Systematic characterization of mutations altering protein degradation in human cancers

Abstract

The ubiquitin-proteasome system (UPS) is the primary route for selective protein degradation in human cells. The UPS is an attractive target for novel cancer therapies, but the precise UPS genes and substrates important for cancer growth are incompletely understood. Leveraging multi-omics data across more than 9,000 human tumors and 33 cancer types, we found that over 19% of all cancer driver genes affect UPS function. We implicate transcription factors as important substrates and show that c-Myc stability is modulated by CUL3. Moreover, we developed a deep learning model (deepDegron) to identify mutations that result in degron loss and experimentally validated the prediction that gain-of-function truncating mutations in GATA3 and PPM1D result in increased protein stability. Last, we identified UPS driver genes associated with prognosis and the tumor microenvironment. This study demonstrates the important role of UPS dysregulation in human cancer and underscores the potential therapeutic utility of targeting the UPS.

Figure 1.. Study Overview.

Somatic mutations from 33 cancer types in The Cancer Genome Atlas (TCGA) (left) were analyzed to reveal significantly mutated genes in the Ubiquitin-Proteasome System (UPS) and its substrates with a significant enrichment of mutations at known degron-related sites (middle). A machine learning model, deepDegron (bottom right), was then used to find additional degron sites and to implicate the impact of additional mutations. Lastly, leveraging the significantly mutated genes in the UPS pathway, we associated UPS pathway genes with protein abundance or inferred activity of transcription factors to implicate putative substrates (top right).

Figure 2.. Landscape of cancer driver genes in the Ubiquitin-Proteasome System (UPS).

(A) Driver gene analysis was performed by the 20/20+ method. Scatter plot for each UPS gene (dots) is shown with the maximum oncogene (OG) score (x-axis) and maximum tumor suppressor gene (TSG) score (y-axis) across 33 cancer types and a pan-cancer analysis. Red indicates the gene was found to be statistically significant in at least one analysis. (B) Fraction of putative cancer driver genes which occur in the UPS pathway (red bar). Dashed line indicates the median across all analyses. (C) Venn diagram that shows the overlap of putative cancer driver genes in this study (20/20+) with previous studies: TCGA PancanAtlas consortium, ubiquitin pathway analysis by Ge et al., Davoli et al., and of a curated list of cancer driver genes, in general, from the Cancer Gene Census (CGC). (D) Pie diagram displaying the percentage of UPS driver genes in terms of molecular function. (E) Lollipop diagram of CUL3 mutations in Head and Neck squamous cell carcinoma in TCGA. Exon-exon junctions are displayed as dashed lines. Color of circles distinguishes the type of mutation, while colored rectangles are uniprot domain annotations of the protein. (F) Kaplan-meier curves of the relationship between UCHL1 expression and overall patient survival in 4 melanoma datasets. (G) Lollipop diagram of UCHL1 mutations in TCGA skin cutaneous melanoma cohort. Numbered circles indicate a mutation was found in more than one tumor. See also Figure S1

Figure 3.. Somatic mutations are enriched at known degron sites.

(A) Heatmap displaying genes that are enriched for mutations either at literature annotated degron sites (Meszaros et al., 2017), ubiquitination sites (PhosphositePlus), or phosphodegrons (PhosphoSitePlus). Red indicates significant enrichment (q<0.1) for a given gene (y-axis) and cancer type (x-axis) in TCGA. (B) Lollipop diagram of CCND1 mutations in Uterine Corpus Endometrial Carcinoma (UCEC) in TCGA. (C) Boxplots showing the association of CCND1 mutations with Cyclin D1 protein abundance (p=4e-8, Wald test) and a marker of cell cycle progression (MKI67, p=0.003) in UCEC. Heatmap shows t-statistics of the association, after adjustment for RNA expression and tumor subtype. Tumor subtypes: CN_LOW=copy number low; MSI=microsatellite instable; POLE=POLE mutated. RPPA=Reverse Phase Protein Arrays. See also Figure S2

Figure 4.. deepDegron accurately predicts the impact of primary sequence on protein stability.

(A) Performance of deepDegron at predicting the stability of C-terminal peptides from the Global Protein Stability (GPS) assay according to the area under the Receiver Operating Characteristic curve (AUC; maximum=1.0, random=0.5) (see “deepDegron data set” in STAR methods). (B) ROC curve for the N-terminal peptide GPS assay. (C) Diagram showing that the degron potential score is computed based on the difference between a deepDegron model that uses the position of the amino acids versus one that does not (“Bag of Amino Acids”). (D) Sequence logo visualizations of select motifs identified by deepDegron (q<0.05, binomial test, Methods). (E) DeepDegron predicted change in degron potential (delta degron potential) for various mutations of the C-terminal peptide encoded by CHGA. (F) Correlation between the change in degron potential and the protein stability index according to a saturation mutagenesis study of CHGA. (G) GPS stability measurements of C-terminal (top) or N-terminal (bottom) peptides derived from the indicated genes, comparing wild-type (gray histograms) and double mutant (red) sequences. X-axis is proportional to GFP / DsRed signal as measured by flow cytometry (see STAR methods); Y-axis is normalized cell count. See also Figure S3 and S4

Figure 5.. deepDegron finds C-terminal degrons disrupted by mutations in cancer.

(A) Scatter plot showing the results of the mutational enrichment for C-end degron loss across all analyses (33 cancer types and pan-cancer). P-value resolution is limited to 0.0001. (B) Example of GATA3 in breast cancer, which shows that the change in degron potential (red) is considerably more negative than the background model (blue). (C) Lollipop diagram of TCGA mutations in GATA3 for breast cancer. Colored rectangles are Zinc Finger domain 1 (ZnF1) and 2 (ZnF2). (D) Boxplot showing the association of GATA3 mutations with GATA3 protein abundance in TCGA breast cancer (top left). (E) Western blot of the protein expression of GATA3 mutants compared to control. F=FLAG tag. (F) Top, average read coverage profile for peaks. Bottom, overlap of up-regulated ChIP-seq peaks for GATA3 mutants. (G) Pathway enrichment analysis of up-regulated peaks for GATA3 mutants. (H) Distribution of expression for genes nearby up-regulated peaks stratified by tumor subtype. (I) Western blot showing the impact of mutating the GATA3 degron on markers for luminal and basal-like breast cancer. (J) Western blot analysis of PPM1D (WIP1) mutant versus control. HA=hemagglutinin tag. See also Figure S5

Figure 6.. UPS-substrate inference finds association with markers of tumor immune microenvironment.

(A) Diagram depicting the strategy for associating UPS genes with putative transcription factor substrates. (B) Scatterplot showing the significance of each transcription factor (TF) association for a particular UPS genes (x-axis). (C) Diagram of inferred substrate relationships of KEAP1 and CUL3. (D) Western blot showing the co-immunoprecipitation of CUL3 with c-Myc. (E) Western blot showing increased c-Myc protein abundance in CUL3 KO cells. (F) Quantification of c-Myc protein half-life upon CUL3 KO in Cal27 and Cal33 cells. Cycloheximide (CHX), a protein translation inhibitor, was given at a concentration of 100 μg/ml. Errorbar = +/− 1 SEM. (G) Enrichment analysis for degron motifs in associated TF’s for 4 E3 ubiquitin ligases that have a previously reported degron motif (Fisher’s exact test). (H) Heatmap displaying the association (t statistic) of mutations in UPS driver genes with 5 immune-related biomarkers * = FDR<0.1. (I) Z-score measuring the relative abundance of cancer cells with a gene knockout when they are co-cultured with T cells, where negative values indicate sensitivity to T cell killing. See also Figure S6 and S7