PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Machine learning methods for predictive proteomics.
annalisa barla, giuseppe jurman, samantha riccadonna, marco chierici, stefano merler and cesare furlanello
Briefings in Bioinformatics 2008.

Abstract

The search for predictive biomarkers of disease from high-throughput mass spectrometry (MS) data requires a complex analysis path. Preprocessing and machine-learning modules are pipelined, starting from raw spectra, to set up a predictive classifier based on a shortlist of candidate features. As a machine-learning problem, proteomic profiling on MS data needs caution like the microarray case. The risk of overfitting and of selection bias effects is pervasive: not only potential features easily outnumber samples by 103 times, but it is easy to neglect information-leakage effects during preprocessing from spectra to peaks. The aim of this review is to explain how to build a general purpose design analysis protocol (DAP) for predictive proteomic profiling: we show how to limit leakage due to parameter tuning and how to organize classification and ranking on large numbers of replicate versions of the original data to avoid selection bias. The DAP can be used with alternative components, i.e. with different preprocessing methods (peak clustering or wavelet based), classifiers e.g. Suport Vector Machine (SVM) or feature ranking methods recursive feature elimination (RFE) or I-Relief. A procedure for assessing stability and predictive value of the resulting biomarkers’ list is also provided. The approach is exemplified with experiments on synthetic datasets (from the Cromwell MS simulator) and with publicly available datasets from cancer studies.

EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Learning/Statistics & Optimisation
ID Code:4116
Deposited By:annalisa barla
Deposited On:03 April 2008