Exome and whole-genome sequencing of esophageal adenocarcinoma identifies recurrent driver events and mutational complexity

Abstract

The incidence of esophageal adenocarcinoma (EAC) has risen 600% over the last 30 years. With a 5-year survival rate of ~15%, the identification of new therapeutic targets for EAC is greatly important. We analyze the mutation spectra from whole-exome sequencing of 149 EAC tumor-normal pairs, 15 of which have also been subjected to whole-genome sequencing. We identify a mutational signature defined by a high prevalence of A>C transversions at AA dinucleotides. Statistical analysis of exome data identified 26 significantly mutated genes. Of these genes, five (TP53, CDKN2A, SMAD4, ARID1A and PIK3CA) have previously been implicated in EAC. The new significantly mutated genes include chromatin-modifying factors and candidate contributors SPG20, TLR4, ELMO1 and DOCK2. Functional analyses of EAC-derived mutations in ELMO1 identifies increased cellular invasion. Therefore, we suggest the potential activation of the RAC1 pathway as a contributor to EAC tumorigenesis.

Figure 1. Prominent frequencies of A>C transversions at AA sites identified from whole genome sequencing are observed in less-expressed regions of the genome

a) “Lego” plots of mutation frequencies across 16 WGS samples for all sequenced territory (left) and exons only (right). Base substitutions are divided into six categories to represent the six possible base changes (each category represented by a different color). Substitutions are further subdivided by the 16 possible flanking nucleotides surrounding the mutated base as listed in “trinucleotide context” legend (X, Z). The inset pie chart indicates the distribution of all mutations for a given middle mutated base across the territory being evaluated. A>C transversions at AA dinucleotides are denoted with an asterisk (*). b) Gene expression was detected from Affymetrix U133 Plus 2 arrays on per sample basis for 14 WGS samples. Mutation frequencies within the introns and exons (y-axis) were calculated as number of mutations detected in per million at-risk bases sequenced for a mutation category. Mutation frequencies as they vary by gene expression (with genes binned into quartiles based on gene expression) are plotted separately for all mutations and for AA transversions. c) The frequency of mutation (number of mutations per million bases at risk for mutation) within intronic and exonic regions are plotted with frequencies separated based upon whether the base at risk is present on the transcribed or non-transcribed strands. For the AA transversions, the mutation frequency is calculated separately for the case of at-risk adenine bases when present on the coding or non-coding strands compared to similar analysis for all other mutations. P-values were calculated by Student’s T-test. All error bars represent S.D.

Figure 2. Mutation frequencies and significantly mutated genes in esophageal adenocarcinoma as identified by WES

a) Mutation frequency of a cohort of 149 primary esophageal adenocarcinomas is sorted by the fraction of mutations consisting of A > C transversions at AA sites. MSI-positive samples labeled in dark gray were not included in mutation significance analysis. b) Key clinical parameters described in Supplementary Table 1. c) Center; mutations in significantly mutated genes, colored by the type of coding mutation. Each column denotes an individual tumor and each row represents a gene. Left; number and percentage of samples with mutations in a given gene. Gray bar represents number of AA transversions in a gene. Right, the negative log of the q values for the significance level of mutated genes is shown for all genes with FDR q < 0.1.

Figure 3. Recurrent somatic alterations in ELMO1, DOCK2, and other RAC1 Guanine Nucleotide Exchange Factors (GEFs)

a) Schematic of protein alterations in DOCK2 and ELMO1 detected by WES. Coding alterations in EAC are colored either black (missense) or red (splice site/nonsense); silent mutations are depicted in gray. Conserved domain mapping is from UniProt; SH3, SRC Homology 3; DHR, Dlg homologous region, ELMO, Engulfment and Cell Motility; PH, Pleckstrin homology. b) Sample frequency (left) of candidate ELMO1 and DOCK2 as well as other Rac1-activating guanine nucleotide exchange factors in 145 WES EACs. c) ELMO1 wild-type or mutants (or GFP control) were expressed in NIH/3T3 cells using retroviral transduction with the pBabe vector. Cells were plated in matrigel invasion chambers with full serum containing medium in the lower chamber only, and invading cells from four fields were counted. Invading cells of 3 independent replicates are shown. Error bars represent S.D. P-values compare mutant ELMO1 to wild-type. n.s., not significant. Student’s t-test.

Figure 4. Somatic alterations in frequently altered pathways in cancer, putative therapeutic targets, and treatment biomarkers

a) Potential therapeutic targets or treatment biomarkers are listed by sample. Each column denotes an individual tumor and each row represents a gene. Mutations are colored by the type of mutation event, and genes with amplification of greater than four copies relative to a diploid baseline are marked by red box.

Figure 5. Genetic alterations identified by WES across 145 EACs impacting the WNT/CTNNB1 (β-catenin), RTK/RAS/PI(3)K, TGFB1 (TGF-β)/SMAD4, Chromatin Remodeling Enzyme, RB1, and p53 pathways

Percentages represent number of mutations in a given gene across the cohort. Genes that are predicted to be gain-of-function and loss-of-function are depicted in red and blue, respectively. Frequencies of alteration by mutation or copy-number alteration are shown. Color density of red or blue is based on mutation frequency of a given gene. Genes marked with an asterisk are significant by MutSig analysis. Genes subject to significant focal gain or loss in EAC have copy-number frequency marked in bold.