On Bayesian classification with Laplace priors
Pattern Recognition Letters
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Effective Gene Selection Method Using Bayesian Discriminant Based Criterion and Genetic Algorithms
Journal of Signal Processing Systems
Cancer classification by gradient LDA technique using microarray gene expression data
Data & Knowledge Engineering
Ensemble Neural Networks with Novel Gene-Subsets for Multiclass Cancer Classification
Neural Information Processing
An expert system to classify microarray gene expression data using gene selection by decision tree
Expert Systems with Applications: An International Journal
Learning Nondeterministic Classifiers
The Journal of Machine Learning Research
Identification of Full and Partial Class Relevant Genes
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Bioinformatics contributions to data mining
ICDM'10 Proceedings of the 10th industrial conference on Advances in data mining: applications and theoretical aspects
Model building using bi-level optimization
Journal of Global Optimization
Recursive Mahalanobis Separability Measure for Gene Subset Selection
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
Learning Instance-Specific Predictive Models
The Journal of Machine Learning Research
Methods in case-based classification in bioinformatics: lessons learned
ICDM'11 Proceedings of the 11th international conference on Advances in data mining: applications and theoretical aspects
Stable Gene Selection from Microarray Data via Sample Weighting
IEEE/ACM Transactions on Computational Biology and Bioinformatics (TCBB)
VDMB'06 Proceedings of the First international conference on Data Mining and Bioinformatics
Missing value imputation framework for microarray significant gene selection and class prediction
BioDM'06 Proceedings of the 2006 international conference on Data Mining for Biomedical Applications
AI'05 Proceedings of the 18th Australian Joint conference on Advances in Artificial Intelligence
Tissue classification using gene expression data and artificial neural network ensembles
ICIC'06 Proceedings of the 2006 international conference on Computational Intelligence and Bioinformatics - Volume Part III
On efficient calculations for Bayesian variable selection
Computational Statistics & Data Analysis
Leukemia prediction from gene expression data—a rough set approach
ICAISC'06 Proceedings of the 8th international conference on Artificial Intelligence and Soft Computing
ICCBR'10 Proceedings of the 18th international conference on Case-Based Reasoning Research and Development
Comparison of reuse strategies for case-based classification in bioinformatics
ICCBR'11 Proceedings of the 19th international conference on Case-Based Reasoning Research and Development
An alternating direction method for finding Dantzig selectors
Computational Statistics & Data Analysis
Prognostic modeling with high dimensional and censored data
ICDM'12 Proceedings of the 12th Industrial conference on Advances in Data Mining: applications and theoretical aspects
Engineering Applications of Artificial Intelligence
Assessing similarity of feature selection techniques in high-dimensional domains
Pattern Recognition Letters
| Hi-index | 3.84 |
Motivation: Selecting a small number of relevant genes for accurate classification of samples is essential for the development of diagnostic tests. We present the Bayesian model averaging (BMA) method for gene selection and classification of microarray data. Typical gene selection and classification procedures ignore model uncertainty and use a single set of relevant genes (model) to predict the class. BMA accounts for the uncertainty about the best set to choose by averaging over multiple models (sets of potentially overlapping relevant genes). Results: We have shown that BMA selects smaller numbers of relevant genes (compared with other methods) and achieves a high prediction accuracy on three microarray datasets. Our BMA algorithm is applicable to microarray datasets with any number of classes, and outputs posterior probabilities for the selected genes and models. Our selected models typically consist of only a few genes. The combination of high accuracy, small numbers of genes and posterior probabilities for the predictions should make BMA a powerful tool for developing diagnostics from expression data. Availability: The source codes and datasets used are available from our Supplementary website. Contact: kayee@u.washington.edu Supplementary information: http://www.expression.washington.edu/publications/kayee/bma