A framework for the detection of de novo mutations in family-based sequencing data

Abstract

Germline mutation detection from human DNA sequence data is challenging due to the rarity of such events relative to the intrinsic error rates of sequencing technologies and the uneven coverage across the genome. We developed PhaseByTransmission (PBT) to identify de novo single nucleotide variants and short insertions and deletions (indels) from sequence data collected in parent-offspring trios. We compute the joint probability of the data given the genotype likelihoods in the individual family members, the known familial relationships and a prior probability for the mutation rate. Candidate de novo mutations (DNMs) are reported along with their posterior probability, providing a systematic way to prioritize them for validation. Our tool is integrated in the Genome Analysis Toolkit and can be used together with the ReadBackedPhasing module to infer the parental origin of DNMs based on phase-informative reads. Using simulated data, we show that PBT outperforms existing tools, especially in low coverage data and on the X chromosome. We further show that PBT displays high validation rates on empirical parent-offspring sequencing data for whole-exome data from 104 trios and X-chromosome data from 249 parent-offspring families. Finally, we demonstrate an association between father's age at conception and the number of DNMs in female offspring's X chromosome, consistent with previous literature reports.

Figure 1

Outline of the pipeline used to generate our simulation data. The ‘mutation rate map' is the autosome-wide GoNL derived mutation rate map, as published before.

Figure 2

ROC plot showing the performance of PBT, where the mutation rate prior is used as the hidden parameter. Two scenarios are considered in order to evaluate the relevance of using allele frequency priors (yellow curve: without AF priors, green curve: with AF prior). The analysis is stratified by coverage (columns) and genomic region (rows). The y-scale for the 60x coverage plots is restricted for visibility. Each dot shape corresponds to a specific DNM prior. The allele frequency priors are computed based on 1000 Genomes Phase 3 CEU data.

Figure 3

ROC plot illustrating the performance of three DNM calling methods (PhaseByTransmission, TrioDeNovo and DeNovoGear), with respect to each method's DNM output confidence score. The analysis is stratified by coverage (columns) and genomic region (rows). The posterior cutoffs used for plotting each curve were uniformly distributed across the range of each tool's output DNM confidence scores. Some outlier values where the specificity decreased considerably without any sensitivity gain were removed from the plot and the x-scale for the 60x and 30x coverages is restricted, for visibility purpose. Supplementary Figure SF3 shows the curves with all points. The mutation rate prior values for each scenario, for each tool are selected based on Supplementary Figure SF1.

Figure 4

Fitted linear regression line (dark green) of the number of X chromosome DNMs, as a function of father's age at conception. The data points (blue) represent the set of 547 high confidence DNMs in female offspring. The coefficient estimate is an increase of 0.08 DNMs per year (on the X chromosome).