iProMix: A Mixture Model for Studying the Function of ACE2 based on Bulk Proteogenomic Data

Abstract

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused over six million deaths in the ongoing COVID-19 pandemic. SARS-CoV-2 uses ACE2 protein to enter human cells, raising a pressing need to characterize proteins/pathways interacted with ACE2. Large-scale proteomic profiling technology is not mature at single-cell resolution to examine the protein activities in disease-relevant cell types. We propose iProMix, a novel statistical framework to identify epithelial-cell specific associations between ACE2 and other proteins/pathways with bulk proteomic data. iProMix decomposes the data and models cell type-specific conditional joint distribution of proteins through a mixture model. It improves cell-type composition estimation from prior input, and uses a nonparametric inference framework to account for uncertainty of cell-type proportion estimates in hypothesis test. Simulations demonstrate iProMix has well-controlled false discovery rates and favorable powers in nonasymptotic settings. We apply iProMix to the proteomic data of 110 (tumor-adjacent) normal lung tissue samples from the Clinical Proteomic Tumor Analysis Consortium lung adenocarcinoma study, and identify interferon $\alpha /\gamma$ response pathways as the most significant pathways associated with ACE2 protein abundances in epithelial cells. Strikingly, the association direction is sex-specific. This result casts light on the sex difference of COVID-19 incidences and outcomes, and motivates sex-specific evaluation for interferon therapies. Supplementary materials for this article are available online.

Keyword:

• ACE2
• Cell type-specific association
• COVID-19
• Mixture model
• Proteomics

Supplementary Materials

Supplementary Figures S1–S6 and proof of the identifiability of Θ in the proposed model.

Acknowledgments

This work was supported by the National Institute of Health under grants 5U24CA210993, R03AG075567, U24CA271114, R01CA237541 and P30CA196521.

Data Availability Statement

The iProMix procedure was implemented in the R package iProMix, which is publicly available at https://github.com/songxiaoyu/iProMix.

Disclosure Statement

The authors report there are no competing interests to declare.

Additional information

Funding

The authors gratefully acknowledge National Institute of Health grants 5U24CA210993, R03AG075567, U24CA271114, R01CA237541, and P30CA196521