Accurate de novo design of high-affinity protein-binding macrocycles using deep learning

Developing macrocyclic binders to therapeutic proteins typically relies on large-scale screening methods that are resource intensive and provide little control over binding mode. Despite progress in protein design, there are currently no robust approaches for de novo design of protein-binding macrocycles. Here we introduce RFpeptides, a denoising diffusion-based pipeline for designing macrocyclic binders against protein targets of interest. We tested 20 or fewer designed macrocycles against each of four diverse proteins and obtained binders with medium to high affinity against all targets. For one of the targets, Rhombotarget A (RbtA), we designed a high-affinity binder (K<sub>d</sub> < 10 nM) despite starting from the predicted target structure. X-ray structures for macrocycle-bound myeloid cell leukemia 1, γ-aminobutyric acid type A receptor-associated protein and RbtA complexes match closely with the computational models, with a Cα root-mean-square deviation < 1.5 Å to the design models. RFpeptides provides a framework for rapid and custom design of macrocyclic peptides for diagnostic and therapeutic applications.

Authors

Institutions

Publication Details

Journal
Nature Chemical Biology
Published
2025-06-20
DOI
https://doi.org/10.1038/s41589-025-01929-w
Citations
34
Primary Topic
Peptidase Inhibition and Analysis
Type
article
Field-Weighted Citation Impact
35.54

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Accurate de novo design of high-affinity protein-binding macrocycles using deep learning

Yensi Flores Bueso, Manfred P Schneider, Stacey Gerben, Asim K. Bera et al.
34 citations
Nature Chemical Biology
Peptidase Inhibition and Analysis
35.54
article

Accurate de novo design of high-affinity protein-binding macrocycles using deep learning

Yensi Flores Bueso, Manfred P Schneider, Stacey Gerben, Asim K. Bera, Analisa Murray, Alexandria N. Leveille, Joseph D. Mougous, Stephen Rettie, Alex Kang, Andi Liu, Gaurav Bhardwaj, Joshua A. Kritzer, Mila Lamb, David A. Baker, Paul M. Levine, Victor Adebomi, David Juergens, Sergey Ovchinnikov, Alina Üffing, Dieter Willbold, Evans Brackenbrough, Qinqin Zhao, Frank DiMaio, Oliver H. Weiergräber, Joana A. Wilms, Vibha Vasireddy
article en
34 citations

Abstract

Developing macrocyclic binders to therapeutic proteins typically relies on large-scale screening methods that are resource intensive and provide little control over binding mode. Despite progress in protein design, there are currently no robust approaches for de novo design of protein-binding macrocycles. Here we introduce RFpeptides, a denoising diffusion-based pipeline for designing macrocyclic binders against protein targets of interest. We tested 20 or fewer designed macrocycles against each of four diverse proteins and obtained binders with medium to high affinity against all targets. For one of the targets, Rhombotarget A (RbtA), we designed a high-affinity binder (K<sub>d</sub> < 10 nM) despite starting from the predicted target structure. X-ray structures for macrocycle-bound myeloid cell leukemia 1, γ-aminobutyric acid type A receptor-associated protein and RbtA complexes match closely with the computational models, with a Cα root-mean-square deviation < 1.5 Å to the design models. RFpeptides provides a framework for rapid and custom design of macrocyclic peptides for diagnostic and therapeutic applications.

Nature Chemical BiologyVol. 21(12)
Tufts University (US), Howard Hughes Medical Institute (US), Forschungszentrum Jülich (DE), University of Washington (US), University College Cork (IE), The Francis Crick Institute (GB), PDL BioPharma (United States) (US), Heinrich Heine University Düsseldorf (DE), Massachusetts Institute of Technology (US)
Howard Hughes Medical Institute, U.S. Department of Energy, Bill and Melinda Gates Foundation, University of Washington, European Molecular Biology Laboratory, European Commission, Deutsche Forschungsgemeinschaft, European Synchrotron Radiation Facility, National Institutes of Health, Defense Advanced Research Projects Agency, Office of Science, HORIZON EUROPE Framework Programme, National Institute of General Medical Sciences, Biological and Environmental Research, Brookhaven National Laboratory
Openalex Percentile: Top 0%
Peptidase Inhibition and Analysis
35.54
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.