Genome-wide MicroRNA Expression Profiles in COPD: Early Predictors for Cancer Development

Abstract

Chronic obstructive pulmonary disease (COPD) significantly increases the risk of developing cancer. Biomarker studies frequently follow a case-control set-up in which patients diagnosed with a disease are compared to controls. Longitudinal cohort studies such as the COPD-centered German COPD and SYstemic consequences-COmorbidities NETwork (COSYCONET) study provide the patient and biomaterial base for discovering predictive molecular markers. We asked whether microRNA (miRNA) profiles in blood collected from COPD patients prior to a tumor diagnosis could support an early diagnosis of tumor development independent of the tumor type. From 2741 participants of COSYCONET diagnosed with COPD, we selected 534 individuals including 33 patients who developed cancer during the follow-up period of 54 months and 501 patients who did not develop cancer, but had similar age, gender and smoking history. Genome-wide miRNA profiles were generated and evaluated using machine learning techniques. For patients developing cancer we identified nine miRNAs with significantly decreased abundance (two-tailed unpaired t-test adjusted for multiple testing P < 0.05), including members of the miR-320 family. The identified miRNAs regulate different cancer-related pathways including the MAPK pathway (P = 2.3 × 10^-5). We also observed the impact of confounding factors on the generated miRNA profiles, underlining the value of our matched analysis. For selected miRNAs, qRT-PCR analysis was applied to validate the results. In conclusion, we identified several miRNAs in blood of COPD patients, which could serve as candidates for biomarkers to help identify COPD patients at risk of developing cancer.

Keywords: Biomarker; COPD; COSYCONET; Cancer; Lung; microRNA.

Figure 1

Experimental design We profiled individuals with COPD (blue) who either did not develop cancer (Cohort 1) or developed cancer (Cohort 2) during the 54-month follow-up. Genome-wide blood-borne miRNA profiles were generated for all 534 patients. These expression data were correlated with clinical data from the COSYCONET data repository using statistical approaches implemented in the programming environment R. COPD, chronic obstructive pulmonary disease; COSYCONET, COPD and SYstemic consequences-COmorbidities NETwork.

Figure 2

Volcano plots for the pair-wise comparison of patients developing cancer and patients not developing cancer Volcano plots show on the Y-axis the negative log₁₀P value of the t-test and on the Y-axis the log₂ fold change. Green dots indicate miRNAs with higher expression in blood samples from Cohort 1, while red dots represent miRNAs with higher expression in blood samples from Cohort 2 according to the raw P < 0.05. All dots with raw P ≥ 0.05 are colored in gray. The horizontal blue line separates miRNAs that are significant following Benjamini–Hochberg adjustment (above the line; adjusted P < 0.05) and miRNAs that are not significant anymore following the adjustment (below the line).

Figure 3

miRNA-target interaction network for the four core miRNAs The graphic shows for the four core miRNAs miR-320e, miR-517a-3p, miR-519d-3p, and miR-320c the joint target genes from the miRTarbase. miRNA nodes are colored in brown, genes targeted by two miRNAs are colored in blue and genes targeted by three miRNAs are colored in green.

Figure 4

Box-Whisker and Volcano plots for miRNAs including the information of a cancer history A. Box whisker plot for miR-150-5p for the four patient groups shown in Figure 1. Patients in Group 3 showed significantly decreased expression of miR-150-5p. B. Volcano plot for the two extreme groups: Group 1 and Group 4. Green dots indicate miRNAs with higher expression in blood samples from Group 1, while red dots represent miRNAs with higher expression in blood samples from Group 4 according to the unadjusted P < 0.05. All dots with unadjusted P ≥ 0.05 are colored in gray. The horizontal blue line separates miRNAs that are significant following Benjamini–Hochberg adjustment (above the line; adjusted P < 0.05) and miRNAs that are not significant anymore following the adjustment (below the line).

Figure 5

qRT-PCR validation of the expression of three miRNAs The graphic shows the CT values of expression in blood from patients developing cancer (n = 31) and those not developing cancer (n = 56) for the three miRNAs that were evaluated by qRT-PCR. * indicates significant difference in miRNA expression (P < 0.05; two-tailed t-test) between the two patient groups. n.s., non significant.