256222],"study_design_scores_gemma":[0.0001241522,0.00004743238,7.036828e-7,0.09783715,0.00009766964,0.00009208333,0.00009892756,0.003895515,9.638693e-8,0.001449404,0.8959103,0.0004466335],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.289336e-7,0.90808,0.087294,0.0003749134,0.0003493917,0.00121188,0.0006162454,0.00006240413,0.00201107],"genre_scores_gemma":[6.083712e-8,0.8554309,0.1426553,0.001159011,0.0000334622,0.000153995,0.0005064791,0.00002793938,0.00003288424],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8607926,"threshold_uncertainty_score":0.9997676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05249995004114355,"score_gpt":0.3869085237927591,"score_spread":0.3344085737516156,"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."}}