{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001100506,0.001112572,0.001549328,0.0005763554,0.0004025355,0.000748957,0.001765282,0.001140366,0.001280716],"category_scores_gemma":[0.001776207,0.0005661478,0.001225487,0.0005864064,0.0004681308,0.001062273,0.0009368623,0.001602901,0.0005787655],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003964608,"about_ca_system_score_gemma":0.001064867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006492734,"about_ca_topic_score_gemma":0.004326592,"domain_scores_codex":[0.9995176,0.0001646287,0.00002325554,0.0001193302,0.0001161523,0.00005911714],"domain_scores_gemma":[0.9993659,0.0003296484,0.00006259909,0.00004460633,0.000151703,0.00004564211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000128211,0.00009775721,0.00211479,0.00005193163,0.0001580776,0.00009770296,0.00003420084,0.9134205,0.001971097,0.00159678,0.00229746,0.07803153],"study_design_scores_gemma":[0.000002754997,0.0000137735,0.00004944004,0.000001377154,0.000004629124,0.000006644024,0.00000112239,0.9992729,0.0001404724,0.0004305627,0.00007424357,0.000002108002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.09112372,0.001552238,0.9015218,0.0005964491,0.0001346554,0.00009911009,0.0003460836,0.002364502,0.002261509],"genre_scores_gemma":[0.8103805,0.001040037,0.1812927,0.000723923,0.0002400171,0.0003040602,0.001466141,0.0001704717,0.004382089],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006492734,"threshold_uncertainty_score":0.01290989,"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."}}