Analyzing gene expression data in terms of gene sets
Bioinformatics
Quality of Feature Selection Based on Microarray Gene Expression Data
ICCS '08 Proceedings of the 8th international conference on Computational Science, Part III
A First Study on the Use of Coevolutionary Algorithms for Instance and Feature Selection
HAIS '09 Proceedings of the 4th International Conference on Hybrid Artificial Intelligence Systems
Model Instability in Microarray Gene Expression Class Prediction Studies
Computer Aided Systems Theory - EUROCAST 2009
Designing fusers on the basis of discriminants – evolutionary and neural methods of training
HAIS'10 Proceedings of the 5th international conference on Hybrid Artificial Intelligence Systems - Volume Part I
ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part II
Hi-index | 0.00 |
This paper presents a novel approach to building sample classifiers based on microarray gene expression studies. This approach differs from standard methods in the way features are selected. Standard methods focus on features (genes) with most differential expression between classes of samples compared, while the proposed approach takes into account apriori domain knowledge of relationships between features, available e.g., in the form of pathway or gene-ontology databases. Features for classification are then selected on the basis of activation of pathways (gene sets) rather than mutually unrelated genes with very high individual predictive power. Performance of the proposed method is illustrated on the basis of sample microarray studies.