Classification of mislabelled microarrays using robust sparse logistic regression
Open Access
- 15 February 2013
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 29 (7) , 870-877
Abstract
Motivation: Previous studies reported that labelling errors are not uncommon in microarray datasets. In such cases, the training set may become misleading, and the ability of classifiers to make reliable inferences from the data is compromised. Yet, few methods are currently available in the bioinformatics literature to deal with this problem. The few existing methods focus on data cleansing alone, without reference to classification, and their performance crucially depends on some tuning parameters. Results: In this article, we develop a new method to detect mislabelled arrays simultaneously with learning a sparse logistic regression classifier. Our method may be seen as a label-noise robust extension of the well-known and successful Bayesian logistic regression classifier. To account for possible mislabelling, we formulate a label-flipping process as part of the classifier. The regularization parameter is automatically set using Bayesian regularization, which not only saves the computation time that cross-validation would take, but also eliminates any unwanted effects of label noise when setting the regularization parameter. Extensive experiments with both synthetic data and real microarray datasets demonstrate that our approach is able to counter the bad effects of labelling errors in terms of predictive performance, it is effective at identifying marker genes and simultaneously it detects mislabelled arrays to high accuracy. Availability: The code is available from http://cs.bham.ac.uk/∼jxb008. Contact:J.Bootkrajang@cs.bham.ac.uk Supplementary information: Supplementary data are available at Bioinformatics online.Keywords
This publication has 21 references indexed in Scilit:
- Label-Noise Robust Logistic Regression and Its ApplicationsLecture Notes in Computer Science, 2012
- Gene selection in cancer classification using sparse logistic regression with Bayesian regularizationBioinformatics, 2006
- Detecting outlying samples in microarray data: A critical assessment of the effect of outliers on sample classificationChem-Bio Informatics Journal, 2003
- Gene Assessment and Sample Classification for Gene Expression Data Using a Genetic Algorithm / k-nearest Neighbor MethodCombinatorial Chemistry & High Throughput Screening, 2001
- Decontamination of Training Samples for Supervised Pattern Recognition Methods2000
- Identifying Mislabeled Training DataJournal of Artificial Intelligence Research, 1999
- Learning with an unreliable teacherPattern Recognition, 1992
- Efficiency of discriminant analysis when initial samples are classified stochasticallyPattern Recognition, 1990
- Linear Discriminant Analysis with Misallocation in Training SamplesJournal of the American Statistical Association, 1984
- Discriminant Analysis When the Initial Samples are Misclassified II: Non-Random Misclassification ModelsTechnometrics, 1974