SumoPred-PLM: human SUMOylation and SUMO2/3 sites Prediction using Pre-trained Protein Language Model.

SUMOylation is an essential post-translational modification system with the ability to regulate nearly all aspects of cellular physiology. Three major paralogues SUMO1, SUMO2 and SUMO3 form a covalent bond between the small ubiquitin-like modifier with lysine residues at consensus sites in protein substrates. Biochemical studies continue to identify unique biological functions for protein targets conjugated to SUMO1 versus the highly homologous SUMO2 and SUMO3 paralogues. Yet, the field has failed to harness contemporary AI approaches including pre-trained protein language models to fully expand and/or recognize the SUMOylated proteome. Herein, we present a novel, deep learning-based approach called SumoPred-PLM for human SUMOylation prediction with sensitivity, specificity, Matthew's correlation coefficient, and accuracy of 74.64%, 73.36%, 0.48% and 74.00%, respectively, on the CPLM 4.0 independent test dataset. In addition, this novel platform uses contextualized embeddings obtained from a pre-trained protein language model, ProtT5-XL-UniRef50 to identify SUMO2/3-specific conjugation sites. The results demonstrate that SumoPred-PLM is a powerful and unique computational tool to predict SUMOylation sites in proteins and accelerate discovery.

Stimulation of CRISPR-mediated homology-directed repair by an engineered RAD18 variant.

Precise editing of genomic DNA can be achieved upon repair of CRISPR-induced DNA double-stranded breaks (DSBs) by homology-directed repair (HDR). However, the efficiency of this process is limited by DSB repair pathways competing with HDR, such as non-homologous end joining (NHEJ). Here we individually express in human cells 204 open reading frames involved in the DNA damage response (DDR) and determine their impact on CRISPR-mediated HDR. From these studies, we identify RAD18 as a stimulator of CRISPR-mediated HDR. By defining the RAD18 domains required to promote HDR, we derive an enhanced RAD18 variant (e18) that stimulates CRISPR-mediated HDR in multiple human cell types, including embryonic stem cells. Mechanistically, e18 induces HDR by suppressing the localization of the NHEJ-promoting factor 53BP1 to DSBs. Altogether, this study identifies e18 as an enhancer of CRISPR-mediated HDR and highlights the promise of engineering DDR factors to augment the efficiency of precision genome editing.