Genetic Mechanism Revealed of Age-Related Macular Degeneration Based on Fusion of Statistics and Machine Learning Method

Age-related macular degeneration (AMD) is the most common cause of irreversible vision loss in the developed world which affects the quality of life for millions of elderly individuals worldwide. Genome-wide association studies (GWAS) have identified genetic variants at 34 loci contributing to AMD....

Full description

Saved in:
Bibliographic Details
Published inFrontiers in genetics Vol. 12; p. 726599
Main Authors Du, Yongyi, Kong, Ning, Zhang, Jibin
Format Journal Article
LanguageEnglish
Published Frontiers Media S.A 05.08.2021
Subjects
AMD
disease susceptibility
eQTL
Genetics
GWAS
SNPs
Online AccessGet full text

Cover

More Information
Summary:Age-related macular degeneration (AMD) is the most common cause of irreversible vision loss in the developed world which affects the quality of life for millions of elderly individuals worldwide. Genome-wide association studies (GWAS) have identified genetic variants at 34 loci contributing to AMD. To better understand the disease pathogenesis and identify causal genes for AMD, we applied random walk (RW) and support vector machine (SVM) to identify AMD-related genes based on gene interaction relationship and significance of genes. Our model achieved 0.927 of area under the curve (AUC), and 65 novel genes have been identified as AMD-related genes. To verify our results, a statistics method called summary data-based Mendelian randomization (SMR) has been implemented to integrate GWAS data and transcriptome data to verify AMD susceptibility-related genes. We found 45 genes are related to AMD by SMR. Among these genes, 37 genes overlap with those found by SVM-RW. Finally, we revealed the biological process of genetic mutations leading to changes in gene expression leading to AMD. Our results reveal the genetic pathogenic factors and related mechanisms of AMD.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Edited by: Lei Deng, Central South University, China
Reviewed by: Hong Ju, Heilongjiang Vocational College of Biology Science and Technology, China; Hui Ding, University of Electronic Science and Technology of China, China
This article was submitted to Statistical Genetics and Methodology, a section of the journal Frontiers in Genetics
ISSN:1664-8021
1664-8021
DOI:10.3389/fgene.2021.726599