{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008748568,0.001606459,0.0009643794,0.002489714,0.0005348058,0.002687914,0.001179424,0.002276719,0.001366622],"category_scores_gemma":[0.03954928,0.0005321159,0.001031736,0.001831832,0.001208138,0.007482553,0.001772348,0.002387541,0.0008295497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002018084,"about_ca_system_score_gemma":0.001013472,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008467518,"about_ca_topic_score_gemma":0.008377296,"domain_scores_codex":[0.9972145,0.001598753,0.000180092,0.0005010577,0.0003364719,0.0001692295],"domain_scores_gemma":[0.9734704,0.02181514,0.001093308,0.002142139,0.001145829,0.0003331694],"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":[0.0005499626,0.0003167731,0.01524478,0.0003278485,0.0002206491,0.00007366878,0.0001785847,0.873693,0.001189725,0.00495565,0.00392556,0.09932374],"study_design_scores_gemma":[0.00001672109,0.0001915729,0.001392763,0.00004066433,0.00003425942,0.00004025107,0.00007782665,0.9868085,0.001204328,0.009465472,0.000708992,0.00001864816],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8564304,0.008681369,0.1101557,0.006633737,0.00039639,0.0002749928,0.003057024,0.002757592,0.0116128],"genre_scores_gemma":[0.9645871,0.001401169,0.02822725,0.0003307769,0.00007793098,0.00005521478,0.003985052,0.0001363013,0.001199107],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008748568,"threshold_uncertainty_score":0.04626739,"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."}}