{"id":"W4415351327","doi":"10.1021/acs.jcim.5c01996","title":"MFGNN-DSA: A Model for Predicting Drug–Side Effect Associations via Multifeature Fusion and Graph Neural Networks","year":2025,"lang":"en","type":"article","venue":"Journal of Chemical Information and Modeling","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Hebei Provincial Key Research Projects; National Natural Science Foundation of China","keywords":"Feature (linguistics); Graph; Source code; Artificial neural network; Feature vector; Mechanism (biology); Pattern recognition (psychology)","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":[0.0008806867,0.0001027519,0.0001936324,0.0001753964,0.000127957,0.0001904251,0.0001530804,0.0000793017,9.784632e-8],"category_scores_gemma":[0.0003981268,0.00008682731,0.00009249617,0.0001754246,0.00001390174,0.001648956,0.000122613,0.0002632896,3.983897e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005175956,"about_ca_system_score_gemma":0.00004624127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003120635,"about_ca_topic_score_gemma":5.172965e-7,"domain_scores_codex":[0.9990227,0.00004282704,0.0005225496,0.00008591107,0.0001911993,0.0001348119],"domain_scores_gemma":[0.998677,0.0005990711,0.0002823512,0.00006922927,0.0002964596,0.00007593571],"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":[0.00003330639,0.000007555068,0.00007528564,0.00003426183,0.00001971015,1.234561e-7,0.0006371873,0.9490944,0.0004209823,0.0007555235,0.00007759298,0.04884413],"study_design_scores_gemma":[0.0007641756,0.00001755258,0.00003232496,0.00006114329,0.00002627673,0.0000142501,0.00001959842,0.9920574,0.0003601749,0.006562314,0.00001128922,0.00007352146],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2431819,0.0001473829,0.7557311,0.0006417134,0.0001376204,0.0001140924,0.000002371451,0.00001757907,0.00002625742],"genre_scores_gemma":[0.9001881,0.00002164996,0.09921928,0.000501166,0.00005103606,0.000005072189,0.000007922024,0.000002673305,0.000003118829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6570062,"threshold_uncertainty_score":0.3540715,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01393092473649284,"score_gpt":0.2956534932154907,"score_spread":0.2817225684789979,"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."}}