用于训练和验证质谱蛋白质组学机器学习模型的多物种基准。

IF 5.8 2区综合性期刊 Q1 MULTIDISCIPLINARY SCIENCES

Scientific Data Pub Date : 2024-11-08 DOI:10.1038/s41597-024-04068-4

Bo Wen, William Stafford Noble

{"title":"用于训练和验证质谱蛋白质组学机器学习模型的多物种基准。","authors":"Bo Wen, William Stafford Noble","doi":"10.1038/s41597-024-04068-4","DOIUrl":null,"url":null,"abstract":"Training machine learning models for tasks such as de novo sequencing or spectral clustering requires large collections of confidently identified spectra. Here we describe a dataset of 2.8 million high-confidence peptide-spectrum matches derived from nine different species. The dataset is based on a previously described benchmark but has been re-processed to ensure consistent data quality and enforce separation of training and test peptides.","PeriodicalId":21597,"journal":{"name":"Scientific Data","volume":"11 1","pages":"1207"},"PeriodicalIF":5.8000,"publicationDate":"2024-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11549408/pdf/","citationCount":"0","resultStr":"{\"title\":\"A multi-species benchmark for training and validating mass spectrometry proteomics machine learning models.\",\"authors\":\"Bo Wen, William Stafford Noble\",\"doi\":\"10.1038/s41597-024-04068-4\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Training machine learning models for tasks such as de novo sequencing or spectral clustering requires large collections of confidently identified spectra. Here we describe a dataset of 2.8 million high-confidence peptide-spectrum matches derived from nine different species. The dataset is based on a previously described benchmark but has been re-processed to ensure consistent data quality and enforce separation of training and test peptides.\",\"PeriodicalId\":21597,\"journal\":{\"name\":\"Scientific Data\",\"volume\":\"11 1\",\"pages\":\"1207\"},\"PeriodicalIF\":5.8000,\"publicationDate\":\"2024-11-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11549408/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Scientific Data\",\"FirstCategoryId\":\"103\",\"ListUrlMain\":\"https://doi.org/10.1038/s41597-024-04068-4\",\"RegionNum\":2,\"RegionCategory\":\"综合性期刊\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MULTIDISCIPLINARY SCIENCES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Scientific Data","FirstCategoryId":"103","ListUrlMain":"https://doi.org/10.1038/s41597-024-04068-4","RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}

引用次数: 0

摘要

要训练机器学习模型来完成从头测序或光谱聚类等任务，需要大量可靠鉴定的光谱集合。在这里，我们描述了一个包含 280 万个来自 9 个不同物种的高置信度肽谱匹配数据集。该数据集基于之前描述的基准，但经过了重新处理，以确保数据质量的一致性，并强制分离训练肽段和测试肽段。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A multi-species benchmark for training and validating mass spectrometry proteomics machine learning models.

Training machine learning models for tasks such as de novo sequencing or spectral clustering requires large collections of confidently identified spectra. Here we describe a dataset of 2.8 million high-confidence peptide-spectrum matches derived from nine different species. The dataset is based on a previously described benchmark but has been re-processed to ensure consistent data quality and enforce separation of training and test peptides.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Scientific Data Social Sciences-Education

CiteScore

11.20

自引率

4.10%

发文量

689

审稿时长

16 weeks

期刊介绍： Scientific Data is an open-access journal focused on data, publishing descriptions of research datasets and articles on data sharing across natural sciences, medicine, engineering, and social sciences. Its goal is to enhance the sharing and reuse of scientific data, encourage broader data sharing, and acknowledge those who share their data. The journal primarily publishes Data Descriptors, which offer detailed descriptions of research datasets, including data collection methods and technical analyses validating data quality. These descriptors aim to facilitate data reuse rather than testing hypotheses or presenting new interpretations, methods, or in-depth analyses.