{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000916341,0.00009616057,0.0001630506,0.00009569889,0.0000909556,0.00008794288,0.00008035522,0.00009304813,0.000002899601],"category_scores_gemma":[0.0000572449,0.00006583423,0.00001944424,0.0001272724,0.0001664482,0.00004817433,0.00002144657,0.0002526047,0.000001221243],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002606355,"about_ca_system_score_gemma":0.0004226436,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007793492,"about_ca_topic_score_gemma":0.000003303706,"domain_scores_codex":[0.9989501,0.00002897071,0.0005625432,0.00006539279,0.0002438354,0.0001491488],"domain_scores_gemma":[0.999172,0.00001424521,0.0004547536,0.00008579305,0.0001113818,0.0001618727],"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":[0.0002549311,0.0001030323,0.003444108,0.006646866,0.0002462011,0.00000534384,0.009534838,0.0001686577,0.3533805,0.0003946969,0.00416123,0.6216596],"study_design_scores_gemma":[0.004039874,0.01337145,0.1464702,0.008111225,0.000263723,0.003218827,0.006139177,0.4655464,0.06494892,0.0005720468,0.285648,0.001670245],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9655272,0.0006017742,0.03107722,0.002403273,0.0001722354,0.0001576085,0.00001166319,0.00001034578,0.00003871212],"genre_scores_gemma":[0.9909862,0.001876892,0.006596765,0.0002298634,0.0002028864,0.000003926549,0.0000140298,0.000007705545,0.00008168261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6199893,"threshold_uncertainty_score":0.2684642,"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."}}