Splicing profile by capture RNA-seq identifies pathogenic germline variants in tumor suppressor genes

Abstract

Germline variants in tumor suppressor genes (TSGs) can result in RNA mis-splicing and predisposition to cancer. However, identification of variants that impact splicing remains a challenge, contributing to a substantial proportion of patients with suspected hereditary cancer syndromes remaining without a molecular diagnosis. To address this, we used capture RNA-sequencing (RNA-seq) to generate a splicing profile of 18 TSGs (APC, ATM, BRCA1, BRCA2, BRIP1, CDH1, CHEK2, MLH1, MSH2, MSH6, MUTYH, NF1, PALB2, PMS2, PTEN, RAD51C, RAD51D, and TP53) in 345 whole-blood samples from healthy donors. We subsequently demonstrated that this approach can detect mis-splicing by comparing splicing profiles from the control dataset to profiles generated from whole blood of individuals previously identified with pathogenic germline splicing variants in these genes. To assess the utility of our TSG splicing profile to prospectively identify pathogenic splicing variants, we performed concurrent capture DNA and RNA-seq in a cohort of 1000 patients with suspected hereditary cancer syndromes. This approach improved the diagnostic yield in this cohort, resulting in a 9.1% relative increase in the detection of pathogenic variants, demonstrating the utility of performing simultaneous DNA and RNA genetic testing in a clinical context.

Keywords: Cancer genetics; Genetic testing; Next-generation sequencing.

Fig. 1. Splicing landscape of 18 TSGs in healthy controls.

a–c Histogram of control samples by ethnicity, age, and gender. d Violin plot indicating median number of splicing events detected at ≥5% PSI with coverage ≥50× for each reported ethnicity. T test p values between neighboring distributions are shown. All other pairwise t test p values were also non-significant (data not shown). e Hierarchical clustering of PSI for splicing events with PSI >1 in at least 150 individuals, assigning PSI to zero if no event was called. Samples (columns) are labeled by batch, age range, gender, and ethnicity.

Fig. 2. Healthy controls’ alternative splicing events detected in TSG.

a Boxplot indicating median number of splicing events across controls with ≥5% PSI and coverage ≥50× for each hereditary cancer predisposition gene tested. b–g Plots indicating frequency (bar graph) and median PSI with interquartile range (boxplot) for alternative splicing events with PSI ≥5 in ≥5% of controls (17/345 controls). For each gene, alternative splicing events are divided into in-frame and frameshift transcripts. Splicing events are as follows: ES = exon skipping—a combination of a full and partial exon skipping event, ESF = full exon skipping—the entire length of the exon is skipped, ESP = partial exon skipping—some portion of the exon is skipped (i.e., alternative acceptor/donor), IC = cryptic exon—an intronic insertion (split reads on 5′ and 3′ end), IP = partial intronic insertion—an extension of the exon into the intron either upstream (5′) or downstream (3′) of the exon. b–d Hereditary breast and ovarian cancer genes (BRCA1/BRCA2/ATM), e NF1, and f, g colorectal/polyposis genes’ (APC/MUTYH) alternative splicing events.

Fig. 3. Splicing profiling can detect mis-splicing in individuals carrying germline likely pathogenic/pathogenic variants.

a Plot comparing PSI of alternative splicing event associated with the given pathogenic (red) or variant likely pathogenic (VLP; blue) germline DNA variant obtained from proband against median PSI and interquartile range for that splicing event in controls, excluding samples in which the splicing event was not detected (black boxplot; outlier points are not shown). If the event was not found in controls, only the proband PSI was plotted. All PSI values were significantly higher than the mean control PSI (one-sample two-sided t test, p < 1 × 10⁻⁵⁵). For CDH1 r.1055_1137del, the PSI values of 20 and 27 were observed in individuals with the pathogenic variant c.1137 + 1delG and the PSI value of 33 was observed in an individual with the VLP c.1057G > A. b–g Sashimi plot indicating reads supporting alternative splicing obtained via CloneSeq for HBOC (b, c), HNPCC (d, e), and HDGC (hereditary diffuse gastric cancer)/FAP (f, g) variants. b Partial skipping of CDS6 in PALB2. c Partial skipping of CDS2 in ATM. d Full skipping of CDS18 in MLH1. e Partial retention of intron 7 in MSH2. f Full skipping of CDS2 in APC. g Partial skipping of CDS16 in CDH1.

Fig. 4. Pathogenic variants identified in a consecutive cohort of 1000 patients analyzed by paired DNA and RNA genetic testing.

All PSI values shown were significantly higher than the mean control PSI (one-sample two-sided t test, p < 1 × 10⁻⁵⁵). a PSI for variant-associated r dot, shown in red, compared to boxplot representing median and interquartile range of PSI for healthy controls, if applicable (outlier points are not shown). b Sashimi plot of BRCA1 r. r.80_81ins81-8_81-1 indicating coverage and junction reads supporting the 8 bp partial intronic insertion. Patient plot is tuna-colored, whereas control plot is salmon colored. c Sashimi plot of BRCA1 r.5075_5152del indicating coverage and junction reads supporting the coding exon 16 skipping. d Sashimi plot of BRCA2 r.426_475del indicating coverage and junction reads supporting the coding exon 4 skipping. e Sashimi plot of ATM r.8269_8418del indicating coverage and junction reads supporting the coding exon 56 skipping. f Sashimi plot of ATM r.3061_3077del indicating coverage and junction reads supporting the partial skipping of coding exon 19. g Sashimi plot of MUTYH r.576_577ins577-4_577-1 indicating coverage and junction reads supporting the partial intron 7 retention. h Sashimi plot of PMS2 r.11_23del indicating coverage and junction reads supporting the partial skipping of coding exon 1.