A Comparison of Methods for Classifying Clinical Samples Based on Proteomics Data: A Case Study for Statistical and Machine Learning Approaches
Open Access
- 28 September 2011
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 6 (9) , e24973
Abstract
The discovery of protein variation is an important strategy in disease diagnosis within the biological sciences. The current benchmark for elucidating information from multiple biological variables is the so called “omics” disciplines of the biological sciences. Such variability is uncovered by implementation of multivariable data mining techniques which come under two primary categories, machine learning strategies and statistical based approaches. Typically proteomic studies can produce hundreds or thousands of variables, p, per observation, n, depending on the analytical platform or method employed to generate the data. Many classification methods are limited by an n≪p constraint, and as such, require pre-treatment to reduce the dimensionality prior to classification. Recently machine learning techniques have gained popularity in the field for their ability to successfully classify unknown samples. One limitation of such methods is the lack of a functional model allowing meaningful interpretation of results in terms of the features used for classification. This is a problem that might be solved using a statistical model-based approach where not only is the importance of the individual protein explicit, they are combined into a readily interpretable classification rule without relying on a black box approach. Here we incorporate statistical dimension reduction techniques Partial Least Squares (PLS) and Principal Components Analysis (PCA) followed by both statistical and machine learning classification methods, and compared them to a popular machine learning technique, Support Vector Machines (SVM). Both PLS and SVM demonstrate strong utility for proteomic classification problems.Keywords
This publication has 45 references indexed in Scilit:
- Large-Scale Proteomics and Phosphoproteomics of Urinary ExosomesJournal of the American Society of Nephrology, 2009
- Sparse canonical methods for biological data integration: application to a cross-platform studyBMC Bioinformatics, 2009
- CMA – a comprehensive Bioconductor package for supervised classification with high dimensional dataBMC Bioinformatics, 2008
- Conditional variable importance for random forestsBMC Bioinformatics, 2008
- Application of the Random Forest Classification Method to Peaks Detected from Mass Spectrometric Proteomic Profiles of Cancer Patients and ControlsStatistical Applications in Genetics and Molecular Biology, 2008
- Combination of SELDI-TOF-MS and Data Mining Provides Early-stage Response Prediction for Rectal Tumors Undergoing Multimodal Neoadjuvant TherapyAnnals of Surgery, 2007
- Dimension Reduction for Classification with Gene Expression Microarray DataStatistical Applications in Genetics and Molecular Biology, 2006
- Linear Models and Empirical Bayes Methods for Assessing Differential Expression in Microarray ExperimentsStatistical Applications in Genetics and Molecular Biology, 2004
- Mass spectrometry-based proteomicsNature, 2003
- Visualisation of Gene Expression Data - the GE-biplot, the Chip-plot and the Gene-plotStatistical Applications in Genetics and Molecular Biology, 2003