{"id":"W4393895133","doi":"10.5281/zenodo.8101702","title":"MetaPep: A core peptide database for faster human gut metaproteomics database searches","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Metaproteomics; Database; Computer science; Core (optical fiber); Computational biology; Chemistry; Biology; Proteomics; 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","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001788624,0.0004666269,0.0004089332,0.0003836107,0.001949745,0.0007487932,0.002433178,0.0003096581,0.001585603],"category_scores_gemma":[0.002819152,0.0004829761,0.0002031509,0.000376236,0.0002855838,0.00003729147,0.004674033,0.0007739846,0.006692948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000889618,"about_ca_system_score_gemma":0.00002332439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000831177,"about_ca_topic_score_gemma":0.00001240802,"domain_scores_codex":[0.9968632,0.0003575392,0.0006029779,0.0008860303,0.000575857,0.0007144334],"domain_scores_gemma":[0.9966671,0.00004642643,0.0003906895,0.001940613,0.0006625179,0.0002926854],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000120146,0.00009979877,4.15987e-7,0.0007957203,0.0002613673,0.00001168241,0.00005532848,0.00003980923,0.02024873,0.000118957,0.9771151,0.001132938],"study_design_scores_gemma":[0.0007845562,0.0005108523,0.00001226755,0.0000894363,0.0001420653,0.00007140668,0.0001168203,0.0003782219,0.000904933,0.00002378908,0.9964573,0.0005083473],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0005786606,0.0000790343,0.003305978,0.0001645649,0.0001713171,0.001460713,0.9923741,0.0002788639,0.00158683],"genre_scores_gemma":[0.0001032652,0.0002910992,0.002587655,0.000269835,0.0005558806,0.00000125861,0.9915641,0.001745826,0.002881059],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0193438,"threshold_uncertainty_score":0.9997622,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06709769633482267,"score_gpt":0.3102441220615064,"score_spread":0.2431464257266838,"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."}}