{"id":"W3205082786","doi":"10.1093/bib/bbab421","title":"MDF-SA-DDI: predicting drug–drug interaction events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism","year":2021,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":183,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Shanghai Jiao Tong University; Science and Technology Commission of Shanghai Municipality; National Natural Science Foundation of China","keywords":"Computer science; Feature learning; Drug; Feature (linguistics); Artificial intelligence; Encoder; Fusion; Transformer; Mechanism (biology); Fusion mechanism; Pattern recognition (psychology); Machine learning; Medicine; Pharmacology; Engineering","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":[0.001438231,0.0004419107,0.0003989957,0.000462961,0.0004427231,0.0003882525,0.0005278283,0.0001611807,0.00001461511],"category_scores_gemma":[0.000369433,0.000447255,0.0001816921,0.0009021287,0.00003808516,0.00168425,0.0003247819,0.0007107466,0.00002273509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002752251,"about_ca_system_score_gemma":0.0001995642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001533498,"about_ca_topic_score_gemma":0.0001098955,"domain_scores_codex":[0.9967086,0.0003569376,0.0009101112,0.0005996554,0.0009066144,0.000518086],"domain_scores_gemma":[0.9977811,0.0007576636,0.0004852287,0.0005182343,0.0002698574,0.0001879186],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003250687,0.003680197,0.009058684,0.002632203,0.0002496548,0.0001004808,0.1214093,0.3391659,0.005575537,0.003571684,0.00308765,0.5111436],"study_design_scores_gemma":[0.002241638,0.00003553818,0.006691039,0.0006442728,0.00002894609,0.00007907052,0.001099698,0.9828401,0.002772304,0.0002465862,0.002865853,0.000454954],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2010643,0.00004688016,0.7946356,0.002717481,0.0005910759,0.0004846264,0.00001466881,0.0002835882,0.0001618336],"genre_scores_gemma":[0.2782252,0.0000893032,0.717593,0.003126359,0.00007725265,0.0000380577,0.0001287556,0.00005048704,0.0006715989],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6436742,"threshold_uncertainty_score":0.9997979,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01347361446730321,"score_gpt":0.2656193314134141,"score_spread":0.2521457169461109,"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."}}