Using topic modeling via non-negative matrix factorization to identify relationships between genetic variants and disease phenotypes: A case study of Lipoprotein(a) (LPA)

Juan Zhao,Wei-Qi Wei,Joshua C Denny,Patrick Wu,Qiping Feng,Jeremy L Warner,Zhi Wei

doi:10.1371/journal.pone.0212112

Juan Zhao, Wei-Qi Wei + Show 5 more

Open Access

https://doi.org/10.1371/journal.pone.0212112

Copy DOI

Abstract

Genome-wide and phenome-wide association studies are commonly used to identify important relationships between genetic variants and phenotypes. Most studies have treated diseases as independent variables and suffered from the burden of multiple adjustment due to the large number of genetic variants and disease phenotypes. In this study, we used topic modeling via non-negative matrix factorization (NMF) for identifying associations between disease phenotypes and genetic variants. Topic modeling is an unsupervised machine learning approach that can be used to learn patterns from electronic health record data. We chose the single nucleotide polymorphism (SNP) rs10455872 in LPA as the predictor since it has been shown to be associated with increased risk of hyperlipidemia and cardiovascular diseases (CVD). Using data of 12,759 individuals with electronic health records (EHR) and linked DNA samples at Vanderbilt University Medical Center, we trained a topic model using NMF from 1,853 distinct phenotypes and identified six topics. We tested their associations with rs10455872 in LPA. Topics enriched for CVD and hyperlipidemia had positive correlations with rs10455872 (P < 0.001), replicating a previous finding. We also identified a negative correlation between LPA and a topic enriched for lung cancer (P < 0.001) which was not previously identified via phenome-wide scanning. We were able to replicate the top finding in a separate dataset. Our results demonstrate the applicability of topic modeling in exploring the relationship between genetic variants and clinical diseases.

Highlights

Elucidating associations between genetic variants and human diseases creates new avenues for disease prevention and enables precise identification and treatment of diseases [1,2]
The dataset used in the analyses described were obtained from Vanderbilt University Medical Centers BioVU which is supported by institutional funding and by the CTSA grant ULTR000445 from NCATS/NIH
During the past two decades, genetic studies have uncovered thousands of genetic variants that influence risk for disease phenotypes [3], e.g., the discovery of a variant in proprotein convertase subtilisin/kexin type 9 (PCSK9[4]) associated with low plasma low-density lipoprotein, which led to a new therapeutic drug class that was approved by the US Food and Drug Administration in 2015

Summary

Introduction

Elucidating associations between genetic variants and human diseases creates new avenues for disease prevention and enables precise identification and treatment of diseases [1,2]. During the past two decades, genetic studies have uncovered thousands of genetic variants that influence risk for disease phenotypes [3], e.g., the discovery of a variant in proprotein convertase subtilisin/kexin type 9 (PCSK9[4]) associated with low plasma low-density lipoprotein, which led to a new therapeutic drug class that was approved by the US Food and Drug Administration in 2015. Many of these discoveries come from large-scale association analyses. The output is different, these techniques share many commonalities

Methods

Results

Discussion

Conclusion