Protein language models-assisted optimization of a Uracil-N glycosylase variant enables programmable T-to-S base editing

Current base editors use DNA deaminases, including cytidine deaminase in cytidine base editor (CBE) or adenine deaminase in adenine base editor (ABE), to facilitate transition nucleotide substitutions. Combining CBE or ABE with glycosylase enzymes can induce limited transversion mutations. Nonetheless, a critical demand remains for base editors capable of generating alternative mutation types, such as T>G corrections. In this study, we leveraged pre-trained protein language models to optimize a uracil-N-glycosylase (UNG) variant with altered specificity for thymines (eTDG). Notably, after two rounds of testing fewer than 50 top-ranking variants, more than 50% exhibited over 1.5-fold enhancement in enzymatic activities. When eTDG was fused with nCas9, it induced programmable T-to-S (G/C) substitutions and corrected db/db diabetic mutation in mice (up to 55%). Our findings not only establish orthogonal strategies for developing novel base editors, but also demonstrate the capacities of protein language models for optimizing enzymes without extensive task-specific training data. To develop a novel transversion base editors, we harness UNG variants to create orthogonal transversion base editors (CGBE and TSBE) independent of deaminases. We also developed a strategy based on protein language models and optimized an enhanced Uracil N-glycosylase variant with specificities toward thymines (eTDG).