Xuenan Mi
Senior Scientist, AI/ML for drug discovery
Research Interests
Make your next move.
Prepare your application
Review drafts before you send them.
Explore related searches
Articles (7)
Year:
2025
Year:
2025
We trained multiple peptide language models and demonstrated their efficacy at predicting the substrates of ribosomally synthesized and post-translationally modified peptide (RiPP) biosynthetic enzymes.
Year:
2025
Year:
2024
Ribosomally synthesized and post-translationally modified peptides (RiPPs) comprise a structurally and functionally diverse group of natural products. Lasso peptides represent one of about 50 known molecular classes of RiPPs, which display a characteristic [1] rotaxane conformation formed by a lasso cyclase. This unique, threaded conformation endows lasso peptides with diverse biological activities and remarkable thermal and proteolytic stability. The prediction of lasso peptide properties, such as substrate compatibility with a particular lasso cyclase or desired biological activity, remains challenging due to limited experimental data and the intricate nature of the substrate fitness landscapes. Protein language models (PLMs) have demonstrated impressive performance in predicting protein structure and function. However, general-purpose PLMs perform poorly in lasso peptide-related predictive tasks. Therefore, there is a need to provide effective representations for lasso peptides to enable enhanced property prediction. In this study, we developed a lasso peptide-specific language model (LassoESM) by leveraging advances in pre-trained PLMs to aid the prediction of lasso peptide related properties and experimentally validate the model predictions. We demonstrate that LassoESM embeddings can accurately predict substrate compatibility for a lasso cyclase of interest when experimental data for model training was scarce. Using a deep learning framework incorporating cross-attention between lasso cyclase and substrate peptide embeddings, we identify non-cognate pairs of lasso cyclases and substrate peptides with predicted compatibility. We further show that LassoESM embeddings improve the prediction of RNA polymerase inhibitory activity, which represents a biological activity of several known lasso peptides. We anticipate that LassoESM and future iterations thereof will be instrumental for the rational design of lasso peptides with desired properties.
Year:
2024
Year:
2023
Year:
2023
Collaborators (9)
Christopher Fields
Director, HPCBio
University of Illinois at Urbana-Champaign
Jennifer Ann Smith
Professor
University of Michigan
Tanika Kelly
Professor
University of Chicago
Nora Franceschini
Professor
University of North Carolina
Douglas Mitchell
William Kelly Warren Sr. Professor of Biochemistry
Vanderbilt University
Wilfred A. van der Donk
Investigator
Howard Hughes Medical Institute
Adrienne Tin
Associate Professor
University of Mississippi Medical Center
Diwakar Shukla
Professor
University of Illinois at Urbana-Champaign
Yang Pan
Assistant Professor
University of Illinois Chicago (UIC)
Make your next move.
Prepare your application
Review drafts before you send them.