A novel approach for characterizing microsatellite instability in cancer cells

Abstract

Microsatellite instability (MSI) is characterized by the expansion or contraction of DNA repeat tracts as a consequence of DNA mismatch repair deficiency (MMRD). Accurate detection of MSI in cancer cells is important since MSI is associated with several cancer subtypes and can help inform therapeutic decisions. Although experimental assays have been developed to detect MSI, they typically depend on a small number of known microsatellite loci or mismatch repair genes and have limited reliability. Here, we report a novel genome-wide approach for MSI detection based on the global detection of insertions and deletions (indels) in microsatellites found in expressed genes. Our large-scale analyses of 20 cancer cell lines and 123 normal individuals revealed striking indel features associated with MSI: there is a significant increase of short microsatellite deletions in MSI samples compared to microsatellite stable (MSS) ones, suggesting a mechanistic bias of repair efficiency between insertions and deletions in normal human cells. By incorporating this observation into our MSI scoring metric, we show that our approach can correctly distinguish between MSI and MSS cancer cell lines. Moreover, when we applied this approach to primal tumor samples, our metric is also well consistent with diagnosed MSI status. Thus, our study offers new insight into DNA mismatch repair system, and also provides a novel MSI diagnosis method for clinical oncology with better reliability.

Figure 1. An outline of the study (a) MSI characterization pipeline used in this study (b) Definition of PI and PD.

PI refers to the proportion of insertions in microsatellites over all insertions, and PD refers to the proportion of deletions in microsatellites over all deletions.

Figure 2. Indel counts from RNA-Seq.Y axis shows the number of samples.

(a) HapMap samples (b) cancer cell lines.

Figure 3. Proportions of microsatellite indels in different regions of transcripts.

(a) Coding sequences (b) 3′UTR (c) 5′UTR (d) Non-coding RNA.

Figure 4. Cumulative distribution of microsatellite indel lengths for cancer cell lines and HapMap samples.

(a) Microsatellite deletions (b) Microsatellite insertions.

Figure 5. MSI-seq index correctly reflects the MSI statuses of samples.

(a) Comparison between the PI/PD ratios of HapMap samples, MSI cancer cell lines and MSS cancer cell lines (b) PI/PD ratios for all HapMap samples and cancer cell lines. HapMap samples’ PI/PD ratios are represented by the empirical distribution density curve. The ratios for known cell lines are plotted in red vertical lines. Known MSS cell lines are plotted in blue, and all the other cell lines are plotted in purple.

Figure 6. Expression levels of MMR genes shown in FPKM values for MSI/MSS cell lines.

Values are normalized by the mean value of each column.

Figure 7. PI/PD ratios for paired tumor and normal samples from colon cancer patients.

14 are diagnosed as MSI and 14 are diagnosed as MSS.