{"id":"W3188405687","doi":"10.1016/j.ymeth.2021.08.001","title":"NetAUC: A network-based multi-biomarker identification method by AUC optimization","year":2021,"lang":"en","type":"article","venue":"Methods","topic":"Bioinformatics and Genomic Networks","field":"Biochemistry, Genetics and Molecular Biology","cited_by":40,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Saskatchewan","funders":"Science and Technology Program of Gansu Province; Training Program for Excellent Young Innovators of Changsha; National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Interpretability; Receiver operating characteristic; Biomarker; Identification (biology); Computer science; Classifier (UML); Area under curve; Binary classification; Biological network; Computational biology; Machine learning; Biomarker discovery; Artificial intelligence; Bioinformatics; Support vector machine; Biology; Proteomics; Gene","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":[0.003323892,0.001985345,0.001950141,0.002546025,0.0007823678,0.001644451,0.001745976,0.001555612,0.003066128],"category_scores_gemma":[0.008499931,0.0005961495,0.001479366,0.002001708,0.0006619071,0.00140013,0.001768071,0.002093436,0.001218282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001063706,"about_ca_system_score_gemma":0.001909401,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005729681,"about_ca_topic_score_gemma":0.005240651,"domain_scores_codex":[0.9984183,0.0007418641,0.00006554902,0.0002972616,0.0003894242,0.00008758214],"domain_scores_gemma":[0.9976116,0.001242947,0.0001703946,0.0002174732,0.0006446616,0.0001127756],"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":[0.0006620766,0.0002703625,0.003422948,0.0003533519,0.0005536621,0.0001786923,0.00007400572,0.4571759,0.007097097,0.01157762,0.01837507,0.5002591],"study_design_scores_gemma":[0.00001886476,0.00004189538,0.0002578326,0.0000124249,0.00002868784,0.00005120617,0.000005692744,0.9919196,0.001403683,0.004527695,0.001719198,0.00001308806],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005333317,0.0005688622,0.9895484,0.0002406912,0.00009701218,0.00007447231,0.0002826671,0.002856795,0.0009977308],"genre_scores_gemma":[0.1525109,0.0004505384,0.8397583,0.0003408263,0.0001545187,0.0004266429,0.001332726,0.001144185,0.003881298],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005729681,"threshold_uncertainty_score":0.01757866,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02272812069918315,"score_gpt":0.3529032148169889,"score_spread":0.3301750941178058,"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."}}