Abstract
Understanding genetic mechanism of complex diseases is a serious challenge. Existing methods often neglect the heterogeneity phenomenon of complex diseases, resulting in lack of power or low reproducibility. Addressing heterogeneity when detecting epistatic single nucleotide polymorphisms (SNPs) can enhance the power of association studies and improve prediction performance of complex diseases diagnosis. In this study, we propose a three-stage framework including epistasis detection, clustering and prediction to address both epistasis and heterogeneity of complex diseases based on deep learning method. The epistasis detection stage applies a multi-objective optimization method to find several candidate sets of epistatic SNPs which contribute to different subtypes of complex diseases. Then, a K-means clustering algorithm is used to define subtypes of the case group. Finally, a deep learning model has been trained for disease prediction based on graphics processing unit (GPU). Experimental results on pure and heterogeneous datasets show that our method has potential practicality and can serve as a possible alternative to other methods. Therefore, when epistasis and heterogeneity exist at the same time, our method is especially suitable for diagnosis of complex diseases.
Highlights
Due to the ‘missing heritability’ and lack of reproducibility, the exploration of relationships between single nucleotide polymorphisms (SNPs) and complex diseases have been transferred from single variation to biomarkers interactions which are defined as epistasis[2]
Multifactor dimensionality reduction (MDR)[3] and exhaustive search based on multi-objective optimization (ESMO)[4] apply parallel computing to save running time
We cannot tell which method is dominant, which means that for pure datasets our method DPEH can serve as a possible alternative to multifactor dimensionality reduction (MDR)
Summary
Understanding genetic mechanism of complex diseases is a serious challenge. Existing methods often neglect the heterogeneity phenomenon of complex diseases, resulting in lack of power or low reproducibility. Addressing heterogeneity when detecting epistatic single nucleotide polymorphisms (SNPs) can enhance the power of association studies and improve prediction performance of complex diseases diagnosis. We propose a three-stage framework including epistasis detection, clustering and prediction to address both epistasis and heterogeneity of complex diseases based on deep learning method. The epistasis detection stage applies a multi-objective optimization method to find several candidate sets of epistatic SNPs which contribute to different subtypes of complex diseases. With using the exhaustive strategy, all of epistatic combinations have been tested, so that the power of association studies is relatively higher Heuristic methods such as AntEpiSeeker[9] and MACOED10 use prior knowledge or information retrieved by swarm intelligence to narrow down the combination space. After introducing the method of DPEH, the experimental results both on pure and heterogeneous datasets are provided to demonstrate the practicality of DPEH
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have