Frequent mutation of histone-modifying genes in non-Hodgkin lymphoma

Abstract

Follicular lymphoma (FL) and diffuse large B-cell lymphoma (DLBCL) are the two most common non-Hodgkin lymphomas (NHLs). Here we sequenced tumour and matched normal DNA from 13 DLBCL cases and one FL case to identify genes with mutations in B-cell NHL. We analysed RNA-seq data from these and another 113 NHLs to identify genes with candidate mutations, and then re-sequenced tumour and matched normal DNA from these cases to confirm 109 genes with multiple somatic mutations. Genes with roles in histone modification were frequent targets of somatic mutation. For example, 32% of DLBCL and 89% of FL cases had somatic mutations in MLL2, which encodes a histone methyltransferase, and 11.4% and 13.4% of DLBCL and FL cases, respectively, had mutations in MEF2B, a calcium-regulated gene that cooperates with CREBBP and EP300 in acetylating histones. Our analysis suggests a previously unappreciated disruption of chromatin biology in lymphomagenesis.

Figure 1. Genome-wide visualization of somatic mutation targets in NHL

Overview of structural rearrangements and copy number variations (CNVs) in the 11 DLBCL genomes and cSNVs in the 109 recurrently mutated genes identified in our analysis. Inner arcs represent somatic fusion transcripts identified in one of the 11 genomes. The CNVs and LOH detected in each of the 11 DLBCL tumour/normal pairs are displayed on the concentric sets of rings. The inner 11 rings show regions of enhanced homozygosity plotted with blue (interpreted as LOH). The outer 11 rings show somatic CNVs. Purple circles indicate the position of genes with at least two confirmed somatic mutations with circle diameter proportional to the number of cases with cSNVs detected in that gene. Circles representing the genes with significant evidence for positive selection are labelled. Coincidence between recurrently mutated genes and regions of gain/loss are colour-coded in the labels (green=loss, red=gain). For example B2M, which encodes beta-2-microglobulin, is recurrently mutated and is deleted in two cases.

Figure 2. Overview of mutations and potential cooperative interactions in NHL

This heat map displays possible trends towards co-occurrence (red) and mutual exclusion (blue) of somatic mutations and structural rearrangements. Colours were assigned by taking the minimum value of a left- and right-tailed Fisher exact test. To capture trends a P-value threshold of 0.3 was used, with the darkest shade of the colour indicating those meeting statistical significance (P <=0.05). The relative frequency of mutations in ABC (blue), GCB (red), unclassifiable (black) DLBCLs and FL (yellow) cases is shown on the left. Genes were arranged with those having significant (P<0.05, Fisher exact test) enrichment for mutations in ABC cases (blue triangle) towards the top (and left) and those with significant enrichment for mutations in GCB cases (red triangle) towards the bottom (and right). The total number of cases in which each gene contained either cSNVs or confirmed somatic mutations is shown at the top. The cluster of blue squares (upper-right) results from the mutual exclusion of the ABC-enriched mutations (e.g. MYD88, CD79B) from the GCB-enriched mutations (e.g. EZH2, GNA13). Presence of structural rearrangements involving the two oncogenes BCL6 and BCL2 (indicated as BCL6s and BCL2s) was determined with FISH techniques utilizing break-apart probes (Methods).

Figure 3. Summary and effect of somatic mutations affecting MLL2 and MEF2B

(A) Re-sequencing the MLL2 locus in 89 samples revealed mainly nonsense (red circles) and frameshift-inducing indel mutations (orange triangles). A smaller number of non-synonymous somatic mutations (green circles) and point mutations or deletions affecting splice sites (yellow stars) were also observed. All of the non-synonymous point mutations affected a residue within either the catalytic SET domain, the FYRC domain (“FY-rich C-terminal domain”) or PHD zinc finger domains. The effect of these splice site mutations on MLL2 splicing was also explored (Supplementary Figure S7). (B) The cSNVs and somatic mutations found in MEF2B in all FL and DLBCL cases sequenced are shown with the same symbols. Only the amino acids with variants in at least two patients are labelled. cSNVs were most prevalent in the first two protein coding exons of MEF2B (exons 2 and 3). The crystal structure of MEF2 bound to EP300 supports the idea that two of the mutated sites (L67 and Y69) are important in the interaction between these proteins (Supplementary Figure S8; Supplementary Discussion).