{"id":"W4386258894","doi":"10.1016/j.csbj.2023.08.025","title":"MetaPep: A core peptide database for faster human gut metaproteomics database searches","year":2023,"lang":"en","type":"article","venue":"Computational and Structural Biotechnology Journal","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Metaproteomics; Database search engine; Database; Sequence database; Computer science; Computational biology; Metagenomics; Biology; Search engine; Information retrieval","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002022674,0.0002059558,0.000238619,0.0002077798,0.0007784719,0.00007661912,0.0003453713,0.0001917407,0.00008801292],"category_scores_gemma":[0.0000808747,0.0001750584,0.00009577039,0.0002211675,0.0003050055,0.0001848121,0.000266008,0.000613298,0.000006364111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004576774,"about_ca_system_score_gemma":0.00005176098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004270907,"about_ca_topic_score_gemma":0.00000294316,"domain_scores_codex":[0.998766,0.00001043055,0.0003608302,0.000358416,0.000168965,0.000335346],"domain_scores_gemma":[0.999184,0.0001295054,0.0001978476,0.0002364059,0.0001372251,0.0001150357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007055038,0.0000171506,0.0004046818,0.0001196312,0.0001579616,0.00002832411,0.00006169169,0.0008920485,0.8825641,0.09991793,0.001972328,0.01379363],"study_design_scores_gemma":[0.001714213,0.0001162839,0.0008808884,0.00009791784,0.0001114914,0.001440368,0.0003891307,0.07754941,0.1510351,0.7560533,0.009970424,0.000641491],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8636932,0.0001549657,0.131159,0.003314976,0.00003861133,0.0002845873,0.0009566649,0.0003342156,0.00006372879],"genre_scores_gemma":[0.6413625,0.000156953,0.3560876,0.0001527631,0.0001965556,0.0001148067,0.001482051,0.00003488653,0.0004119004],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7315289,"threshold_uncertainty_score":0.7138676,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05752189728448905,"score_gpt":0.3402681764971878,"score_spread":0.2827462792126987,"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."}}