{"id":"W4404219622","doi":"10.1093/bib/bbae575","title":"A multichannel graph neural network based on multisimilarity modality hypergraph contrastive learning for predicting unknown types of cancer biomarkers","year":2024,"lang":"en","type":"article","venue":"Briefings in Bioinformatics","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Science North","funders":"National Natural Science Foundation of China","keywords":"Hypergraph; Modality (human–computer interaction); Artificial neural network; Computer science; Graph; Artificial intelligence; Pattern recognition (psychology); Natural language processing; Mathematics; Theoretical computer science","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":[0.0005826147,0.0007072924,0.0006848329,0.0008719168,0.0002497494,0.0005275976,0.001082615,0.001034029,0.001054777],"category_scores_gemma":[0.001773825,0.000312699,0.0007296399,0.0006504835,0.0005416106,0.001030365,0.0006348523,0.001052048,0.000230378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008815255,"about_ca_system_score_gemma":0.0006115999,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008108141,"about_ca_topic_score_gemma":0.00907384,"domain_scores_codex":[0.9997023,0.00006966411,0.00001238705,0.0001190893,0.00005751821,0.00003899296],"domain_scores_gemma":[0.9995509,0.0002108016,0.00005251132,0.00003497087,0.0001240104,0.00002678511],"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":[0.0002028287,0.0001364288,0.004667222,0.000107425,0.0001434764,0.0001757547,0.00008649147,0.7532462,0.01134731,0.008021574,0.002764792,0.2191004],"study_design_scores_gemma":[0.000002467772,0.00001428272,0.0001890424,0.000002838195,0.00000767764,0.00001157645,0.000002902734,0.9977267,0.0005123223,0.001391218,0.0001350363,0.000004000204],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08879279,0.001165025,0.9060397,0.0006053931,0.0001086599,0.00006761452,0.0002951926,0.0008115472,0.002114145],"genre_scores_gemma":[0.8575471,0.0006768901,0.1354901,0.0005544358,0.00009127269,0.0001520446,0.0007649891,0.00005799946,0.004665004],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008108141,"threshold_uncertainty_score":0.01612186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01026486699106989,"score_gpt":0.2561441162420022,"score_spread":0.2458792492509323,"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."}}