Exome sequencing reveals pathogenic mutations in 91 strains of mice with Mendelian disorders

Abstract

Spontaneously arising mouse mutations have served as the foundation for understanding gene function for more than 100 years. We have used exome sequencing in an effort to identify the causative mutations for 172 distinct, spontaneously arising mouse models of Mendelian disorders, including a broad range of clinically relevant phenotypes. To analyze the resulting data, we developed an analytics pipeline that is optimized for mouse exome data and a variation database that allows for reproducible, user-defined data mining as well as nomination of mutation candidates through knowledge-based integration of sample and variant data. Using these new tools, putative pathogenic mutations were identified for 91 (53%) of the strains in our study. Despite the increased power offered by potentially unlimited pedigrees and controlled breeding, about half of our exome cases remained unsolved. Using a combination of manual analyses of exome alignments and whole-genome sequencing, we provide evidence that a large fraction of unsolved exome cases have underlying structural mutations. This result directly informs efforts to investigate the similar proportion of apparently Mendelian human phenotypes that are recalcitrant to exome sequencing.

Figure 1.

Phenotypic distribution of spontaneous mutant strains in the study. The cohort of mutant strains selected for exome sequencing represents various phenotypes that have an observable common characteristic during the course of normal breeding and husbandry. System level or tissue level mammalian phenotype (MP) terms were assigned on the basis of primary phenotypes. Phenotypes are arranged clockwise from largest to smallest group and similarly from top to bottom in the key.

Figure 2.

Distribution of pathogenic mutation types (A) and the value of chromosomal linkage (B) for mutation discovery in spontaneous mouse models of Mendelian disease. Pathogenic mutations consisted of a variety of lesions, the majority of which were single nucleotide substitutions. Due to ascertainment bias, copy number variants and structural mutations (>50 bp) were more rare (A). Chromosomal linkage data had a significant impact on the validation burden and a potential for false positive mutation calls. The largest effect (two orders of magnitude) was on potentially low-impact (modifier) variant calls. Variant calls were categorized by predicted impact according to SnpEff impact annotations (B) (see Methods and Supplemental File 4).

Figure 3.

Graphical view of alignments across Tshr (A), Myo5a (B), and Wnt7a (C). Graphical views of the alignments were generated using the Integrative Genomics Viewer (IGV) and RefSeq exon annotations are shown. In each case, split reads (arrow) span the junctions of copy number variations and structural rearrangements. In Tshr, a cluster of four single nucleotide variants (SNVs) with unexpected allele frequencies of 0.3–0.63 was called in a homozygous sample; three of the four SNVs were soft filtered as a SNP cluster by GATK. Manual analysis of the alignment revealed a homozygous deletion in the final exon of this gene (A). In another example, a heterozygous SNV was called in a splice donor site of myosin VA (Myo5a) in a sample. In the alignment surrounding the SNV call there were split reads, as well as flagged reads (B, colored reads) with mates mapping throughout the genome, providing evidence of a retroviral or intra-cisternal A-particle (IAP) insertion in exon 3 (B). In a third example, a SNV call was flagged by our algorithm as a mutation candidate but could not be validated due to multiple failed PCR assays. The SNV was in wingless-related MMTV integration site 7a (Wnt7a) in an affected sample from a pedigree with recessive skeletal abnormalities. Manual analysis of the alignment surrounding the SNV call revealed two clusters of flagged reads flanking an ∼23-kb region, spanning intron 3, the 5′ splice site, and a portion of exon 3. Moreover, there was zero coverage across exon 3 and the 5′ splice site of intron 3, regions that are normally covered by WES (C).