High-accuracy peptide mass fingerprinting using peak intensity data with machine learning

被引：8

作者：

Yang, Dongmei ^{[1
,3
]}

Ramidssoon, Kevin ^{[1
,3
]}

Hamlett, Eric ^{[1
,3
]}

Giddings, Morgan C. ^{[1
,2
,3
]}

机构：

[1] Univ N Carolina, Dept Comp Sci, Dept Microbiol & Immunol, Chapel Hill, NC 27599 USA

[2] Univ N Carolina, Joint Dept Biomed Engn, Chapel Hill, NC 27599 USA

[3] N Carolina State Univ, Raleigh, NC 27695 USA

来源：

JOURNAL OF PROTEOME RESEARCH | 2008年 / 7卷 / 01期

关键词：

ion suppression; mass spectrometry; peptide mass fingerprinting; protein identification; peak intensity;

D O I：

10.1021/pr070088g

中图分类号：

Q5 [生物化学];

学科分类号：

071010 ; 081704 ;

摘要：

For MALDI-TOF mass spectrometry, we show that the intensity of a peptide-ion peak is directly correlated with its sequence, with the residues M, H, P, R, and L having the most substantial effect on ionization. We developed a machine learning approach that exploits this relationship to significantly improve peptide mass fingerprint (PMF) accuracy based on training data sets from both true-positive and false-positive PMF searches. The model's cross-validated accuracy in distinguishing real versus false-positive database search results is 91%, rivaling the accuracy of MS/MS-based protein identification.

引用

页码：62 / 69

页数：8

共 22 条

[1] Approximate is better than "exact" for interval estimation of binomial proportions [J].