SAERMA: Stacked Autoencoder Rule Mining Algorithm for the Interpretation of Epistatic Interactions in GWAS for Extreme Obesity

Montanez, Casimiro A Curbelo, Fergus, Paul ORCID: 0000-0002-7070-4447, Chalmers, Carl ORCID: 0000-0003-0822-1150, Malim, Nurul Hashimah Ahamed Hassain, Abdulaimma, Basma, Reilly, Denis and Falciani, Francesco ORCID: 0000-0003-1432-2871
(2020) SAERMA: Stacked Autoencoder Rule Mining Algorithm for the Interpretation of Epistatic Interactions in GWAS for Extreme Obesity. IEEE Access, 8. 112379 - 112392.

This is the latest version of this item.

[img] Text
1908.10166v1.pdf - Submitted Version

Download (920kB) | Preview
[img] Text
09119109.pdf - OA Published Version

Download (7MB) | Preview


One of the most important challenges in the analysis of high-throughput genetic data is the development of efficient computational methods to identify statistically significant Single Nucleotide Polymorphisms (SNPs). Genome-wide association studies (GWAS) use single-locus analysis where each SNP is independently tested for association with phenotypes. The limitation with this approach, however, is its inability to explain genetic variation in complex diseases. Alternative approaches are required to model the intricate relationships between SNPs. Our proposed approach extends GWAS by combining deep learning stacked autoencoders (SAEs) and association rule mining (ARM) to identify epistatic interactions between SNPs. Following traditional GWAS quality control and association analysis, the most significant SNPs are selected and used in the subsequent analysis to investigate epistasis. SAERMA controls the classification results produced in the final fully connected multi-layer perceptron neural network (MLPNN) by manipulating the interestingness measures, support and confidence, in the rule generation process. The best classification results were achieved with 204 SNPs compressed to 100 units (77% AUC, 77% SE, 68% SP, 53% Gini, logloss = 0.58, and MSE = 0.20), although it was possible to achieve 73% AUC (77% SE, 63% SP, 45% Gini, logloss = 0.62, and MSE = 0.21) with 50 hidden units – both supported by close model interpretation.

Item Type: Article
Uncontrolled Keywords: Obesity, Bioinformatics, Genomics, Diseases, Artificial neural networks, Deep learning, Association rules, autoencoders, deep learning, epistasis, genome-wide association studies (GWAS), obesity
Depositing User: Symplectic Admin
Date Deposited: 11 Aug 2020 10:17
Last Modified: 07 Sep 2022 11:41
DOI: 10.1109/ACCESS.2020.3002923
Open Access URL:
Related URLs:

Available Versions of this Item