{"id":"W4395694330","doi":"10.1101/2024.04.25.590553","title":"SAMP: Identifying Antimicrobial Peptides by an Ensemble Learning Model Based on Proportionalized Split Amino Acid Composition","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Antimicrobial Peptides and Activities","field":"Immunology and Microbiology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Office of Experimental Program to Stimulate Competitive Research; National Institute of General Medical Sciences; National Cancer Institute; National Institutes of Health","keywords":"Antimicrobial peptides; Composition (language); Ensemble learning; Antimicrobial; Amino acid; Pseudo amino acid composition; Computational biology; Chemistry; Artificial intelligence; Biochemistry; Peptide; Computer science; Biology; Microbiology; Philosophy; Linguistics","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":[0.00105362,0.001113096,0.001558992,0.000570285,0.0003939778,0.0007480276,0.001776263,0.001144218,0.001314815],"category_scores_gemma":[0.001667647,0.0005697582,0.00122891,0.0005761467,0.0004563131,0.001080295,0.0009088442,0.001629068,0.0005851336],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004087897,"about_ca_system_score_gemma":0.001092387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006678955,"about_ca_topic_score_gemma":0.004465977,"domain_scores_codex":[0.9995387,0.0001527557,0.00002259561,0.0001149109,0.000112574,0.00005842869],"domain_scores_gemma":[0.999401,0.0003091433,0.00005833379,0.00004112954,0.0001458339,0.00004452349],"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":[0.0001347691,0.00009902865,0.00201787,0.00005191093,0.0001585104,0.00009765638,0.0000331337,0.9114721,0.001997756,0.001505711,0.002262486,0.08016899],"study_design_scores_gemma":[0.000002805245,0.00001359561,0.00004849107,0.000001371907,0.000004643144,0.000006748612,0.00000110911,0.999285,0.0001463857,0.0004136009,0.00007411296,0.000002122844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09163363,0.001631104,0.9007317,0.0005966797,0.000141426,0.0001025489,0.0003559385,0.002471085,0.002335831],"genre_scores_gemma":[0.8090519,0.001064497,0.1823234,0.0007503547,0.0002427724,0.0003059784,0.001473497,0.0001723472,0.004615218],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006678955,"threshold_uncertainty_score":0.01328021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.016445366333351,"score_gpt":0.2352226063009762,"score_spread":0.2187772399676252,"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."}}