{"id":"W4406260133","doi":"10.1109/bibm62325.2024.10822148","title":"HCCL: Hierarchical Channels and Contrastive Learning for Drug-Gene Multi-Relation Prediction","year":2024,"lang":"en","type":"article","venue":"","topic":"Computational Drug Discovery Methods","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Saskatchewan","funders":"National Natural Science Foundation of China; Ministry of Education","keywords":"Relation (database); Computer science; Artificial intelligence; Natural language processing; Machine learning; Data mining","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":[0.00157318,0.0009449359,0.001018245,0.001247888,0.0004669508,0.0008373357,0.001884732,0.001157185,0.001998688],"category_scores_gemma":[0.003910039,0.0003696589,0.000785392,0.001192871,0.001044032,0.001652349,0.001474109,0.002037383,0.0005096068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001351552,"about_ca_system_score_gemma":0.00178063,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00975568,"about_ca_topic_score_gemma":0.009923203,"domain_scores_codex":[0.9993591,0.000198251,0.00002382308,0.0001695527,0.0001522138,0.00009706684],"domain_scores_gemma":[0.9982318,0.001104113,0.0001534642,0.0001946192,0.0002073003,0.000108717],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003750483,0.0004611031,0.004908005,0.0001500464,0.0001469069,0.0002120454,0.0001006909,0.6211598,0.009321101,0.02385645,0.008536158,0.3307726],"study_design_scores_gemma":[0.000007658361,0.00002094809,0.0001258943,0.000002123867,0.000006035213,0.000008115011,0.000002980152,0.9943144,0.0009254708,0.004317908,0.0002630958,0.000005321904],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04021913,0.0008270681,0.9534047,0.0005702036,0.00008904047,0.00009640984,0.0003554379,0.002485463,0.00195264],"genre_scores_gemma":[0.8086403,0.000496109,0.1841919,0.0008198863,0.0001834639,0.0002300629,0.001170544,0.000191711,0.004076093],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00975568,"threshold_uncertainty_score":0.0193978,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02545681909976938,"score_gpt":0.3071283551646614,"score_spread":0.281671536064892,"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."}}