Back to Search
Start Over
Effective Enrichment of Gene Expression Data Sets
- Source :
- ICMLA (1)
- Publication Year :
- 2012
- Publisher :
- IEEE, 2012.
-
Abstract
- 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.
- Subjects :
- Differential equations
Differential equation
Computer science
gene expression data sets
sample generation
Gene regulatory network
gene regulatory network
computer.software_genre
Machine learning
sampling data
Mathematical model
gene expression data
Gene expression
Training
Boolean functions
Boolean function
Gene
Probabilistic logic
Measurement
learning
business.industry
probabilistic Boolean networks
gene regulation modeling
gene expression data analysis
Data set
multiobjective filtering mechanism
multiple perspectives
ordinary differential equations
Ordinary differential equation
multimodel framework
Data mining
Artificial intelligence
business
computer
GRN
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2012 11th International Conference on Machine Learning and Applications
- Accession number :
- edsair.doi.dedup.....d1e23a883edd7d8bdf48996f2b82ce71