{"id":"W3209941363","doi":"10.1093/bib/bbab449","title":"A similarity-based deep learning approach for determining the frequencies of drug side effects","year":2021,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Natural Science Foundation of China; Scottish Funding Council","keywords":"Side effect (computer science); Computer science; Drug; Similarity (geometry); Machine learning; Side chain; Artificial intelligence; Far side of the Moon; Data mining; Medicine; Pharmacology; Chemistry","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":[0.0007843897,0.0008408873,0.001115246,0.001560286,0.000308299,0.0006173633,0.001483181,0.001162081,0.002597726],"category_scores_gemma":[0.002593988,0.0004082423,0.001080015,0.0009216149,0.0003463418,0.00112844,0.0009952674,0.001568238,0.0005809097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008060649,"about_ca_system_score_gemma":0.001674925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005869733,"about_ca_topic_score_gemma":0.008233438,"domain_scores_codex":[0.9993718,0.0001048132,0.00006700237,0.0001655378,0.0002079614,0.00008292054],"domain_scores_gemma":[0.9990903,0.0003482767,0.0001606449,0.00007503935,0.0002503999,0.00007531379],"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":[0.0004926584,0.0006984858,0.0152546,0.000349233,0.0003349034,0.000459663,0.00009747574,0.2851354,0.007725309,0.005155825,0.01159272,0.6727037],"study_design_scores_gemma":[0.00002099096,0.0001159068,0.001011062,0.00001643803,0.00003851011,0.0001199465,0.000007957764,0.9924254,0.001552525,0.003625856,0.001053313,0.00001200977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09637012,0.003153206,0.8902764,0.001205373,0.0001905103,0.0002533821,0.00145104,0.002447723,0.004652294],"genre_scores_gemma":[0.8051692,0.001415693,0.1797171,0.001258847,0.0002006375,0.0003091298,0.003264852,0.0001386132,0.008525975],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005869733,"threshold_uncertainty_score":0.01167119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01869175495575962,"score_gpt":0.267787777476734,"score_spread":0.2490960225209744,"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."}}