miRNAs in lung cancer - studying complex fingerprints in patient's blood cells by microarray experiments

Abstract

Background: Deregulated miRNAs are found in cancer cells and recently in blood cells of cancer patients. Due to their inherent stability miRNAs may offer themselves for blood based tumor diagnosis. Here we addressed the question whether there is a sufficient number of miRNAs deregulated in blood cells of cancer patients to be able to distinguish between cancer patients and controls.

Methods: We synthesized 866 human miRNAs and miRNA star sequences as annotated in the Sanger miRBase onto a microarray designed by febit biomed gmbh. Using the fully automated Geniom Real Time Analyzer platform, we analyzed the miRNA expression in 17 blood cell samples of patients with non-small cell lung carcinomas (NSCLC) and in 19 blood samples of healthy controls.

Results: Using t-test, we detected 27 miRNAs significantly deregulated in blood cells of lung cancer patients as compared to the controls. Some of these miRNAs were validated using qRT-PCR. To estimate the value of each deregulated miRNA, we grouped all miRNAs according to their diagnostic information that was measured by Mutual Information. Using a subset of 24 miRNAs, a radial basis function Support Vector Machine allowed for discriminating between blood cell samples of tumor patients and controls with an accuracy of 95.4% [94.9%-95.9%], a specificity of 98.1% [97.3%-98.8%], and a sensitivity of 92.5% [91.8%-92.5%].

Conclusion: Our findings support the idea that neoplasia may lead to a deregulation of miRNA expression in blood cells of cancer patients compared to blood cells of healthy individuals. Furthermore, we provide evidence that miRNA patterns can be used to detect human cancers from blood cells.

Figure 1

The bar-chart shows for 15 of the 27 deregulated miRNAs the median value of cancer samples and normal samples. Here, blue bars correspond to cancer samples while red bars to controls.

Figure 2

Back to back histograms of two examples. The color-coding corresponds to the one used in Figure 1.

Figure 3

Scatterplot of fold quotients of qRT-PCR (x-axis) and microarray experiments (y-axis).

Figure 4

The mutual information of all miRNAs that have higher information content than the best permutation test (upper red line). The middle red line denotes the 95% quantile of the 1000 permutation tests and the bottom red line the mean of the permutation experiments, corresponding to the background MI.

Figure 5

Venn diagrams for different analyses. A) Venn diagram of the t-test mirVANA and MPEA labeling. B) Venn diagram of the t-test and the Mutual Information. The right circle shows significant MI miRNAs, separated in the miRNAs that are higher than the highest permutation test and the miRNAs higher than 95% of all 1000 permutation tests. The 27 miRNAs are all included in these miRNAs, indicated by the green circle. C) Venn diagram of t-test miRNAs and miRNAs used in the best classification subset. The 24 miRNAs used for classification are all contained in the set of 27 most significant mRNAs

Figure 6

Boxplots of the classification accuracy, specificity, and sensitivity of the 100 repetitions of the 10-fold cross-validation (red boxes) and the same values for random permutation tests (blue boxes).