Author ORCID Identifier
Document Type
Article
Publication Date
8-7-2012
Abstract
Background: An approach to molecular classification based on the comparative expression of protein pairs is presented. The method overcomes some of the present limitations in using peptide intensity data for class prediction for problems such as the detection of a disease, disease prognosis, or for predicting treatment response. Data analysis is particularly challenging in these situations due to sample size (typically tens) being much smaller than the large number of peptides (typically thousands). Methods based upon high dimensional statistical models, machine learning or other complex classifiers generate decisions which may be very accurate but can be complex and difficult to interpret in simple or biologically meaningful terms. A classification scheme, called ProtPair, is presented that generates simple decision rules leading to accurate classification which is based on measurement of very few proteins and requires only relative expression values, providing specific targeted hypotheses suitable for straightforward validation.Results: ProtPair has been tested against clinical data from 21 patients following a bone marrow transplant, 13 of which progress to idiopathic pneumonia syndrome (IPS). The approach combines multiple peptide pairs originating from the same set of proteins, with each unique peptide pair providing an independent measure of discriminatory power. The prediction rate of the ProtPair for IPS study as measured by leave-one-out CV is 69.1%, which can be very beneficial for clinical diagnosis as it may flag patients in need of closer monitoring. The " top ranked" proteins provided by ProtPair are known to be associated with the biological processes and pathways intimately associated with known IPS biology based on mouse models.Conclusions: An approach to biomarker discovery, called ProtPair, is presented. ProtPair is based on the differential expression of pairs of peptides and the associated proteins. Using mass spectrometry data from " bottom up" proteomics methods, functionally related proteins/peptide pairs exhibiting co-ordinated changes expression profile are discovered, which represent a signature for patients progressing to various disease conditions. The method has been tested against clinical data from patients progressing to idiopthatic pneumonia syndrome (IPS) following a bone marrow transplant. The data indicates that patients with improper regulation in the concentration of specific acute phase response proteins at the time of bone marrow transplant are highly likely to develop IPS within few weeks. The results lead to a specific set of protein pairs that can be efficiently verified by investigating the pairwise abundance change in independent cohorts using ELISA or targeted mass spectrometry techniques. This generalized classifier can be extended to other clinical problems in a variety of contexts.
Keywords
biomarker discovery, classification, Idiopathic Pneumonia Syndrome, ProtPair classifier.
Publication Title
BMC Bioinformatics
Grant
UL1 RR024989
Rights
© 2012 Kaur et al.; licensee BioMed Central Ltd. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Recommended Citation
Kaur, P., Schlatzer, D., Cooke, K. et al. Pairwise protein expression classifier for candidate biomarker discovery for early detection of human disease prognosis. BMC Bioinformatics 13, 191 (2012). https://doi.org/10.1186/1471-2105-13-191
Manuscript Version
Final Publisher Version