1,000x Faster than PLINK: Genome-Wide Epistasis Detection with Logistic Regression Using Combined FPGA and GPU Accelerators

EasyChair Preprint 60

Abstract

Logistic regression as implemented in PLINK is a powerful and commonly used framework for assessing gene-gene (GxG) interactions. However, fitting regression models for each pair of markers in a genome-wide dataset is a computationally intensive task. Performing billions of tests with PLINK takes days if not weeks, for which reason pre-filtering techniques and fast epistasis screenings are applied to reduce the computational burden. Here, we demonstrate that employing a combination of a Xilinx UltraScale KU115 FPGA and an Nvidia Tesla P100 GPU leads to runtimes of only minutes for logistic regression GxG tests on a genome-wide level. In particular, a dataset with 53,000 samples genotyped at 130,000 SNPs was analyzed in 8 minutes, resulting in a speedup of more than 1,000 when compared to PLINK v1.9 using 32 threads on a server-grade computing platform. Furthermore, on-the-fly calculation of test statistics, p-values and LD-scores in double precision make commonly used pre-filtering strategies obsolete.

Keyphrases: Boost, Computer Science, FPGA computing, GPU computing, Genome-Wide Association Studies (GWAS), Genome-wide association study, Hardware Accelerator, PLINK, contingency table, gene-gene (GxG) interaction, gene-gene interaction, genome wide interaction study, genome-wide interaction studies (GWIS), gpu computing architecture, heterogeneous architectures, hybrid computing, intel xeon e5, kintex ultrascale ku115, linkage disequilibrium, linkage disequilibrium (LD), logistic regression, logistic regression test, nvidia tesla p100, tesla p100 gpu, ultrascale ku115 fpga, xilinx kintex ultrascale

@booklet{EasyChair:60,
  author    = {Lars Wienbrandt and Jan Christian Kässens and Matthias Hübenthal and David Ellinghaus},
  title     = {1,000x Faster than PLINK: Genome-Wide Epistasis Detection with Logistic Regression Using Combined FPGA and GPU Accelerators},
  doi       = {10.29007/w46m},
  howpublished = {EasyChair Preprint 60},
  year      = {EasyChair, 2018}}