Predicting adenine base editing efficiencies in different cellular contexts by deep learning
In conclusion, our work confirms that adenine base editing holds considerable potential for correcting a large fraction of pathogenic mutations. We also provide BEDICT2.0 - a robust computational model that helps identify sgRNA-ABE combinations capable of achieving high on-target editing with minimal bystander effects in both in vitro and in vivo settings.
Authors
- Gerald Schwank (ORCID: https://orcid.org/0000-0003-0767-2953)
- Michael Krauthammer (ORCID: https://orcid.org/0000-0002-4808-1845)
- Amina Mollaysa
- Kim Fabiano Marquart (ORCID: https://orcid.org/0000-0001-7393-4398)
- Paulo J.C. Lin
- Nicolas Mathis (ORCID: https://orcid.org/0000-0002-4051-8344)
- Sharan Janjuha (ORCID: https://orcid.org/0000-0002-5910-2912)
- Steven H.Y. Fan
- Ahmed Allam (ORCID: https://orcid.org/0000-0003-0871-1977)
- Ying K. Tam (ORCID: https://orcid.org/0000-0002-4083-5251)
- Norbert Pardi (ORCID: https://orcid.org/0000-0003-1008-6242)
- Yanik Weber (ORCID: https://orcid.org/0000-0002-0914-8541)
- Hiromi Muramatsu (ORCID: https://orcid.org/0000-0003-1544-1493)
- Máté Vadovics (ORCID: https://orcid.org/0000-0001-9028-987X)
- Lucas Kissling (ORCID: https://orcid.org/0000-0002-4989-0695)
- Woohyun J Moon
Institutions
- University of Zurich (CH)
- ETH Zurich (CH)
- Acuitas Therapeutics (Canada) (CA)
- University of Pennsylvania (US)
Publication Details
- Journal
- Genome biology
- Published
- 2025-05-08
- DOI
- https://doi.org/10.1186/s13059-025-03586-7
- Citations
- 3
- Primary Topic
- CRISPR and Genetic Engineering
- Type
- article
- Field-Weighted Citation Impact
- 2.42
Funders
- National Science Foundation
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung
- Université de Genève
- National Institutes of Health
- Staatssekretariat für Bildung, Forschung und Innovation
- Functional Genomics Center Zurich
- National Institute of Allergy and Infectious Diseases