Experimental microdissection enables functional harmonisation of pancreatic cancer subtypes

Abstract

Objective: Pancreatic ductal adenocarcinoma (PDA) has among the highest stromal fractions of any cancer and this has complicated attempts at expression-based molecular classification. The goal of this work is to profile purified samples of human PDA epithelium and stroma and examine their respective contributions to gene expression in bulk PDA samples.

Design: We used laser capture microdissection (LCM) and RNA sequencing to profile the expression of 60 matched pairs of human PDA malignant epithelium and stroma samples. We then used these data to train a computational model that allowed us to infer tissue composition and generate virtual compartment-specific expression profiles from bulk gene expression cohorts.

Results: Our analysis found significant variation in the tissue composition of pancreatic tumours from different public cohorts. Computational removal of stromal gene expression resulted in the reclassification of some tumours, reconciling functional differences between different cohorts. Furthermore, we established a novel classification signature from a total of 110 purified human PDA stroma samples, finding two groups that differ in the extracellular matrix-associated and immune-associated processes. Lastly, a systematic evaluation of cross-compartment subtypes spanning four patient cohorts indicated partial dependence between epithelial and stromal molecular subtypes.

Conclusion: Our findings add clarity to the nature and number of molecular subtypes in PDA, expand our understanding of global transcriptional programmes in the stroma and harmonise the results of molecular subtyping efforts across independent cohorts.

Keywords: pancreatic cancer.

Figure 1.. Compartment–specific gene expression profiling of pancreatic tumors

(A) Images of Cresyl Violet stained human PDA frozen sections before and after laser capture microdissection of malignant epithelial and adjacent stromal cells. (B) RIN values for RNA samples derived from the indicated compartment (N = 60 each). (C) Number of genes and transcripts detected at >1 FPKM in the samples from (B). (D) Principal component analysis of the 60 paired epithelial and stromal LCM expression profiles from (C). Color graduation shows pairing of samples from the same tumor. Three samples discussed later are labeled. (E) Heatmap showing the expression of marker genes for epithelial cells (Epi.), endothelial cells (Endo.), cancer associated fibroblasts (CAF) and immunocytes (Imm). (F, G) Protein validation of genes predicted as epithelium–specific (F) or stroma–specific (G) based on mRNA expression. Bar height and color shading reflect the certainty (t-statistic) of differential expression. The box color below each bar summarizes results of immunohistochemistry on PDA sections from the Human Protein Atlas (HPA). IHC staining pattern was categorized as strongly or weakly supportive of the predicted compartment (blue/red), indeterminate (grey), absent (white), or opposite the predicted pattern (black). (H) An example epithelium–specific gene, LGALS4, showed a protein staining pattern that was strongly consistent with its mRNA expression (at left). Blue and red arrows indicate PDA epithelium and stroma, respectively. (I) LGALS1 exhibited a highly stroma-specific expression pattern.

Figure 2.. Analysis and classification of pancreatic tumor cohorts and classifiers

(A) Tumor and stroma content analysis of pancreatic tumors from the ICGC (blue), UNC (red), and TCGA (grey) cohorts. (B) Analysis of gene expression across 60 pairs of PDA epithelium and stroma LCM-RNA-seq profiles, highlighting the genes used to determine each subtype from the Collisson, Moffitt, and Bailey classifiers. Top panel displays the compartment– specificity of the signature genes for each subtype based on the t-statistic of their differential expression between PDA epithelium and stroma samples; positive values indicate stromal enrichment. Lower panel depicts the average expression of each signature genes across all LCM-RNA-seq samples, in fragments per million mapped fragments (FPM). (C) Heatmap depicting the differential expression of indicated marker genes in deconvolved virtual epithelial (veTCGA) and stromal (vsTCGA) profiles from the TCGA cohort. (D) Epithelial fraction of TCGA pancreatic tumors allocated to the Basal-like (red) and Classical (blue) subtypes based on analysis of either bulk or virtual epithelial expression profiles. (E, F) Analysis of gene sets associated with the Moffitt Basal-like (red) and Classical (blue) subtypes based in bulk expression profiles (E) from TCGA versus virtual epithelial profiles (F) of the same tumors. Heatmap depicts gene set variance analysis (GSVA) scores per sample for indicated gene sets. Stratification of bulk TCGA profiles using the Moffitt classifier results in groups that are not differentially enriched in the gene sets classically associated with Basal-like versus Classical subtypes. However, following deconvolution the virtual epithelial profiles stratify into two groups that reflect the functional biology of the Basal-like and Classical subtypes.

Figure 3.. Systematic stromal subtyping of PDA

(A–D) Heatmaps of the top 30 DEG between groups obtained by clustering stromal LCM– RNA–Seq samples from CUMC tumors (A), and virtual stromal (vs) profiles from the UNC (B), ICGC (C) and TCGA (D) cohorts, respectively. Clustering was based on the expression of a signature derived from stromal LCM profiles from 110 individual patients (CUMC-S classifier, see Supplementary Methods). Top section of heat-map depicts GSVA scores per sample for indicated gene sets. In each virtual stroma dataset, two groups were identified, one with features indicating elevated extracellular matrix deposition and remodeling (“ECM– rich”, purple) and another enriched in various immune and interleukin pathways (“Immune-rich”, green). (E–G) Multilayered donut plots showing (i) the alignment of epithelial with stromal subtypes for each tumor in each cohort and (ii) the proportion of each epithelial subtype. Separate pie charts summarize the proportion of stromal subtypes per cohort.

Figure 4.. Combined epithelial and stromal subtypes associate with overall survival

Kaplan-Meier (KM) survival analysis of patients with resected PDA from the ICGC (n= 93), TCGA (n= 137), or UNC (n= 125) cohorts, stratified by the indicated signatures applied to either bulk expression profiles (thin lines) or transcriptionally deconvolved versions of the same (thick lines). Below each KM plot, horizontal bars indicate the hazard ratios (HR) from a Cox proportional hazards model (CPHM), along with their 80% (blue), 90% (yellow) and 95% (orange) confidence intervals. (A-C) KM plot of patients from the indicated cohorts using the Moffitt-E signature to stratify Basal-like (red) versus Classical (blue) tumors, showing that the detection of a differential prognosis among the epithelial subtypes is generally enhanced by transcriptional deconvolution. Bars indicate HR for Basal-like tumors in virtual epithelial and bulk profiles. (D-F) KM plot of patients from the indicated cohorts using the CUMC–S signature to stratify ECM-rich (purple) versus Immune-rich (green) tumor. Kaplan-Meier (KM) survival analysis depicts overall survival relative to stromal subtype. Stromal subtypes are statistically associated with outcome in the ICGC cohort with ECM-rich tumors having a worse prognosis. Bars indicate HR for ECM-rich tumors in virtual stromal and bulk profiles. (G-I) KM plot of patients from the indicated cohorts using a combination of the Moffitt–E and CUMC– S signatures. Red lines indicate Basal-like tumors with an ECM-rich stroma while blue lines indicate Classical tumors with an Immune-rich stroma; all other tumors are represented as a grey line. Bars indicate HR for Basal-like::ECM-rich tumors in bulk and virtual epithelial/stroma (ves) profiles.