{"id":"W2956168392","doi":"10.1016/j.cmpb.2019.07.009","title":"AMC-Net: Asymmetric and multi-scale convolutional neural network for multi-label HPA classification","year":2019,"lang":"en","type":"article","venue":"Computer Methods and Programs in Biomedicine","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University; University of Ontario Institute of Technology","funders":"Knut och Alice Wallenbergs Stiftelse; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Human Protein Atlas; Pattern recognition (psychology); Deep learning; Multi-label classification; Artificial neural network; Feature extraction; Binary classification; Machine learning; Robustness (evolution); Support vector machine","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":[0.001076932,0.0001748289,0.0002469886,0.000105926,0.0000643349,0.00003471564,0.0001244692,0.000173058,0.000002116],"category_scores_gemma":[0.00005383907,0.0001449519,0.00003466726,0.0002572333,0.0001686806,0.000007357491,0.0001373001,0.0001455439,0.00000107952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001055749,"about_ca_system_score_gemma":0.00001716761,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001275893,"about_ca_topic_score_gemma":0.00000722497,"domain_scores_codex":[0.9988052,0.0001503865,0.0003350574,0.0003424225,0.00008780429,0.0002791692],"domain_scores_gemma":[0.9993936,0.00009338692,0.0001344348,0.0002085083,0.00007379833,0.00009630334],"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":[0.00005811136,0.0001058339,0.1045408,0.000146932,0.00002997481,3.085723e-7,0.0001043205,0.00003700453,0.005592577,0.000114867,0.0002502325,0.889019],"study_design_scores_gemma":[0.002940389,0.0008909812,0.08031377,0.00004247141,0.00001640351,0.00002278709,0.00003492122,0.8938326,0.000098048,0.0000423299,0.02158554,0.000179776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1474199,0.002286205,0.8486784,0.0002484829,0.0005368326,0.0007723593,0.000007309659,0.00002134489,0.00002913373],"genre_scores_gemma":[0.03508989,0.0001496804,0.9634507,0.0003881734,0.0003616474,0.00004474663,0.0003579852,0.0000173951,0.0001397571],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8937955,"threshold_uncertainty_score":0.5910965,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06901865286101067,"score_gpt":0.3827700430446068,"score_spread":0.3137513901835962,"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."}}