Effective Enrichment of Gene Expression Data Sets
The ever-growing need for gene-expression data analysis motivates studies in sample generation due to the lack of enough gene-expression data. It is common that there are thousands of genes but only tens or rarely hundreds of samples available. In this paper, we attempt to formulate the sample generation task as follows: first, building alternative Gene Regulatory Network (GRN) models, second, sampling data from each of them, and then filtering the generated samples using metrics that measure compatibility, diversity and coverage with respect to the original dataset. We constructed two alternative GRN models using Probabilistic Boolean Networks and Ordinary Differential Equations. We developed a multi-objective filtering mechanism based on the three metrics to assess the quality of the newly generated data. We presented a number of experiments to show effectiveness and applicability of the proposed multi-model framework.
Keywords: GRN ; gene expression data sets ; gene regulatory network ; gene expression data analysis ; multimodel framework ; multiobjective filtering mechanism ; ordinary differential equations ; probabilistic Boolean networks ; sampling data ; Boolean functions ; Differential equations ; Gene expression ; Mathematical model ; Measurement ; Probabilistic logic ; Training ; gene expression data ; gene regulation modeling ; learning ; multiple perspectives ; ordinary differential equations ; probabilistic boolean networks ; sample generation
Record created on 2015-08-21, modified on 2016-08-09