Integrated Genomic Characterization of Pancreatic Ductal Adenocarcinoma

Abstract

We performed integrated genomic, transcriptomic, and proteomic profiling of 150 pancreatic ductal adenocarcinoma (PDAC) specimens, including samples with characteristic low neoplastic cellularity. Deep whole-exome sequencing revealed recurrent somatic mutations in KRAS, TP53, CDKN2A, SMAD4, RNF43, ARID1A, TGFβR2, GNAS, RREB1, and PBRM1. KRAS wild-type tumors harbored alterations in other oncogenic drivers, including GNAS, BRAF, CTNNB1, and additional RAS pathway genes. A subset of tumors harbored multiple KRAS mutations, with some showing evidence of biallelic mutations. Protein profiling identified a favorable prognosis subset with low epithelial-mesenchymal transition and high MTOR pathway scores. Associations of non-coding RNAs with tumor-specific mRNA subtypes were also identified. Our integrated multi-platform analysis reveals a complex molecular landscape of PDAC and provides a roadmap for precision medicine.

Keywords: KRAS; PDAC; RPPA; TCGA; genomics; heterogeneity; miRNA; molecular subtypes; pancreatic cancer; tumor cellularity.

Figure 1. Landscape of genomic alterations in pancreatic ductal adenocarcinoma (PDAC)

Integrated genomic data for 149 non-hypermutated samples (columns), including: mutations (classified as truncating, in-frame or missense); high-level amplifications and homozygous deletions (“Deep Deletion”), fusions derived from analysis of mRNA data, and germline mutations for selected genes as described in the text. Overall number of mutations/Mb and clinicopathologic data for each sample are shown as tracks at the top. Significantly mutated genes (q ≤ 0.1) from exome sequencing data listed in order of q-value, followed by other recurrently altered genes organized in functional classes of oncogenes (red), DNA damage repair genes (green) and chromatin modification genes (blue). Significantly mutated genes from these classes are also colored accordingly. The percentage of PDAC samples with an alteration of any type is noted at the left. See also Figure S1, Tables S1–S3.

Figure 2. KRAS mutational heterogeneity

(A–C) Histogram of cancer cell fraction (CCF) estimates (X-axis) for all identified mutated genes (Y-axis, blue bars) as well as point estimates and 95% confidence intervals for selected genes (colored horizontal lines) for a tumor (YB-A89D) with clonal KRAS^G12R mutation and clonal CDKN2A and SMAD4 mutations but also harboring a second apparent subclone with a KRAS^G12D and TP53 mutation (A), a tumor (XD-AAUG) with a clonal KRAS^G12V mutation and a subclonal KRAS^Q61H mutation (B), and a tumor (RB-A7B8) with a clonal KRAS^G12R mutation, a subclonal KRAS^G12V mutation, and a clonal GNAS mutation (C). (D) Schematic model of the tumor shown in (C) based on CCF evidence for biallelic KRAS mutations in a subset of cells. (E) Tumor (2J-AAB1) with CCF evidence of multiple subclonal KRAS alterations in the same tumor. (F) Schematic model of the tumor shown in (E) with evidence for multiple subclones, each harboring a different KRAS mutation. See also Figure S2.

Figure 3. Alternate drivers in KRAS wild-type samples

(A) Co-mut plot for KRAS wild-type tumors (n = 10) displaying integrated data including mutations, copy number alterations, mRNA fusions and germline alterations as described in Figure 1. (B–D) Recurrently mutated GNAS (B), CTNNB1 (C) and BRAF (D) observed in KRAS wild-type samples. (E) Focal high-level amplification of ERBB2 in a KRAS wild-type sample. Red dotted lines indicate the boundaries of the amplicon. Chromosome position and ABSOLUTE copy number (CN) are indicated on the X- and Y-axes, respectively. Genes positioned within the genomic locus are indicated below. (F) RPPA scores for TSC/MTOR pathway in samples with KRAS mutation (blue), BRAF mutation (brown), or wild-type for both KRAS and BRAF (red). Column scatter plots show mean with standard deviation. Mann-Whitney rank-sum test, p = 0.0007. See also Table S4

Figure 4. Assessment and impact of purity on molecular analysis

(A) Box plots show estimated tumor purity distributions determined by three methods for all 150 tumors. Dot plots embedded within the box plots show purity estimates for the 74 low-purity (red, purity below median) and 76 high-purity (blue, purity above median) samples used for supervised analyses. (B) Workflow of the two-stage approach for supervised clustering of 74 low purity samples using tumor-specific groups identified in the 76 high-purity samples. (C-E) Box plots of ABSOLUTE tumor purity for samples classified using the published mRNA signatures from Moffitt et al. (C), Collisson et al. (D), and Bailey et al. (E). (F) Sample overlap for mRNA subtypes from Bailey et al., Collisson et al., or Moffitt et al. (from inside to outside, respectively); DNA methylation estimated leukocyte fraction; and high/low purity based on ABSOLUTE. (a) Overlap between samples classified as ‘pancreatic progenitor’ (Bailey et al) ‘classical’ (Collisson et al.) and ‘classical’ (Moffitt et al.) mRNA subtypes. (b) Overlap between samples classified ‘squamous’ (Bailey et al.) and ‘basal-like’ (Moffitt et al.) mRNA subtypes. (c) squamous and progenitor are overrepresented in the high purity samples. (d) ADEX is a subset of exocrine-like. (e) Leukocyte fraction is elevated in Immunogenic samples, especially those also classified as quasimesenchymal. All box plots shown display full range, median, and upper and lower quartiles. See also Figures S3 and Table S5.

Figure 5. Unsupervised clustering and differential abundance for miRNAs and lncRNAs, for 76 high-purity tumours

(A) Heatmap of row-scaled, log₁₀-transformed normalized expression for miRNA 5p and 3p mature strands (miRs) that were abundant and also differentially abundant across three consensus clusters computed using unsupervised non-negative matrix factorization clustering (NMF) (Cancer Genome Atlas Research, 2014; Gaujoux and Seoighe, 2010). Below the heatmap (top to bottom): a profile of silhouette width calculated from the consensus membership matrix (W_cm), clinical or molecular covariates with Fisher exact p values, mutation calls for significantly mutated genes, and a profile of ABSOLUTE purity (Carter et al., 2012), with a Kruskal-Wallis p value. Only p < 0.15 are shown. (B) Distributions of normalized abundance (RPM) for a subset of miRs that were scored as highly differentially abundant in a SAM multiclass analysis, or were differentially abundant (FDR < 0.05) and are known to be associated with cancers. (C, D) Results of a 2-cluster consensus clustering solution (Wilkerson and Hayes, 2010) for a subset of highly-variant lncRNAs presented similar to what shown in (A) and (B) respectively. All box plots shown display median values, and the 25th to 75th percentile, while whiskers extend up to 1.5 times the interquartile range. All data points are shown as individual dots. See also Figure S4 and Table S6.

Figure 6. RPPA profiles identify biologically distinct subsets of high purity tumors

(A) Unsupervised consensus clustering of RPPA protein expression data for 45 of the 76 high-purity samples. (B) Cox survival analysis between clusters (p = 0.045, likelihood ratio test from Cox analysis with purity as covariate). (C) Differences in proteomic pathway activity scores across RPPA cluster/class for several pathway scores defined in (Akbani et al., 2014). Box plots indicate the median, upper and lower quartiles, with whiskers extending 1.5 times the interquartile range. Points indicate pathway scores for all 45 samples. See also Table S7.

Figure 7. Integrated analysis

(A) Integrated clustering of methylation, miRNA, lncRNA, and mRNA data using Similarity Network Fusion (SNF) on high purity samples. (B) Network fusion diagram of the two integrated clusters: each node is a sample, with node color indicating SNF cluster and node size proportional to ABSOLUTE purity. Edges are colored according to the datatype giving the strongest similarity between patients. Nodes positioned in between the top and bottom clusters generally have lower purity, reflecting the weaker signal for molecular classification. (C) DNA methylation heat map and overlapping tracks sorted by GATA6 expression. (D) CDKN2A status in all 150 cases showing mutation, deletion, or methylation in a subset of tumors. (E) Network of selected relationships between miRNA, lncRNA, mRNA, and methylation sites observed in the high purity samples, with edges indicating significant anti-correlations. Validated and predicted miRNA:mRNA associations from external sources are colored per legend. (F) Relationship of the expression of mir-192-5p with nearby DNA methylation and expression of CAV1, a predicted target of mir-192-5p. All box plots shown display full range, median, and upper and lower quartiles. See also Figures S5 and Table S8.