| Combining gene expression and interaction network data to improve kidney lesion score prediction. | |
| | |
MedLine Citation:
|
PMID: 22450270 Owner: NLM Status: In-Data-Review |
Abstract/OtherAbstract:
|
Current method of diagnosing kidney rejection based on histopathology of renal biopsies in form of lesion scores is error-prone. Researchers use gene expression microarrays in combination of machine learning to build better kidney rejection predictors. However the high dimensionality of data makes this task challenging and compels application of feature selection methods. We present a method for predicting lesions using combination of statistical and biological feature selection methods along with an ensemble learning technique. Results show that combining highly interacting genes (Hub Genes) from protein-protein interaction network with genes selected by squared t-test method brings the most accurate kidney lesion score predictor. |
| | |
Authors:
|
Davoud Moulavi; Mohsen Hajiloo; Jorg Sander; Philip F Halloran; Russell Greiner |
Publication Detail:
|
Type: Journal Article |
Journal Detail:
|
Title: International journal of bioinformatics research and applications Volume: 8 ISSN: 1744-5485 ISO Abbreviation: Int J Bioinform Res Appl Publication Date: 2012 |
Date Detail:
|
Created Date: 2012-03-27 Completed Date: - Revised Date: - |
Medline Journal Info:
|
Nlm Unique ID: 101253758 Medline TA: Int J Bioinform Res Appl Country: Switzerland |
Other Details:
|
Languages: eng Pagination: 54-66 Citation Subset: IM |
Affiliation:
|
Department of Computing Science, University of Alberta, Edmonton, Alberta T6G 2E8, Canada. |
Export Citation:
|
APA/MLA Format Download EndNote Download BibTex |
| MeSH Terms | |
Descriptor/Qualifier:
|
|
From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
Previous Document: Large margin classifiers and Random Forests for integrated biological prediction.
Next Document: Detecting molecular selection on single amino acid replacements.