{"id":"W4379208001","doi":"10.1101/2023.05.30.542978","title":"Deep learning from harmonized peptide libraries enables retention time prediction of diverse post translational modifications","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"National Institutes of Health","keywords":"Workflow; Computer science; Deep learning; Proteome; Peptide; Fragmentation (computing); Artificial intelligence; Proteomics; Computational biology; Machine learning; Data mining; Bioinformatics; Chemistry; Database; Biology; 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":[0.0001826461,0.0003701532,0.0004059403,0.0001808436,0.0003115278,0.0001247557,0.000458337,0.0005403957,0.0003362088],"category_scores_gemma":[0.0001699431,0.0004529964,0.0002112227,0.0003037525,0.000153824,0.0002872159,0.0002646435,0.0007656704,0.00006638295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001181638,"about_ca_system_score_gemma":0.0002309286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001237248,"about_ca_topic_score_gemma":0.000001582925,"domain_scores_codex":[0.9978637,0.00004962108,0.0006671955,0.0007996004,0.0003356471,0.000284262],"domain_scores_gemma":[0.99774,0.0001386799,0.000663501,0.0008439099,0.0004888207,0.0001250781],"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":[0.00004097363,0.00008087676,0.002197676,0.0001927625,0.0001375073,0.000002323359,0.00002955262,0.002431831,0.9936422,0.001144706,0.00009411986,0.0000055404],"study_design_scores_gemma":[0.0005788784,0.00002061385,0.02175712,0.0005661992,0.0002999873,9.897774e-9,0.00002633855,0.03747644,0.936034,0.0004880729,0.0021125,0.0006398371],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7817813,0.0006312533,0.2072478,0.0004640569,0.0002004073,0.0009354752,0.005950751,0.002706437,0.00008258994],"genre_scores_gemma":[0.9165576,0.0004503308,0.08167086,0.00001229284,0.0002844853,0.0006536785,0.000115842,0.0001473601,0.0001075508],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1347763,"threshold_uncertainty_score":0.9997922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02708163328435503,"score_gpt":0.2199839869494261,"score_spread":0.1929023536650711,"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."}}