Protein-nucleic acid language model-assisted design of precise and compact adenine base editor

Adenine base editors (ABEs) are powerful tools for gene therapy. However, efficient version of ABEs (e.g. ABE8e) always induce excessive bystander and off-target editing events and are large in size, hindering their potential in clinical disease treatment. Here, we develop a pre-trained Protein-Nucleic Acid Constrained Language Model to design ABE8e with high activity, reduced editing window and decreased size. By further engineering, the smallest ABE8e- PNLM-pcABE- with a 27% size reduction, exhibits high activity, precise 3-nt editing window, and reduced off-target events near background level in HEK293T cells. Compared to ABE8e, PNLM-pcABE has up to 133.5-fold precision improvement in pathogenic mutation correction. By PNLM-pcABE, the albino mouse model carrying desired base mutation is nearly 100% obtained via zygotes microinjection and the expression of PCSK9 substantially decreases in mice receiving in vivo delivery with lipid nanoparticle (LNP), indicating their great potential in gene therapy and disease modeling.