Genetic and Functional Drivers of Diffuse Large B Cell Lymphoma

Abstract

Diffuse large B cell lymphoma (DLBCL) is the most common form of blood cancer and is characterized by a striking degree of genetic and clinical heterogeneity. This heterogeneity poses a major barrier to understanding the genetic basis of the disease and its response to therapy. Here, we performed an integrative analysis of whole-exome sequencing and transcriptome sequencing in a cohort of 1,001 DLBCL patients to comprehensively define the landscape of 150 genetic drivers of the disease. We characterized the functional impact of these genes using an unbiased CRISPR screen of DLBCL cell lines to define oncogenes that promote cell growth. A prognostic model comprising these genetic alterations outperformed current established methods: cell of origin, the International Prognostic Index comprising clinical variables, and dual MYC and BCL2 expression. These results comprehensively define the genetic drivers and their functional roles in DLBCL to identify new therapeutic opportunities in the disease.

Keywords: DLBCL; TCGA; The Cancer Genome Atlas; diffuse large B cell lymphoma; exome sequencing; genetic mutations.

Figure 1. The landscape of genetic drivers in 1001 DLBCLs

A. The mutational heatmap indicates the most recurrently altered genes in 1001 DLBCL cases with frequency >5%, color-coded by four genetic alteration types: missense mutation (yellow), copy number gain (red), truncating mutation (green), and copy number loss (blue). To the right of the mutational heatmap, the stacked bargraph indicates the gene-level alteration type breakdown using the same four-color scheme. B. Clinical features of the corresponding 1001 patients are indicated below the mutational heatmap, including the International Prognostic Index (IPI) score, response to therapy (complete response or not), activated B cell-like (ABC) vs. germinal center B cell-like (GCB) DLBCL subtype, and gender. See also Figure S1, S2, Table S1.

Figure 2. ABC/GCB based classification of DLBCL

A. RNAseq gene expression classifier distinguishes Germinal Center B cell-like DLBCL (GCB), Unclassified DLBCL (UC), Activated B cell-like DLBCL (ABC). B. Comparison of RNAseq subtype score vs. the NanoString linear predictor score (top) using (Pearson’s correlation R²=0.87, p<10⁻⁶) and by immunohistochemistry Hans GCB vs. Non-GCB classification (Wilcoxon test p<10⁻⁶) (bottom). C. Genetic alterations that are enriched in ABC vs. GCB DLBCL (Fisher’s test FDR<0.1). D. Network of genes with statistically significant (p<0.01) overlap or co-occurrence (red edges) and mutational exclusion (blue edges). Stronger associations are indicated with thicker and darker colored lines between nodes (p<0.001). Genes significantly enriched in GCB or ABC DLBCL are colored in green and orange respectively, or grey otherwise. See also Table S2.

Figure 3. Defining the functional role of genetic drivers through CRISPR screen

A. Schematic of CRISPR screen performed for six cell lines in triplicate. B. A ranked list of CRISPR scores for the 19,032 genes targeted in the screen. Illustrative driver genes are shown in blue (likely oncogenes) or red (likely tumor suppressor genes). C. CRISPR scores for 35 DLBCL oncogenes are shown alongside the frequency of genetic alterations and functional group. See also Figure S3, Table S3

Figure 4. Integrative analysis of gene expression, genetic alterations and outcome

A. Schematic depicting the integrative analysis. B. Heatmap of expression of significantly correlated geneset exemplars across DLBCL samples (N=625). C. Heatmap of fold-change associations of significant genetic alterations with genesets exemplars. Fold-changes for significant associations (ANOVA test p<0.05) are shown in yellow-purple color scales, while insignificant associations are colored grey. D. (Left) Enrichment of CRISPR hits within the cluster exemplar gene sets (Fisher’s test p<0.05). (Right) Survival association with cluster exemplar signature (logrank test, p<0.05). See also Table S4.

Figure 5. Genomic risk model stratifies DLBCL survival

A. Overall survival of 1001 DLBCL cases, cases stratified by IPI groups, ABC/GCB DLBCL, MYC & BCL2 expression. B. Hazard ratios and 95% confidence intervals of selected survival-associated genetic alterations (p<0.05). C. Schematic depicting multivariate survival modeling. D. Combinations of genetic and expression features that comprise the genomic risk model in DLBCL patients. E. Survival of the predicted risk groups in the test set (logrank test, p=8×10⁻⁵). F. Cross validation performance of the genomic risk model compared to that with only genetic alterations (DNA-only), and gene expression (RNA-only). G. The genomic risk model significantly stratifies survival within known risk groups (logrank test) See also Figure S5, Table S5.

Figure 6. Comparison of clinical risk model (IPI) with genomic risk model

A. Comparison of hazard ratios (high vs. low risk groups) and 95% confidence intervals for various DLBCL risk models, including our genomic risk model. B. The matrix of Kaplan-Meier survival plots indicates risk stratification by clinical risk model (IPI) vs. genomic risk model for all patients and patients stratified by minimum overall survival of 1, 3, and 5 years (logrank test). C. Survival plot for response to initial therapy (logrank test, p<10⁻⁶). D. Prediction of response to initial therapy using clinical risk model (left) and genomic risk model (right) (chi-squared test). E. Survival plots showing the stratification of genomic and clinical risk models for each of the individual responses to therapy (logrank test).