De Novo Protein Binder Design for Advanced Glycation End Products: A Computational Approach to Targeting Age-Related Glycative Damage (Stage 1 Registered Report)
Year: 2026
Type: report
Abstract: Advanced glycation end products (AGEs) accumulate with age and contribute to cardiovascular disease, neurodegeneration, and diabetic complications through receptor for advanced glycation end products (RAGE) activation and direct protein cross-linking.Despite decades of research, no approved therapies specifically target AGEs.This project applies deep learningbased protein design to create de novo protein binders that sequester carboxymethyllysine (CML), the most abundant and well-characterized AGE species.Using RFdiffusion All-Atom, we will generate 10,000 protein scaffold designs conditioned on the CML molecular structure, followed by sequence optimization with ProteinMPNN and in silico filtering using AlphaFold2 and Rosetta.The top 100-200 computational designs will be validated experimentally through yeast surface display screening against CML-modified bovine serum albumin, and top candidates will undergo binding affinity characterization by biolayer interferometry.We hypothesize that this pipeline will yield at least one binder with measurable binding to CMLmodified protein and sub-micromolar affinity.All computational designs, experimental protocols, and raw data will be made openly available.This work represents the first application of RFdiffusion All-Atom to AGE targeting and will establish whether computationally designed protein binders can serve as a new class of anti-glycation therapeutics.
Author: Kejun Ying
Language: English
Subfield: Clinical Biochemistry
Domain: Life Sciences
Open Access status: gold
Funder: University of Washington
OpenAlex ID: W7141302133