Carlo Melendez, Justin Sanders, Melih Yilmaz, Wout Bittremieux, William E. Fondrie, Sewoong Oh and William Stafford Noble*,
{"title":"计算卡萨诺沃消化酶偏差","authors":"Carlo Melendez, Justin Sanders, Melih Yilmaz, Wout Bittremieux, William E. Fondrie, Sewoong Oh and William Stafford Noble*, ","doi":"10.1021/acs.jproteome.4c0042210.1021/acs.jproteome.4c00422","DOIUrl":null,"url":null,"abstract":"<p >A key parameter of any bottom-up proteomics mass spectrometry experiment is the identity of the enzyme that is used to digest proteins in the sample into peptides. The Casanovo de novo sequencing model was trained using data that was generated with trypsin digestion; consequently, the model prefers to predict peptides that end with the amino acids “K” or “R\". This bias is desirable when Casanovo is used to analyze data that was also generated using trypsin but can be problematic if the data was generated using some other digestion enzyme. In this work, we modify Casanovo to take as input the identity of the digestion enzyme alongside each observed spectrum. We then train Casanovo with data generated by using several different enzymes, and we demonstrate that the resulting model successfully learns to capture enzyme-specific behavior. However, we find, surprisingly, that this new model does not yield a significant improvement in sequencing accuracy relative to a model trained without enzyme information but using the same training set. This observation may have important implications for future attempts to make use of experimental metadata in de novo sequencing models.</p>","PeriodicalId":48,"journal":{"name":"Journal of Proteome Research","volume":"23 10","pages":"4761–4769 4761–4769"},"PeriodicalIF":3.6000,"publicationDate":"2024-08-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Accounting for Digestion Enzyme Bias in Casanovo\",\"authors\":\"Carlo Melendez, Justin Sanders, Melih Yilmaz, Wout Bittremieux, William E. Fondrie, Sewoong Oh and William Stafford Noble*, \",\"doi\":\"10.1021/acs.jproteome.4c0042210.1021/acs.jproteome.4c00422\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p >A key parameter of any bottom-up proteomics mass spectrometry experiment is the identity of the enzyme that is used to digest proteins in the sample into peptides. The Casanovo de novo sequencing model was trained using data that was generated with trypsin digestion; consequently, the model prefers to predict peptides that end with the amino acids “K” or “R\\\". This bias is desirable when Casanovo is used to analyze data that was also generated using trypsin but can be problematic if the data was generated using some other digestion enzyme. In this work, we modify Casanovo to take as input the identity of the digestion enzyme alongside each observed spectrum. We then train Casanovo with data generated by using several different enzymes, and we demonstrate that the resulting model successfully learns to capture enzyme-specific behavior. However, we find, surprisingly, that this new model does not yield a significant improvement in sequencing accuracy relative to a model trained without enzyme information but using the same training set. This observation may have important implications for future attempts to make use of experimental metadata in de novo sequencing models.</p>\",\"PeriodicalId\":48,\"journal\":{\"name\":\"Journal of Proteome Research\",\"volume\":\"23 10\",\"pages\":\"4761–4769 4761–4769\"},\"PeriodicalIF\":3.6000,\"publicationDate\":\"2024-08-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Proteome Research\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://pubs.acs.org/doi/10.1021/acs.jproteome.4c00422\",\"RegionNum\":2,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BIOCHEMICAL RESEARCH METHODS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Proteome Research","FirstCategoryId":"99","ListUrlMain":"https://pubs.acs.org/doi/10.1021/acs.jproteome.4c00422","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOCHEMICAL RESEARCH METHODS","Score":null,"Total":0}
A key parameter of any bottom-up proteomics mass spectrometry experiment is the identity of the enzyme that is used to digest proteins in the sample into peptides. The Casanovo de novo sequencing model was trained using data that was generated with trypsin digestion; consequently, the model prefers to predict peptides that end with the amino acids “K” or “R". This bias is desirable when Casanovo is used to analyze data that was also generated using trypsin but can be problematic if the data was generated using some other digestion enzyme. In this work, we modify Casanovo to take as input the identity of the digestion enzyme alongside each observed spectrum. We then train Casanovo with data generated by using several different enzymes, and we demonstrate that the resulting model successfully learns to capture enzyme-specific behavior. However, we find, surprisingly, that this new model does not yield a significant improvement in sequencing accuracy relative to a model trained without enzyme information but using the same training set. This observation may have important implications for future attempts to make use of experimental metadata in de novo sequencing models.
期刊介绍:
Journal of Proteome Research publishes content encompassing all aspects of global protein analysis and function, including the dynamic aspects of genomics, spatio-temporal proteomics, metabonomics and metabolomics, clinical and agricultural proteomics, as well as advances in methodology including bioinformatics. The theme and emphasis is on a multidisciplinary approach to the life sciences through the synergy between the different types of "omics".