{"id":"W4400985439","doi":"10.54254/2755-2721/79/20241329","title":"Predicting drug-drug interactions using heterogeneous graph neural networks: HGNN-DDI","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Graph; Drug; Artificial neural network; Machine learning; Similarity (geometry); Artificial intelligence; Data mining; Theoretical computer science; Medicine; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002248123,0.0002218265,0.0001689388,0.0002639816,0.0001694819,0.0004657512,0.000252028,0.00002302622,0.000004362068],"category_scores_gemma":[0.00001391627,0.0002395658,0.00008414022,0.000572884,0.0000261346,0.0004664676,0.0002392375,0.000267811,0.000004755224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006102084,"about_ca_system_score_gemma":0.00004418209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001910924,"about_ca_topic_score_gemma":0.000002070236,"domain_scores_codex":[0.998633,0.00003163034,0.0003035119,0.0004807778,0.0002727356,0.0002783771],"domain_scores_gemma":[0.9987401,0.0009177413,0.00004262068,0.0001424981,0.0000444563,0.000112608],"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":[0.00000219558,0.00001072993,0.00003205793,0.00003580493,0.00004734666,0.00001689535,0.0003539646,0.9382751,0.0001139589,0.04992036,0.00002267744,0.01116888],"study_design_scores_gemma":[0.0001070187,0.000004433949,0.0005074707,0.0000566561,0.00001430757,0.0001965459,0.00001711662,0.9907551,0.00004745677,0.007864376,0.0002007748,0.0002287294],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1822497,0.0006998233,0.8153957,0.0001270578,0.0008545726,0.0001191407,0.000004261342,0.0004508354,0.00009885184],"genre_scores_gemma":[0.8977616,0.000004937551,0.1017919,0.00009631189,0.0002722491,0.0000211372,0.00001575027,0.00002632995,0.000009774554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7155119,"threshold_uncertainty_score":0.976921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01130945940185478,"score_gpt":0.2515757607468486,"score_spread":0.2402663013449938,"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."}}