{"id":"W2947763854","doi":"10.1038/s41592-019-0426-7","title":"Prosit: proteome-wide prediction of peptide tandem mass spectra by deep learning","year":2019,"lang":"en","type":"article","venue":"Nature Methods","topic":"Advanced Proteomics Techniques and Applications","field":"Chemistry","cited_by":979,"is_retracted":false,"has_abstract":false,"ca_institutions":"IONICS Mass Spectrometry (Canada)","funders":"Bundesministerium für Bildung und Forschung; Agence Nationale de la Recherche; Nvidia","keywords":"Tandem mass spectrometry; Database search engine; Proteome; Computer science; Bottom-up proteomics; Proteomics; Computational biology; Mass spectrometry; Peptide; Deep learning; Artificial intelligence; Chemistry; Chromatography; Search engine; Protein mass spectrometry; Biology; Biochemistry; Information retrieval","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":[0.001024178,0.002204684,0.0011712,0.001356122,0.0006205781,0.001316336,0.001875826,0.001325948,0.004441229],"category_scores_gemma":[0.002446657,0.0007254387,0.001365682,0.001131342,0.0004375942,0.00115988,0.002136605,0.001931829,0.002904569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009643634,"about_ca_system_score_gemma":0.001324998,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003784798,"about_ca_topic_score_gemma":0.006757431,"domain_scores_codex":[0.9995877,0.00006584095,0.00001999328,0.0001593535,0.0001068869,0.00006022041],"domain_scores_gemma":[0.9994051,0.0002363867,0.00008205435,0.0001148768,0.00008749263,0.00007406293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004848282,0.001564289,0.02076923,0.001758439,0.002264409,0.000972697,0.0001925403,0.1185693,0.1266272,0.008080744,0.1914192,0.5229336],"study_design_scores_gemma":[0.000164302,0.0002193011,0.002841009,0.0000459663,0.0001317561,0.0002301333,0.00002886938,0.9573752,0.01945464,0.01004005,0.009400149,0.00006857009],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1805882,0.005643149,0.6043553,0.001584697,0.0006857614,0.0003805484,0.05478857,0.1464366,0.005537171],"genre_scores_gemma":[0.5072307,0.001831803,0.3917954,0.001604327,0.0003315501,0.0008323692,0.08320867,0.004104777,0.009060404],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004441229,"threshold_uncertainty_score":0.01485741,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00743944056699306,"score_gpt":0.3140974849949114,"score_spread":0.3066580444279183,"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."}}