{"id":"W4200227922","doi":"10.1093/bib/bbab511","title":"Predicting drug–drug interactions by graph convolutional network with multi-kernel","year":2021,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Graph; Drug; Kernel (algebra); Drug-drug interaction; Theoretical computer science; Medicine; Mathematics; Pharmacology","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":[0.0005697515,0.0001990796,0.0002207084,0.0001192021,0.0002179245,0.0002923847,0.0004817662,0.00003140046,0.00001472269],"category_scores_gemma":[0.0002207708,0.00019739,0.00007476898,0.001054305,0.00009086324,0.001450848,0.0003809448,0.0003522682,0.00002163526],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001191691,"about_ca_system_score_gemma":0.0003325125,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001646653,"about_ca_topic_score_gemma":0.0002278681,"domain_scores_codex":[0.9981428,0.0001145473,0.0006016013,0.0002766965,0.0004626004,0.0004016915],"domain_scores_gemma":[0.9982278,0.0008304621,0.0002652396,0.000349416,0.0002218613,0.0001052752],"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":[0.00004803535,0.0006797332,0.04661186,0.0002761697,0.0002323197,0.0000873197,0.01346381,0.7170237,0.0000624266,0.0893691,0.1004582,0.03168744],"study_design_scores_gemma":[0.0006760669,0.000009295599,0.007126966,0.0001889627,0.000008185668,0.0001578236,0.0002585443,0.9804402,0.0001654821,0.002433856,0.008269221,0.0002654176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02567017,0.0002286177,0.9697857,0.002028508,0.0004220134,0.0001581666,0.00002458993,0.0001532205,0.001529048],"genre_scores_gemma":[0.06804289,0.00003232644,0.9284021,0.002769585,0.00007019157,0.00002930683,0.00008462116,0.00001714441,0.000551813],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2634165,"threshold_uncertainty_score":0.804933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01413073872996588,"score_gpt":0.2631868213987384,"score_spread":0.2490560826687725,"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."}}