Content area

Abstract

Resolving protein-ligand interactions in atomic detail is key to understanding how small molecules regulate macromolecular function. Although recent breakthroughs in cryogenic electron microscopy (cryo-EM) have enabled high-quality reconstruction of numerous complex biomolecules, the resolution of bound ligands is often relatively poor. Furthermore, automated methods for building and refining molecular models into cryo-EM maps have largely focused on proteins and may not be optimized for the diverse properties of small-molecule ligands. Here, we present an approach that integrates generative artificial intelligence (AI) with cryo-EM density-guided simulations to fit ligands into experimental maps. Using three inputs: 1) a protein amino acid sequence, 2) a ligand specification, and 3) an experimental cryo-EM map, we validated our approach on a set of biomedically relevant protein-ligand complexes including kinases, GPCRs, and solute transporters, none of which were present in the AI training data. In cases for which generative AI was not sufficient to predict experimental poses outright, integration of flexible fitting into molecular dynamics simulations improved ligand model-to-map cross-correlation relative to the deposited structure from 40-71% to 82-95%. This work offers a straightforward template for integrating generative AI and density-guided simulations to automate model building in cryo-EM maps of ligand-protein complexes, with potential applications for characterization and design of novel modulators and drugs.

Competing Interest Statement

The authors have declared no competing interest.

Footnotes

* Changed title and some text to better fit the approach used in the manuscript.

* https://zenodo.org/records/14842872

Details

1009240
Business indexing term
Title
Cryo-EM ligand building using generative AI and molecular dynamics
Publication title
bioRxiv; Cold Spring Harbor
Publication year
2025
Publication date
Feb 25, 2025
Section
New Results
Publisher
Cold Spring Harbor Laboratory Press
Source
BioRxiv
Place of publication
Cold Spring Harbor
Country of publication
United States
University/institution
Cold Spring Harbor Laboratory Press
Publication subject
ISSN
2692-8205
Source type
Working Paper
Language of publication
English
Document type
Working Paper
Publication history
 
 
Milestone dates
2025-02-12 (Version 1)
ProQuest document ID
3165948841
Document URL
https://www.proquest.com/working-papers/cryo-em-ligand-building-using-generative-ai/docview/3165948841/se-2?accountid=208611
Copyright
© 2025. This article is published under http://creativecommons.org/licenses/by/4.0/ (“the License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.
Last updated
2025-02-26
Database
2 databases
  • ProQuest One Academic
  • ProQuest One Academic