{"id":"W4404620945","doi":"10.1093/bfgp/elae046","title":"SAMP: Identifying antimicrobial peptides by an ensemble learning model based on proportionalized split amino acid composition","year":2024,"lang":"en","type":"article","venue":"Briefings in Functional Genomics","topic":"Antimicrobial Peptides and Activities","field":"Immunology and Microbiology","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Institute of General Medical Sciences; National Cancer Institute; National Institute on Alcohol Abuse and Alcoholism; National Institutes of Health; American Cancer Society","keywords":"Biology; Antimicrobial peptides; Benchmarking; Artificial intelligence; Computational biology; Scalability; Python (programming language); Ensemble learning; Pseudo amino acid composition; Computer science; Matthews correlation coefficient; Machine learning; Peptide; Support vector machine; Biochemistry","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003404817,0.000293853,0.0002990602,0.0002512456,0.000409221,0.0001904038,0.0001408449,0.0002642171,0.0002293135],"category_scores_gemma":[0.00002667933,0.0003159413,0.0001597721,0.0001565614,0.0002005925,0.0003629758,0.00006056841,0.0006341221,0.0002331986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002620441,"about_ca_system_score_gemma":0.0002088632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002001091,"about_ca_topic_score_gemma":0.00001779701,"domain_scores_codex":[0.9983267,0.0001098397,0.0004380728,0.0006202664,0.00008696603,0.000418202],"domain_scores_gemma":[0.9994982,0.0001196302,0.0001225614,0.0001607839,0.00006601399,0.00003275772],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004915325,0.000202057,0.0001950503,0.00007327367,0.00005639372,0.000008914411,0.0001832162,0.08415252,0.8959212,0.002558967,0.01432926,0.001827573],"study_design_scores_gemma":[0.003529863,0.0004994007,0.002095208,0.0007724524,0.0001528244,0.0002526222,0.000257731,0.1660135,0.7828812,0.002462842,0.03957811,0.001504245],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9256179,0.0005099705,0.07060593,0.0008905485,0.0007694234,0.0003031634,0.0001692983,0.0002704496,0.0008632903],"genre_scores_gemma":[0.9903886,0.00005560787,0.002279758,0.001637972,0.0001069275,0.00002471542,0.002490887,0.00005954791,0.002956016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1130401,"threshold_uncertainty_score":0.9999292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02234263277806389,"score_gpt":0.2417353928309051,"score_spread":0.2193927600528412,"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."}}