{"id":"W4405762935","doi":"10.1101/2024.12.18.629045","title":"Zero-shot retention time prediction for unseen post-translational modifications with molecular structure encodings","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Manitoba","funders":"Universiteit Gent; Fonds Wetenschappelijk Onderzoek; Vlaamse regering; Universiteit Antwerpen; Vlaams Supercomputer Centrum","keywords":"Encoder; Computer science; Retention time; Transformer; Peptide; Posttranslational modification; Workflow; Artificial intelligence; Computational biology; Machine learning; Chemistry; Chromatography; Biology; Biochemistry; Engineering","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":[0.001064859,0.0007705347,0.0004937412,0.0005856499,0.0001501569,0.0006934059,0.0008728835,0.000728938,0.0004819478],"category_scores_gemma":[0.002017379,0.0002192599,0.0004957297,0.0004025933,0.0003223802,0.0008732504,0.00050326,0.0009386757,0.0004513158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000538018,"about_ca_system_score_gemma":0.0007661383,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002608104,"about_ca_topic_score_gemma":0.002949883,"domain_scores_codex":[0.9997229,0.00003956652,0.00001289014,0.0001061096,0.00008358112,0.00003496935],"domain_scores_gemma":[0.9989433,0.0004900611,0.0001837979,0.0001449246,0.0001680573,0.00006999232],"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":[0.00253509,0.0005496971,0.02602847,0.0003456725,0.0002574949,0.0006749033,0.0001172183,0.5208338,0.1916732,0.003692122,0.00544427,0.247848],"study_design_scores_gemma":[0.000008743816,0.00006266023,0.0007829176,0.000004288625,0.00001340636,0.00005502785,0.000006503556,0.974238,0.023492,0.0009721598,0.0003542375,0.00001010089],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4998532,0.001311534,0.4912441,0.0002791795,0.0001024287,0.00003882878,0.001395376,0.00460172,0.001173557],"genre_scores_gemma":[0.9086602,0.0003815924,0.08642692,0.0001250188,0.00003320773,0.00002504464,0.002537777,0.0001615776,0.001648627],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002608104,"threshold_uncertainty_score":0.005631566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01086974375438825,"score_gpt":0.2274872570336091,"score_spread":0.2166175132792209,"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."}}