{"id":"W4402134398","doi":"10.21203/rs.3.rs-4864640/v1","title":"SDV-HGNN: similarity-based dual view heterogeneous graph neural network method for drug adverse side effect prediction","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Computer science; Context (archaeology); Similarity (geometry); Drug; Artificial neural network; Dual (grammatical number); Artificial intelligence; Side effect (computer science); Graph; Machine learning; Benchmark (surveying); 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005524847,0.0007127326,0.0009337052,0.001567278,0.0004107765,0.0005378228,0.001578303,0.001001225,0.002653131],"category_scores_gemma":[0.00176927,0.0002992811,0.0008349164,0.001269763,0.0002610228,0.0008216219,0.0009582092,0.0009542206,0.0006967769],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005768899,"about_ca_system_score_gemma":0.0008967022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01392308,"about_ca_topic_score_gemma":0.01957713,"domain_scores_codex":[0.9996276,0.00007880812,0.00001990348,0.0001309951,0.00009968532,0.00004289065],"domain_scores_gemma":[0.9995975,0.0001225854,0.00003558478,0.00008482526,0.000130041,0.00002952505],"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":[0.0003484123,0.0003173907,0.006205309,0.0001779816,0.0003630828,0.0001906336,0.00005822592,0.2658025,0.005838375,0.00502217,0.01979035,0.6958855],"study_design_scores_gemma":[0.00001209257,0.00002802496,0.0005405655,0.000006314796,0.00002519154,0.00003146409,0.000008859514,0.9947508,0.000845696,0.003118495,0.0006261512,0.000006223669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.07852285,0.001498865,0.9072706,0.0005232979,0.0002837448,0.0001624048,0.002541899,0.005512028,0.003684339],"genre_scores_gemma":[0.6997644,0.000538552,0.2869691,0.0003463012,0.0001575345,0.0001727385,0.005202203,0.0003296067,0.006519609],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01392308,"threshold_uncertainty_score":0.02768409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05787062334335553,"score_gpt":0.4255454252844124,"score_spread":0.3676748019410568,"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."}}