Exome sequencing of pleuropulmonary blastoma reveals frequent biallelic loss of TP53 and two hits in DICER1 resulting in retention of 5p-derived miRNA hairpin loop sequences

Abstract

Pleuropulmonary blastoma is a rare childhood malignancy of lung mesenchymal cells that can remain dormant as epithelial cysts or progress to high-grade sarcoma. Predisposing germline loss-of-function DICER1 variants have been described. We sought to uncover additional contributors through whole exome sequencing of 15 tumor/normal pairs, followed by targeted resequencing, miRNA analysis and immunohistochemical analysis of additional tumors. In addition to frequent biallelic loss of TP53 and mutations of NRAS or BRAF in some cases, each case had compound disruption of DICER1: a germline (12 cases) or somatic (3 cases) loss-of-function variant plus a somatic missense mutation in the RNase IIIb domain. 5p-Derived microRNA (miRNA) transcripts retained abnormal precursor miRNA loop sequences normally removed by DICER1. This work both defines a genetic interaction landscape with DICER1 mutation and provides evidence for alteration in miRNA transcripts as a consequence of DICER1 disruption in cancer.

Figure 1

Matrix of frequent copy-number alterations and significantly mutated genes derived from exome sequence data in each case. Cases are in columns and genetic alterations are in rows with events color-coded as indicated. The loss-of-function category includes nonsense, splice-site, insertion and deletion mutations. Copy-neutral LOH refers to chromosome- or arm-level loss-of-heterozygosity without a change in copy number (for example, loss of the chromosome containing the wild-type allele and duplication of the chromosome containing the mutant allele), as shown in Figure 3.

Figure 2

Location of somatic mutations and germline variants in significantly mutated genes. Protein domains are as annotated from the UniProt record indicated under each gene name. Somatic mutations are indicated by black text above the protein model, whereas germline variants are indicated by green text below the protein model. Mutations detected in the extension cohort using targeted resequencing are included in the counts of somatic DICER1 mutations.

Figure 3

Somatic chromosome 14 copy-number segments and allele fractions of variants heterozygous in matched normal. Data points are the tumor allele fractions of heterozygous, non-reference alleles in the matched normal sample. Somatic deletion of the non-reference allele results in tumor allele fractions near 0, whereas gain of the non-reference base or deletion of the reference base results in values approaching 1. Colored bars represent copy-number states inferred from fractional coverage values. Each panel depicts different combinations of copy-number alteration and loss-of-heterozygosity detected by whole exome sequencing. (a) Copy quiet: Compound germline loss-of-function (LOF) and somatic RNase IIIb missense mutation without further copy-number alteration (nine cases). (b) Wild-type deletion: Deletion of wild-type allele resulting in hemizygosity for the somatic RNase IIIb missense mutation (PPB_11). (c) Trisomy: Copy-number gain of chromosome 14 resulting in duplication of RNase IIIb mutant allele and retention of germline LOF allele (two cases). An additional case has duplication of the germline LOF allele and retention of the RNase IIIb mutant allele (PPB_5). (d) Chromosomal copy neutral loss-of-heterozygosity: Copy-neutral loss of wild-type allele and duplication of entire chromosome 14 containing the somatic RNase IIIb missense mutation (PPB_15). (e) Arm-level copy neutral loss-of-heterozygosity: Copy-neutral loss of wild-type allele and duplication of 14q containing the somatic RNase IIIb missense mutation (PPB_13).

Figure 4

(a) Relative expression level of 5p- and 3p-derived miRNAs in 5 normal lung and 28 PPB tissues as measured by total microarray intensities. Normal tissues (black) had higher expression of 5p miRNA compared with 3p miRNA, whereas all PPBs (red) appeared to have lower overall expression of 5p miRNAs compared with normal tissues. (b–d) The fraction of reads with start and end points confined to functional units of 1595 miRNA primary transcripts. 5p and 3p Regions as annotated by miRbase build 19. Hairpin loop regions were defined as the genome segment between 5p and 3p regions. 5p+Loop+3p denotes reads that include 5p, loop and 3p sequence (that is, precursor miRNAs). The fraction of reads corresponding to these regions in each miRNA individually is provided as Supplementary Figure 6 and Supplementary Table 9. (b) In normal tissues, reads were primarily derived from mature 5p and 3p miRNAs sequenced, with higher expression from 5p miRNA compared with 3p miRNA, consistent with the microarray data. (c) In addition to skewed ratio of 5p and 3p miRNA expression compared with normal tissues, primary PPB tissue had increased fraction of reads containing 5p and loop sequences (5p+loop), and full-length, pre-miRNAs (5p+loop+3p) (Supplementary Figure 4). (d) Owing to the presumed depletion of normal cells, the presence of extended 5p miRNAs and pre-miRNAs is even clearer in a PPB cell line derived from the tissue displayed in (c).