MicroRNA molecular profiling identifies potential signaling pathways conferring resistance to chemoradiation in locally-advanced rectal adenocarcinoma

Abstract

Purpose: There has been growing interest in using chemoradiation (CRT) for non-operative management of rectal cancer, and identifying patients who might benefit most from this approach is crucial. This study identified miRNAs (miRs) associated with clinical outcomes and treatment resistance by evaluating both pre- and post-CRT expression profiles.

Methods: Forty patients, 9 with pathologic complete response (pCR) and 31 with pathologic incomplete response (pIR) were included. MicroRNA was extracted from 40 pre-therapy tumor samples and 31 post-chemoradiation surgical samples with pathologic incomplete response (pIR). A generalized linear model was used to identify miRs associated with pCR. A linear mixed effects model was used to identify miRs differentially expressed before and after treatment. miR expression was dichotomized at the mean and clinical outcomes were evaluated using Cox proportional hazard modeling.

Results: Nine miRs were associated with pCR (p<0.05), but none were significant after false discovery rate correction. Among patients with pIR, 68 miRs were differentially expressed between the pre and post-CRT groups (FDR p<0.05). Ingenuity pathway analysis (IPA) demonstrated multiple signaling networks associated with pIR, including p38MAPK, TP53, AKT, IL-6, and RAS. Increased let-7b was correlated with increased distant metastasis (DM), worse relapse-free survival (RFS), and worse overall survival (OS) (p<0.05).

Conclusions: No miRs were significantly correlated with pCR. We identified miRs that were differentially expressed between pre- and post-CRT tumor samples, and these miRs implicated multiple signaling pathways that may confer resistance to CRT. In addition, we identified an association between increased let-7b and worse clinical outcomes (DM, DFS, OS).

Keywords: biomarker; chemotherapy; miRNA; radiation; rectal cancer.

Figure 1. Multi-dimensional scaling of pre-therapy and post-therapy samples for miRNA molecular profiling

(A) Histogram displaying filtering of samples based on missing probes. We removed 5 patient samples (to the right of the red line) based on >60% missing probes. (B) Density distribution of miRNAs (n=168) for each patient sample before (left) and after (right) normalization. Normalization standardizes the mean and smooths distribution of miRNAs (bandwidth= 0.445). (C) Multi-dimensional scaling (MDS) of pre-therapy miR profiles in patients with pCR (green or “CR”) and pre-therapy miR profiles in patients with pIR (black, “A samples”). As observed, there is no significant separation in pre-therapy profiles between pCR and pIR patients. Distances on the plot demonstrate the log2-fold changes between the samples. (D) Multi-dimensional scaling (MDS) of pre-therapy miR profiles in patients pIR (black, “A samples”) and post-therapy miR profiles in patients with pIR (red or “B samples”). A significant separation is observed between pre-therapy and post-therapy miR profiles in pIR patients. and post-therapy miR profiles in patients with pIR.

Figure 2. Heat map of differentially expressed miRNAs between pre-therapy and post-therapy tumor samples in patients with pIR

68 miRNAs were identified (bottom axis) using a linear mixed effect model analysis (using FDR<0.05). The red colors indicate higher expression for a particular miRNA, while the green colors represent lower expression. The black line divides the patient samples between pre-therapy (above black line, “A” samples) and post-therapy (below black line, “B” samples) samples. For example, miR-4286 is predominantly green in pre-therapy samples and red in post-therapy samples, indicating a significant increase in expression in post-therapy samples. miRNA expression values are normalized to the average value (0) using z-score normalization methods, where over-expression of a particular miR is shown in red, no change shown in white, and under-expression shown as green.

Figure 3. Volcano plot displaying differentially expressed miRNAs between pre-therapy to post-therapy tissues

miRNAs higher in post-treatment samples (right side) and miRNAs lower in post-treatment samples (left side) are shown. miRNAs that were significantly differentially expressed after FDR correction (p<0.05) are shown as red squares. In addition, miRNAs that had a FDR p-value<10⁻⁴ are labeled. X axis depicts log₂ expression fold change, while Y axis depicts log₁₀ FDR p-value.

Figure 4. Ingenuity Pathway Analysis (IPA) of miRNAs differentially expressed between pre-therapy and post-therapy tumor samples from patients with pIR

(A) Network #1 demonstrates potential associations between these miRNAs and p38 MAPK, Ras, MAP2K1/2, and Smad family proteins. (B) Network #2 demonstrates potential associations between these miRNAs and IL-6, ERBB2, E2F1, and CDKN2A. (C) Network #3 is a more stringent analysis of only miRs with an FDR <10⁻⁴, and included molecules such as TP53, ZEB2, Smad3, and Bcl6.

Figure 5. Kaplan-Maier survival plots for let-7b

Higher pre-therapy levels of let-7b are associated with worse DMFS (A), RFS (C), and OS (D). No statistically significant relationship between pre-therapy let-7b levels and LRC was found (B).