A Compendium of Co-regulated Protein Complexes in Breast Cancer Reveals Collateral Loss Events

Abstract

Protein complexes are responsible for the bulk of activities within the cell, but how their behavior and abundance varies across tumors remains poorly understood. By combining proteomic profiles of breast tumors with a large-scale protein-protein interaction network, we have identified a set of 285 high-confidence protein complexes whose subunits have highly correlated protein abundance across tumor samples. We used this set to identify complexes that are reproducibly under- or overexpressed in specific breast cancer subtypes. We found that mutation or deletion of one subunit of a co-regulated complex was often associated with a collateral reduction in protein expression of additional complex members. This collateral loss phenomenon was typically evident from proteomic, but not transcriptomic, profiles, suggesting post-transcriptional control. Mutation of the tumor suppressor E-cadherin (CDH1) was associated with a collateral loss of members of the adherens junction complex, an effect we validated using an engineered model of E-cadherin loss.

Keywords: E-cadherin; breast cancer; cancer; driver gene mutations; post-transcriptional control; protein complexes; proteogenomics; proteomics.

Graphical abstract

Figure 1

BrCa-Core Complex Discovery (A) An integrated protein-protein interaction network is combined with tumor proteomic profiles to identify sets of densely connected proteins that display correlated expression profiles across tumor proteomes. By comparing the results with those derived from randomly relabeled protein interaction networks, we can estimate the false discovery rate (FDR). The BrCa-Core set contains 285 complexes at an estimated FDR of 10%. (B) BrCa-Core 17: the COP9 signalosome. The heatmap on the right shows protein expression of all subunits across 77 breast tumor proteomes. These have been sorted based on the mean abundance of all subunits. (C) BrCa-Core 14: the conserved oligomeric Golgi (COG) complex. (D) BrCa-Core 47 contains the ORC2–5 complex found in CORUM with the addition of LRWD1. (E) BrCa-Core 25, the COPI complex. (F) BrCa-Core 48, the EARP complex with the recently identified EARP interactor TSSC1. (G) BrCa-Core 26, the Commander complex.

Figure 2

Subtype-Specific Complex Expression (A) Heatmap displaying protein expression levels of specific BrCa-Core complexes. Tumor samples are grouped according to subtype (using IHC markers), indicated on top of the heatmap. Genes are grouped into specific complexes indicated on the right of the heatmap. Shown are the expression levels taken from Tyanova et al., 2016 (used for validation). These expression levels have been normalized such that the maximum expression level is 1 and minimum is 0. Heatmap for the discovery dataset (Mertins et al., 2016) is shown in Figure S2A. Complexes differentially expressed in specific subtypes are highlighted with boxes colored to match the subtype they are differentially expressed in. (B) Boxplots displaying the subtype-specific protein expression levels of selected subunits of the COPI complex (BrCa-Core 25) in the Tyanova et al. dataset (top) and TCGA dataset (bottom). These boxplots show median and interquartile range and are colored according to sample subtype (matching Figure 2A).

Figure 3

Subunit Loss Is Associated with a Reduction in Protein Complex Expression (A) Model displaying a potential series of events; mutation or deletion of one subunit is associated with reduced protein abundance of that subunit and potentially a reduction in expression of the entire complex. (B) Mutation or deletion of EXOC2 is associated with a reduction in protein abundance of the exocyst complex (BrCa-Core 27). Boxplots display the protein abundance of different subunits partitioned according to EXOC2 status. Each boxplot shows the median and interquartile range. Genes marked with a star indicate those whose proteomic abundance is significantly lower (one-sided Mann-Whitney test, p < 0.05) in samples with EXOC2 mutation/deletion. (C) CDH1 mutation is associated with a reduction in protein expression of an adherens junction complex (BrCa-Core 30). Legend as for (B).

Figure 4

E-cadherin Loss Is Associated with Reduced Expression of an Adherens Junction Complex (A) In tumor samples, CDH1 mutation is associated with a decrease in mRNA and protein expression of CDH1 but only of protein expression for CTNNA1 and CTNNB1. All expression and RPPA measurements are Z scores. Boxplots show median and interquartile range. p values calculated using a Mann-Whitney test. mRNA measurements for all three genes were available for 992 tumors, RPPA data for CDH1, and CTNNB1 were available for 760 tumors, while RPPA data for CTNNA1 were available for only 64 tumors. (B) Protein expression measured in a pair of isogenic MCF7 cell lines that differ by CDH1 status. Shown are the log2 label-free quantification intensities. p values are calculated using a two-sided heteroscedastic t test.