Maximizing CRISPR/Cas9 phenotype penetrance applying predictive modeling of editing outcomes in Xenopus and zebrafish embryos

Thomas Naert,Dieter Tulkens,Nicole A Edwards,Andy Willaert,Paul Coucke,Annekatrien Boel,Marjolein Carron,Kris Vleminckx,Nikko-Ideen Shaidani,Suzan Demuynck,Aaron M Zorn,Marcin Wlizla,Marko E Horb

doi:10.1038/s41598-020-71412-0

Abstract

CRISPR/Cas9 genome editing has revolutionized functional genomics in vertebrates. However, CRISPR/Cas9 edited F0 animals too often demonstrate variable phenotypic penetrance due to the mosaic nature of editing outcomes after double strand break (DSB) repair. Even with high efficiency levels of genome editing, phenotypes may be obscured by proportional presence of in-frame mutations that still produce functional protein. Recently, studies in cell culture systems have shown that the nature of CRISPR/Cas9-mediated mutations can be dependent on local sequence context and can be predicted by computational methods. Here, we demonstrate that similar approaches can be used to forecast CRISPR/Cas9 gene editing outcomes in Xenopus tropicalis, Xenopus laevis, and zebrafish. We show that a publicly available neural network previously trained in mouse embryonic stem cell cultures (InDelphi-mESC) is able to accurately predict CRISPR/Cas9 gene editing outcomes in early vertebrate embryos. Our observations can have direct implications for experiment design, allowing the selection of guide RNAs with predicted repair outcome signatures enriched towards frameshift mutations, allowing maximization of CRISPR/Cas9 phenotype penetrance in the F0 generation.

Highlights

CRISPR/Cas[9] genome editing has revolutionized functional genomics in vertebrates
We find that the InDelphi network that was trained on mouse embryonic stem cells is highly predictive for the CRISPR/Cas[9] editing outcomes in developing vertebrate embryos
The ratios of cells within the mosaic presenting with certain insertions and deletions (INDELs) variants is representative of the probabilistic outcomes of gene editing towards that specific mutation

Summary

Introduction

CRISPR/Cas[9] genome editing has revolutionized functional genomics in vertebrates. CRISPR/Cas[9] edited F0 animals too often demonstrate variable phenotypic penetrance due to the mosaic nature of editing outcomes after double strand break (DSB) repair. We believe that in many cases the inability to retrieve phenotypes in Xenopus and zebrafish F 0 CRISPR/Cas[9] edited animals is the consequence of in-frame mutations in a substantial number of cells in the mosaic mutant animal To circumvent this problem, targeting of gRNA to functional protein domains has been suggested and several tools have been released that allow actively integrating structural information in the gRNA design p rocess[20,21]. We find that the InDelphi network that was trained on mouse embryonic stem cells (mESC) is highly predictive for the CRISPR/Cas[9] editing outcomes in developing vertebrate embryos We rationalize this will allow to select gRNAs favoring frameshift gene editing outcomes prone to nonsense-mediated decay (NMD), thereby maximizing subsequent protein knock-out in CRISPR/Cas[9] animal models

Methods

Results

Conclusion