EquiDesign: a versatile computational framework for de novo protein sequence design.
6 affiliations
- 1College of Artificial Intelligence, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800, China.
- 2Center for Data Science and Intelligent Computing, Nanjing Agricultural University, No. 666 Binjiang Avenue, Nanjing, Jiangsu 211800, China.
- 3Research and Development-Statistics, Eli Lilly and Company, Lilly Corporate Center, Indianapolis, IN 46285, United States.
- 4Department of the Built Environment, College of Design and Engineering, National University of Singapore, 4 Architecture Drive, Singapore 117566, Singapore.
- 5College of Mechanical and Vehicle Engineering, Hunan University, Changsha 410082, China.
- 6Laboratory of Gastrointestinal Microbiology, College of Animal Science and Technology, Nanjing Agricultural University, No. 1 Weigang Road, Nanjing 210095, China.
Abstract
Designing amino acid sequences that uniquely fold into target three-dimensional conformations defines the protein inverse folding problem, a formidable bottleneck in de novo protein design. Current computational paradigms, including deep learning-based approaches, often struggle to reconcile high sequence accuracy with structural stability, computational efficiency, and generalizability across diverse protein families. Here, we present EquiDesign, a deep learning framework that surmounts these constraints via a novel multistep Equiformer-enhanced architecture. By disentangling geometric features into invariant scalars and equivariant vectors, EquiDesign preserves the intrinsic directional topology of the protein backbone during message passing. This is achieved through spatial K-nearest neighbor graph construction and geometric attention mechanisms that hierarchically fuse multiscale contextual information, yielding a physically grounded representation of protein conformations. Extensive benchmarking demonstrates that EquiDesign achieves superior sequence recovery on standard and challenging test sets compared with state-of-the-art methods. Critically, the generated sequences exhibit exceptional structural fidelity, folding stability, and sequence diversity, as validated by comprehensive controls against training-set memorization, compositional bias, and physical energy landscapes, alongside targeted diversity sampling. These results establish EquiDesign as a robust, scalable, and generalizable inverse folding solution, driven by SE(3)-equivariant encoding and multiscale geometric attention, thus propelling de novo protein design toward unprecedented structural precision.
Related
- AIPFusion-Net: an interaction-fusion framework for anti-inflammatory peptide prediction using protein language model embeddings, local sequence patterns, and handcrafted descriptors.
- Modular multifunctional 5HP2O linkers for the versatile assembly of protein-oligonucleotide conjugates
- Representation learning for low-data protein fitness prediction using sequence–structure embeddings and graph neural networks
- Sequence‐encoded dynamics diversify allostery within a conserved protein scaffold
- Sequence Engineering at Non-motif Modulator Residues Yields a Peptide That Effectively Targets a Single PDZ Protein in a Disease-relevant Cellular Context
BibTeX
@article{gao2026equidesign,
title = {{EquiDesign: a versatile computational framework for de novo protein sequence design.}},
author = {Qiang Gao and Zhongyu Xu and Kai Chen and Xiaochen Cen and Ke Yan and Jinxin Liu and Zhiwei Ji},
journal = {Briefings in bioinformatics},
year = {2026},
month = sep,
doi = {10.1093/bib/bbag581},
url = {https://europepmc.org/article/MED/42932845},
note = {CC BY},
}
RIS
TY - JOUR
TI - EquiDesign: a versatile computational framework for de novo protein sequence design.
AU - Qiang Gao
AU - Zhongyu Xu
AU - Kai Chen
AU - Xiaochen Cen
AU - Ke Yan
AU - Jinxin Liu
AU - Zhiwei Ji
PY - 2026
DA - 2026/09/01
JO - Briefings in bioinformatics
DO - 10.1093/bib/bbag581
UR - https://europepmc.org/article/MED/42932845
AB - Designing amino acid sequences that uniquely fold into target three-dimensional conformations defines the protein inverse folding problem, a formidable bottleneck in de novo protein design. Current computational paradigms, including deep learning-based approaches, often struggle to reconcile high sequence accuracy with structural stability, computational efficiency, and generalizability across diverse protein families. Here, we present EquiDesign, a deep learning framework that surmounts these constraints via a novel multistep Equiformer-enhanced architecture. By disentangling geometric features into invariant scalars and equivariant vectors, EquiDesign preserves the intrinsic directional topology of the protein backbone during message passing. This is achieved through spatial K-nearest neighbor graph construction and geometric attention mechanisms that hierarchically fuse multiscale contextual information, yielding a physically grounded representation of protein conformations. Extensive benchmarking demonstrates that EquiDesign achieves superior sequence recovery on standard and challenging test sets compared with state-of-the-art methods. Critically, the generated sequences exhibit exceptional structural fidelity, folding stability, and sequence diversity, as validated by comprehensive controls against training-set memorization, compositional bias, and physical energy landscapes, alongside targeted diversity sampling. These results establish EquiDesign as a robust, scalable, and generalizable inverse folding solution, driven by SE(3)-equivariant encoding and multiscale geometric attention, thus propelling de novo protein design toward unprecedented structural precision.
SN - 1467-5463
SN - 1477-4054
ER -