Inferring Personalized and Race-Specific Causal Effects of Genomic Aberrations on Gleason Scores: A Deep Latent Variable Model.

Zhong Chen,Chindo Hicks,Kun Zhang,Andrea Edwards

doi:10.3389/fonc.2020.00272

Abstract

Extensive research has examined socioeconomic factors influencing prostate cancer (PCa) disparities. However, to what extent molecular and genetic mechanisms may also contribute to these inequalities still remains elusive. Although various in vitro, in vivo, and population studies have originated to address this issue, they are often very costly and time-consuming by nature. In this work, we attempt to explore this problem by a preliminary study, where a joint deep latent variable model (DLVM) is proposed to in silico quantify the personalized and race-specific effects that a genomic aberration may exert on the Gleason Score (GS) of each individual PCa patient. The core of the proposed model is a deep variational autoencoder (VAE) framework, which follows the causal structure of inference with proxies. Extensive experimental results on The Cancer Genome Atlas (TCGA) 270 European-American (EA) and 43 African-American (AA) PCa patients demonstrate that ERG fusions, somatic mutations in SPOP and ATM, and copy number alterations (CNAs) in ERG are the statistically significant genomic factors across all low-, intermediate-, and high-grade PCa that may explain the disparities between these two groups. Moreover, compared to a state-of-the-art deep inference method, our proposed method achieves much higher precision in causal effect inference in terms of the impact of a studied genomic aberration on GS. Further validation on an independent set and the assessment of the genomic-risk scores along with corresponding confidence intervals not only validate our results but also provide valuable insight to the observed racial disparity between these two groups regarding PCa metastasis. The pinpointed significant genomic factors may shed light on the molecular mechanism of cancer disparities in PCa and warrant further investigation.

Highlights

Prostate cancer (PCa) is the most commonly diagnosed nonskin cancer and the second leading cause of cancer mortality in American men [1]
Compared to causal effect VAE (CEVAE), the overall average reductions in inference root mean square error (RMSE) achieved by deep latent variable model (DLVM) on AAs and EAs are 19.03 and 22.98%, respectively
As to the germline mutations, the average RMSEs of DLVM on AAs and EAs are 14.26 and 28.70% lower than those of CEVAE. These results indicate that, compared to CEVAE, DLVM is more precise and reliable in inferring the race-specific causal effects that a genomic aberration may pose on Gleason Score (GS)

Summary

Introduction

Prostate cancer (PCa) is the most commonly diagnosed nonskin cancer and the second leading cause of cancer mortality in American men [1]. There are many factors that influence racial disparities in PCa, and a number of socioeconomic, cultural, and environmental factors have been identified [4,5,6,7,8]. Unequal access to health care, diet, age, lifestyle, and family history strongly affect the race-specific PCa incidence and mortality rates. Other factors, such as poverty, lack of education, stigma, and type and aggressiveness of treatment have been suggested as potential contributors to the disparity [9, 10]. Edward et al [14] reported that BRCA2 mutation is a potential risk factor associated with PCa incidences. Scott et al [15] showed a much higher rate of cytochrome c oxidase subunit I (COI) mutation present in AA individuals, indicating its importance in racial disparity for PCa

Methods

Results

Discussion

Conclusion