UM
Random Forest Model for Quality Control of High Resolution Mass Spectra from SILAC Labeling Experiments
Chen, Long; Li, Tianjun; Liu, Y; Zhao, L; Cai, G; Xiao, G; Li, KL; Wang, L
2017
Conference Name2017 13TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD)
Pages2043-2048
Publication Place345 E 47TH ST, NEW YORK, NY 10017 USA
PublisherIEEE
AbstractAlthough plenty of chemical and electrical methods were employed to improve the performance of Liquid Chromatography-Mass Spectrometry(LC-MS) methods, the effective bioinformatics and statistical methods for the quantification of proteomics are still irreplaceable. A method for quality control of stable isotope labeling with amino acids in cell culture (SILAC) mass spectra acquired from high resolution mass spectrometers were described here. The mass profiles of light and heavy peptide pairs produced by SILAC and LC-MS are often affected by the collection instrument and the collection methods. Such influences may reduce the accuracy of further ratio estimations. So we applied Random Forest (RF) to remove the low quality mass spectra which deviated from expected theoretical isotopic distributions. Specifically, based on some features of the peptides, we trained a RF classifier and got the probability of positive or negative class for each mass profile via a training set obtained from some yeast samples. Then we tested the RF classifier on other profiles from yeast samples with different Light-Heavy ratios. We found that filtering mass profiles by RF classifier can improve the reliability of peptide ratio estimations significantly.
URLView the original
Indexed ByCPCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000437355302012
The Source to ArticleWOS
全文获取链接
引用统计
Document TypeConference paper
专题University of Macau
推荐引用方式
GB/T 7714
Chen, Long,Li, Tianjun,Liu, Y,et al. Random Forest Model for Quality Control of High Resolution Mass Spectra from SILAC Labeling Experiments[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2017:2043-2048.
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
Google Scholar
中相似的文章 Google Scholar
[Chen, Long]的文章
[Li, Tianjun]的文章
[Liu, Y]的文章
Baidu academic
中相似的文章 Baidu academic
[Chen, Long]的文章
[Li, Tianjun]的文章
[Liu, Y]的文章
Bing Scholar
中相似的文章 Bing Scholar
[Chen, Long]的文章
[Li, Tianjun]的文章
[Liu, Y]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。