Improving strategy for discovering interacting genetic variants in association studies

Revealing the underlying complex architecture of human diseases has received considerable attention since the exploration of genotype-phenotype relationships in genetic epidemiology. Identification of these relationships becomes more challenging due to multiple factors acting together or independent...

Full description

Bibliographic Details
Main Authors: Uppu, S., Krishna, Aneesh
Format: Conference Paper
Published: 2016
Online Access:http://hdl.handle.net/20.500.11937/48977
_version_ 1848758137174097920
author Uppu, S.
Krishna, Aneesh
author_facet Uppu, S.
Krishna, Aneesh
author_sort Uppu, S.
building Curtin Institutional Repository
collection Online Access
description Revealing the underlying complex architecture of human diseases has received considerable attention since the exploration of genotype-phenotype relationships in genetic epidemiology. Identification of these relationships becomes more challenging due to multiple factors acting together or independently. A deep neural network was trained in the previous work to identify two-locus interacting single nucleotide polymorphisms (SNPs) related to a complex disease. The model was assessed for all two-locus combinations under various simulated scenarios. The results showed significant improvements in predicting SNP-SNP interactions over the existing conventional machine learning techniques. Furthermore, the findings are confirmed on a published dataset. However, the performance of the proposed method in the higher-order interactions was unknown. The objective of this study is to validate the model for the higher-order interactions in high-dimensional data. The proposed method is further extended for unsupervised learning. A number of experiments were performed on the simulated datasets under same scenarios as well as a real dataset to show the performance of the extended model. On an average, the results illustrate improved performance over the previous methods. The model is further evaluated on a sporadic breast cancer dataset to identify higher-order interactions between SNPs. The results rank top 20 higherorder SNP interactions responsible for sporadic breast cancer.
first_indexed 2025-11-14T09:39:12Z
format Conference Paper
id curtin-20.500.11937-48977
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T09:39:12Z
publishDate 2016
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-489772017-09-13T15:47:18Z Improving strategy for discovering interacting genetic variants in association studies Uppu, S. Krishna, Aneesh Revealing the underlying complex architecture of human diseases has received considerable attention since the exploration of genotype-phenotype relationships in genetic epidemiology. Identification of these relationships becomes more challenging due to multiple factors acting together or independently. A deep neural network was trained in the previous work to identify two-locus interacting single nucleotide polymorphisms (SNPs) related to a complex disease. The model was assessed for all two-locus combinations under various simulated scenarios. The results showed significant improvements in predicting SNP-SNP interactions over the existing conventional machine learning techniques. Furthermore, the findings are confirmed on a published dataset. However, the performance of the proposed method in the higher-order interactions was unknown. The objective of this study is to validate the model for the higher-order interactions in high-dimensional data. The proposed method is further extended for unsupervised learning. A number of experiments were performed on the simulated datasets under same scenarios as well as a real dataset to show the performance of the extended model. On an average, the results illustrate improved performance over the previous methods. The model is further evaluated on a sporadic breast cancer dataset to identify higher-order interactions between SNPs. The results rank top 20 higherorder SNP interactions responsible for sporadic breast cancer. 2016 Conference Paper http://hdl.handle.net/20.500.11937/48977 10.1007/978-3-319-46687-3_51 restricted
spellingShingle Uppu, S.
Krishna, Aneesh
Improving strategy for discovering interacting genetic variants in association studies
title Improving strategy for discovering interacting genetic variants in association studies
title_full Improving strategy for discovering interacting genetic variants in association studies
title_fullStr Improving strategy for discovering interacting genetic variants in association studies
title_full_unstemmed Improving strategy for discovering interacting genetic variants in association studies
title_short Improving strategy for discovering interacting genetic variants in association studies
title_sort improving strategy for discovering interacting genetic variants in association studies
url http://hdl.handle.net/20.500.11937/48977