{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002131238,0.001662187,0.001004057,0.001495715,0.0004496368,0.001567433,0.001387603,0.001063848,0.001870304],"category_scores_gemma":[0.003997124,0.0007468474,0.001114112,0.001459256,0.0005069833,0.002032038,0.001654788,0.001992424,0.001097727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009405252,"about_ca_system_score_gemma":0.001286857,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00162617,"about_ca_topic_score_gemma":0.003689292,"domain_scores_codex":[0.9991824,0.000122793,0.00004783898,0.000363557,0.0002192647,0.00006409346],"domain_scores_gemma":[0.9987067,0.0005809533,0.0001849566,0.00027914,0.0001797665,0.00006837007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001341196,0.0006800013,0.02132903,0.0009008,0.001014536,0.0004715016,0.0001851257,0.2837552,0.159794,0.00679566,0.02023355,0.5034994],"study_design_scores_gemma":[0.00006368951,0.0001771625,0.00257583,0.00002494738,0.00007499615,0.0001184701,0.00002654764,0.9122764,0.06666904,0.01229554,0.005644726,0.00005257721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2380305,0.001890592,0.7131485,0.0005515715,0.0001587983,0.000161077,0.009192013,0.03252977,0.004337184],"genre_scores_gemma":[0.4700969,0.001025856,0.4990737,0.0006644865,0.00007268468,0.0003920768,0.0235302,0.001530559,0.003613598],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002131238,"threshold_uncertainty_score":0.01127118,"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."}}