{"id":"W4391216324","doi":"10.1109/jbhi.2024.3358632","title":"Anti-Cancer Peptides Identification and Activity Type Classification With Protein Sequence Pre-Training","year":2024,"lang":"en","type":"article","venue":"IEEE Journal of Biomedical and Health Informatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Identification (biology); Sequence (biology); Cancer; Computer science; Artificial intelligence; Protein sequencing; Pattern recognition (psychology); Computational biology; Peptide sequence; Medicine; Biology; Gene; Internal medicine; Genetics","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":[0.0008094157,0.001267734,0.0009550929,0.001471831,0.0002617979,0.0006659165,0.000863083,0.001108733,0.001532315],"category_scores_gemma":[0.001949493,0.0003095047,0.0009562406,0.001102352,0.000322431,0.001210168,0.0006622691,0.001608839,0.001708346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003961318,"about_ca_system_score_gemma":0.0006792299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00160154,"about_ca_topic_score_gemma":0.002615006,"domain_scores_codex":[0.9995554,0.00007788822,0.00003502042,0.0001830775,0.00008929552,0.00005928628],"domain_scores_gemma":[0.9990076,0.0003471576,0.0001611745,0.000195732,0.0002192199,0.0000690953],"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":[0.001304256,0.001128671,0.05120281,0.0007997297,0.0002682937,0.000481656,0.0001161441,0.07915014,0.07444163,0.001444604,0.01806008,0.771602],"study_design_scores_gemma":[0.00006183638,0.0005145323,0.01734984,0.00006961555,0.0001120464,0.0005245051,0.00009319081,0.9285957,0.03764221,0.004530132,0.01045853,0.00004788761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6103323,0.009075633,0.3483999,0.001353718,0.0004377427,0.0003793457,0.009740589,0.0118085,0.008472286],"genre_scores_gemma":[0.7611204,0.003379748,0.2017836,0.0006728079,0.0002310778,0.0003245965,0.02689527,0.0002417749,0.005350709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.00160154,"threshold_uncertainty_score":0.005126119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05267022293871846,"score_gpt":0.3707696935830636,"score_spread":0.3180994706443451,"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."}}