{"id":"W3165146808","doi":"10.1016/j.ailsci.2022.100036","title":"Understanding the performance of knowledge graph embeddings in drug discovery","year":2022,"lang":"en","type":"article","venue":"Artificial Intelligence in the Life Sciences","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Ranking (information retrieval); Identification (biology); Context (archaeology); Domain knowledge; Machine learning; Hyperparameter; Graph; Drug discovery; Knowledge graph; Embedding; Process (computing); Data science; Artificial intelligence; Data mining; Theoretical computer science; Bioinformatics","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":[0.003733705,0.0001414939,0.0001708763,0.0003467387,0.0008747517,0.0001550534,0.003950549,0.0000194293,0.000009535069],"category_scores_gemma":[0.0001242613,0.00008729938,0.00007511507,0.005748517,0.0009749414,0.001178799,0.0006566236,0.0004626712,0.000004890317],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006851977,"about_ca_system_score_gemma":0.0001268795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001115872,"about_ca_topic_score_gemma":0.0004270887,"domain_scores_codex":[0.9974962,0.0004287092,0.0005317043,0.000439749,0.0006425385,0.0004611003],"domain_scores_gemma":[0.9980692,0.001236604,0.0001956862,0.0004441248,0.00002172205,0.00003264945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001709881,0.0001143636,0.004484168,0.00000700413,0.000002681423,0.000005042963,0.01787755,0.3020123,0.0001863174,0.6704233,0.0001169614,0.004753282],"study_design_scores_gemma":[0.00002485829,0.0001952908,0.0008506808,0.00004114207,0.000002890542,0.00001206502,0.02531899,0.5643408,0.00230529,0.4066226,0.00007813484,0.0002072309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8731111,0.0007075226,0.1195001,0.00371843,0.001105062,0.0004165116,0.00000197333,0.0000377804,0.001401539],"genre_scores_gemma":[0.9988279,0.00008242961,0.0005462537,0.0004329401,0.00003914139,0.0000478261,2.39324e-7,0.000004273698,0.00001904729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2638006,"threshold_uncertainty_score":0.7341169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.11443593632942,"score_gpt":0.3198195361523598,"score_spread":0.2053835998229397,"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."}}