MSpectraAI: a powerful platform for deciphering proteome profiling of multi-tumor mass spectrometry data by using deep neural networks
文献类型：期刊论文
| 作者 | Wang, Shisheng1,2; Zhu, Hongwen3; Zhou, Hu3 ; Cheng, Jingqiu1,2; Yang, Hao1,2
|
| 刊名 | BMC BIOINFORMATICS
 |
| 出版日期 | 2020-10-07 |
| 卷号 | 21期号:1页码:15 |
| 关键词 | Raw mass spectrometry data Proteome profiling Feature swath extraction Deep neural networks Multi-tumor types Leave-one-out cross prediction strategy |
| ISSN号 | 1471-2105 |
| DOI | 10.1186/s12859-020-03783-0 |
| 通讯作者 | Cheng, Jingqiu(jqcheng@scu.edu.cn) ; Yang, Hao(yanghao@scu.edu.cn) |
| 英文摘要 | BackgroundMass spectrometry (MS) has become a promising analytical technique to acquire proteomics information for the characterization of biological samples. Nevertheless, most studies focus on the final proteins identified through a suite of algorithms by using partial MS spectra to compare with the sequence database, while the pattern recognition and classification of raw mass-spectrometric data remain unresolved. ResultsWe developed an open-source and comprehensive platform, named MSpectraAI, for analyzing large-scale MS data through deep neural networks (DNNs); this system involves spectral-feature swath extraction, classification, and visualization. Moreover, this platform allows users to create their own DNN model by using Keras. To evaluate this tool, we collected the publicly available proteomics datasets of six tumor types (a total of 7,997,805 mass spectra) from the ProteomeXchange consortium and classified the samples based on the spectra profiling. The results suggest that MSpectraAI can distinguish different types of samples based on the fingerprint spectrum and achieve better prediction accuracy in MS1 level (average 0.967).ConclusionThis study deciphers proteome profiling of raw mass spectrometry data and broadens the promising application of the classification and prediction of proteomics data from multi-tumor samples using deep learning methods. MSpectraAI also shows a better performance compared to the other classical machine learning approaches. |
| WOS关键词 | PEPTIDE IDENTIFICATION ; ACCURATE |
| 资助项目 | National Natural Science Foundation of China[81871475] ; 1.3.5 project for disciplines of excellence, West China Hospital, Sichuan University, Sichuan, China[ZYGD18014] |
| WOS研究方向 | Biochemistry & Molecular Biology ; Biotechnology & Applied Microbiology ; Mathematical & Computational Biology |
| 语种 | 英语 |
| WOS记录号 | WOS:000578528400003 |
| 出版者 | BMC |
| 源URL | [http://119.78.100.183/handle/2S10ELR8/291477]  |
| 专题 | 中国科学院上海药物研究所 |
| 通讯作者 | Cheng, Jingqiu; Yang, Hao |
| 作者单位 | 1.Sichuan Univ, West China Hosp, West China Washington Mitochondria & Metab Res Ct, 88 Keyuan South Rd, Chengdu 610041, Peoples R China 2.Sichuan Univ, West China Hosp, Key Lab Transplant Engn & Immunol, MOH,Regenerat Med Res Ctr, 88 Keyuan South Rd, Chengdu 610041, Peoples R China 3.Chinese Acad Sci, Shanghai Inst Mat Med, Shanghai, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wang, Shisheng,Zhu, Hongwen,Zhou, Hu,et al. MSpectraAI: a powerful platform for deciphering proteome profiling of multi-tumor mass spectrometry data by using deep neural networks[J]. BMC BIOINFORMATICS,2020,21(1):15. |
| APA | Wang, Shisheng,Zhu, Hongwen,Zhou, Hu,Cheng, Jingqiu,&Yang, Hao.(2020).MSpectraAI: a powerful platform for deciphering proteome profiling of multi-tumor mass spectrometry data by using deep neural networks.BMC BIOINFORMATICS,21(1),15. |
| MLA | Wang, Shisheng,et al."MSpectraAI: a powerful platform for deciphering proteome profiling of multi-tumor mass spectrometry data by using deep neural networks".BMC BIOINFORMATICS 21.1(2020):15. |
入库方式： OAI收割
来源：上海药物研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。