An equivariant pretrained transformer for unified 3D molecular representation learning
Top Cited Papers
Open Access
- 10 February 2026
- journal article
- research article
- Published by Springer Nature in Nature Communications
- Vol. 17 (1)
Abstract
Pretraining on a large number of unlabeled 3D molecules has showcased superiority in various scientific applications. However, prior efforts typically focus on pretraining models in a specific domain, missing the opportunity to leverage cross-domain knowledge. To mitigate this gap, we introduce Equivariant Pretrained Transformer, an all-atom foundation model that can be pretrained from multiple domain 3D molecules. Built upon an E(3)-equivariant transformer, the model learns both atom-level interactions and graph-level structural features ( e.g . residuals in proteins), allowing it to generalize across diverse tasks. The model achieves strong gains in ligand binding affinity prediction, while also performing competitively in predicting properties of proteins and small molecules. We further show that the model can help identify potential antiviral compounds against the main protease of the COVID-19 virus, and validate promising candidates through computational and experimental studies.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Accurate structure prediction of biomolecular interactions with AlphaFold 3Nature, 2024
- De novo design of protein structure and function with RFdiffusionNature, 2023
- GEOM, energy-annotated molecular conformations for property prediction and molecular generationScientific Data, 2022
- Repurposing existing drugs: identification of SARS-CoV-2 3C-like protease inhibitorsJournal of Enzyme Inhibition and Medicinal Chemistry, 2021
- Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learningNature Methods, 2019
- DeepDTA: deep drug–target binding affinity predictionBioinformatics, 2018
- SchNet – A deep learning architecture for molecules and materialsThe Journal of Chemical Physics, 2018
- Quantum chemistry structures and properties of 134 kilo moleculesScientific Data, 2014
- The PDBbind Database: Methodologies and UpdatesJournal of Medicinal Chemistry, 2005
- Glide: A New Approach for Rapid, Accurate Docking and Scoring. 1. Method and Assessment of Docking AccuracyJournal of Medicinal Chemistry, 2004