METHOD OF CONSTRUCTION OF GENETIC DATA CLUSTERS
The paper presents a method of construction of genetic data clusters (functional modules) using the randomized matrices. To build the functional modules the selection and analysis of the eigenvalues of the gene profiles correlation matrix is performed. The principal components, corresponding to the...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | Russian |
| Published: |
National Academy of Sciences of Belarus, the United Institute of Informatics Problems
2016-10-01
|
| Series: | Informatika |
| Online Access: | https://inf.grid.by/jour/article/view/125 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The paper presents a method of construction of genetic data clusters (functional modules) using the randomized matrices. To build the functional modules the selection and analysis of the eigenvalues of the gene profiles correlation matrix is performed. The principal components, corresponding to the eigenvalues, which are significantly different from those obtained for the randomly generated correlation matrix, are used for the analysis. Each selected principal component forms gene cluster. In a comparative experiment with the analogs the proposed method shows the advantage in allocating statistically significant different-sized clusters, the ability to filter non- informative genes and to extract the biologically interpretable functional modules matching the real data structure. |
|---|---|
| ISSN: | 1816-0301 |