# Antibody-Antigen Docking and Design via Hierarchical Equivariant Refinement

arXiv: https://arxiv.org/abs/2207.06616 · HTML: https://mlsanity.com/paper/2207.06616/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 14 Jul 2022.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design](https://mlsanity.com/paper/2110.04624/) (2021)
- [Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking](https://mlsanity.com/paper/2111.07786/) (2021)
- [Multi-Scale Representation Learning on Proteins](https://mlsanity.com/paper/2204.02337/) (2022)
- [When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute](https://mlsanity.com/paper/2102.12459/) (2021)
- [End-to-End Learning on 3D Protein Structure for Interface Prediction](https://mlsanity.com/paper/1807.01297/) (2018)
- [Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design](https://mlsanity.com/paper/2106.13058/) (2021)
- [Neural message passing for joint paratope-epitope prediction](https://mlsanity.com/paper/2106.00757/) (2021)

## Built on by (most cited first, 15 of 15)

- [A Survey of Generative AI for de novo Drug Design: New Frontiers in Molecule and Protein Generation](https://mlsanity.com/paper/2402.08703/) (2024)
- [Graph Neural Networks for Molecules](https://mlsanity.com/paper/2209.05582/) (2022)
- [Generalist Equivariant Transformer Towards 3D Molecular Interaction Learning](https://mlsanity.com/paper/2306.01474/) (2023)
- [De novo protein design using geometric vector field networks](https://mlsanity.com/paper/2310.11802/) (2023)
- [A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design](https://mlsanity.com/paper/2311.16126/) (2023)
- [dyAb: Flow Matching for Flexible Antibody Design with AlphaFold-driven Pre-binding Antigen](https://mlsanity.com/paper/2503.01910/) (2025)
- [Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies](https://mlsanity.com/paper/2412.20984/) (2024)
- [MAMMAL -- Molecular Aligned Multi-Modal Architecture and Language](https://mlsanity.com/paper/2410.22367/) (2024)
- [Graph Representation Learning for Interactive Biomolecule Systems](https://mlsanity.com/paper/2304.02656/) (2023)
- [ADIOS: Antibody Development via Opponent Shaping](https://mlsanity.com/paper/2409.10588/) (2024)
- [Kernel-Based Evaluation of Conditional Biological Sequence Models](https://mlsanity.com/paper/2510.15601/) (2025)
- [Active learning for energy-based antibody optimization and enhanced screening](https://mlsanity.com/paper/2409.10964/) (2024)
- [h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network](https://mlsanity.com/paper/2604.23134/) (2026)
- [Deciphering Fingerprints of 3D Molecular Surfaces for Accurate Epitope Prediction](https://mlsanity.com/paper/2606.23830/) (2026)
- [AbGaze: Attentive Geometric Representation Learning for End-to-End Antibody Design](https://mlsanity.com/paper/2609.35296/) (2026)

## Abstract (arXiv)

Computational antibody design seeks to automatically create an antibody that binds to an antigen. The binding affinity is governed by the 3D binding interface where antibody residues (paratope) closely interact with antigen residues (epitope). Thus, predicting 3D paratope-epitope complex (docking) is the key to finding the best paratope. In this paper, we propose a new model called Hierarchical Equivariant Refinement Network (HERN) for paratope docking and design. During docking, HERN employs a hierarchical message passing network to predict atomic forces and use them to refine a binding complex in an iterative, equivariant manner. During generation, its autoregressive decoder progressively docks generated paratopes and builds a geometric representation of the binding interface to guide the next residue choice. Our results show that HERN significantly outperforms prior state-of-the-art on paratope docking and design benchmarks.