A novel machine learning framework for phenotype prediction based on genome-wide DNA methylation data

No Thumbnail Available
Authors
Karagod, Vinay Vittal
Sinha, Kaushik
Issue Date
2017-05
Type
Conference paper
Language
en_US
Keywords
Cancer, DNA , Predictive models , Principal component analysis , Data models , Biomarkers , Analytical models
Research Projects
Organizational Units
Journal Issue
Alternative Title
Abstract

DNA methylation (DNAm) is an epigenetic mechanism used by cells to control gene expression, and identification of DNAm biomarkers can assist in early diagnosis of cancer. Identification of these biomarkers can be done using CpG (Cytosine-phosphate guanine) sites, or particular regions in DNA. Previous machine learning methods known as MS-SPCA and EVORA have been used to link DNAm biomarkers to specific stages of cervical cancer using CpG data. In this paper, we propose a novel machine learning framework that yields greater AUC accuracy than the MS-SPCA and EVORA for predicting stages of cervical cancer using CpG data. This framework appears to be promising in regards to the data examined herein as well as for future biological studies.

Description
Click on the DOI link to access the article (may not be free).
Citation
Karagod, Vinay Vittal; Sinha, Kaushik. 2017. A novel machine learning framework for phenotype prediction based on genome-wide DNA methylation data. 2017 International Joint Conference on Neural Networks (IJCNN), pp 1657-1664
Publisher
IEEE
License
Journal
Volume
Issue
PubMed ID
DOI
ISSN
2161-4393
EISSN