Modeling insertional mutagenesis using gene length and expression in murine embryonic stem cells

Abstract

Background: High-throughput mutagenesis of the mammalian genome is a powerful means to facilitate analysis of gene function. Gene trapping in embryonic stem cells (ESCs) is the most widely used form of insertional mutagenesis in mammals. However, the rules governing its efficiency are not fully understood, and the effects of vector design on the likelihood of gene-trapping events have not been tested on a genome-wide scale.

Methodology/principal findings: In this study, we used public gene-trap data to model gene-trap likelihood. Using the association of gene length and gene expression with gene-trap likelihood, we constructed spline-based regression models that characterize which genes are susceptible and which genes are resistant to gene-trapping techniques. We report results for three classes of gene-trap vectors, showing that both length and expression are significant determinants of trap likelihood for all vectors. Using our models, we also quantitatively identified hotspots of gene-trap activity, which represent loci where the high likelihood of vector insertion is controlled by factors other than length and expression. These formalized statistical models describe a high proportion of the variance in the likelihood of a gene being trapped by expression-dependent vectors and a lower, but still significant, proportion of the variance for vectors that are predicted to be independent of endogenous gene expression.

Conclusions/significance: The findings of significant expression and length effects reported here further the understanding of the determinants of vector insertion. Results from this analysis can be applied to help identify other important determinants of this important biological phenomenon and could assist planning of large-scale mutagenesis efforts.

Figure 1. Diagram of major mechanisms of gene trapping of an endogenous gene with two exons.

(A) In the SA-trap, the SA site allows trapping when inserted into any part of the gene via plasmid or viral integration. (B) The poly-A trap relies on the poly-A (pA) of the endogenous gene because the neomycin-resistance gene does not have a poly-A tail. Note that the poly-A trap has its own constitutive promoter (prom). Also indicated are the splice donor (SD), splice acceptor (SA), and neomycin resistance (NeoR). The major components of each trap were excluded from this diagram to emphasize on the essential elements needed to understand the trapping models. Detailed maps of each major vector type are referenced in the Methods section.

Figure 2. Trapped genes by length and expression.

For each vector type, genes were plotted according to their size and level of expression in ESCs. Genes that have been trapped are shown in red. The circle size is proportional to the number of times a gene has been trapped.

Figure 3. Models of trap likelihood for gene-trap vectors.

Models of the likelihood of trapping a gene with particular length (x-axis) and expression (y-axis) values for each gene-trap event were created through an iterative process, in which outliers (P<0.001) were removed before the final model was created. Probability (z-axis) is given as events per million traps.