Neural Networks: A Comprehensive Foundation
Neural Networks: A Comprehensive Foundation
Kernel Methods for Pattern Analysis
Kernel Methods for Pattern Analysis
Rosetta error model for gene expression analysis
Bioinformatics
Rosetta error model for gene expression analysis
Bioinformatics
An introduction to kernel-based learning algorithms
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
We describe the use of a kernel-based approach using the Laplacian matrix to visualize an integrated Chronic Fatigue Syndrome dataset comprising symptom and fatigue questionnaire and patient classification data, complete blood evaluation data and patient gene expression profiles. We present visualizations of the individual and integrated datasets with the linear and Gaussian kernel functions. An efficient approach inspired by computational linguistics for constructing a linear kernel matrix for the gene expression data is described. Visualizations of the questionnaire data show a cluster of non-fatigued individuals distinct from those suffering from Chronic Fatigue Syndrome that supports the fact that diagnosis is generally made using this kind of data. Clusters unrelated to patient classes were found in the gene expression data. Structure from the gene expression dataset dominated visualizations of integrated datasets that included gene expression data.