# Inverse folding for antibody sequence design using deep learning

arXiv: https://arxiv.org/abs/2310.19513 · HTML: https://mlsanity.com/paper/2310.19513/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 25 references that are in the map.
- First posted on arXiv 30 Oct 2023.

## Builds on (most cited first, 3 of 3)

- [Learning from Protein Structure with Geometric Vector Perceptrons](https://mlsanity.com/paper/2009.01411/) (2020)
- [Diffusion probabilistic modeling of protein backbones in 3D for the motif-scaffolding problem](https://mlsanity.com/paper/2206.04119/) (2022)
- [Generating Novel, Designable, and Diverse Protein Structures by Equivariantly Diffusing Oriented Residue Clouds](https://mlsanity.com/paper/2301.12485/) (2023)

## Built on by (most cited first, 13 of 13)

- [Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization](https://mlsanity.com/paper/2410.15040/) (2024)
- [De novo antibody design with SE(3) diffusion](https://mlsanity.com/paper/2405.07622/) (2024)
- [AbBiBench: A Benchmark for Antibody Binding Affinity Maturation and Design](https://mlsanity.com/paper/2506.04235/) (2025)
- [Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences](https://mlsanity.com/paper/2606.16905/) (2026)
- [Fast and Accurate Antibody Sequence Design via Structure Retrieval](https://mlsanity.com/paper/2502.19395/) (2025)
- [How to make the most of your masked language model for protein engineering](https://mlsanity.com/paper/2603.10302/) (2026)
- [Towards More Accurate Full-Atom Antibody Co-Design](https://mlsanity.com/paper/2502.19391/) (2025)
- [IgCraft: A versatile sequence generation framework for antibody discovery and engineering](https://mlsanity.com/paper/2503.19821/) (2025)
- [Tokenizing Loops of Antibodies](https://mlsanity.com/paper/2509.08707/) (2025)
- [Improved Therapeutic Antibody Reformatting through Multimodal Machine Learning](https://mlsanity.com/paper/2509.19604/) (2025)
- [Is Sequence Information All You Need for Bayesian Optimization of Antibodies?](https://mlsanity.com/paper/2509.24933/) (2025)
- [Deep Learning for Protein Complex Prediction and Design](https://mlsanity.com/paper/2605.11189/) (2026)
- [Antigen-specific Antibody Multi-modal Foundation Model for Functional Antibody Design](https://mlsanity.com/paper/2607.20057/) (2026)

## Abstract (arXiv)

We consider the problem of antibody sequence design given 3D structural information. Building on previous work, we propose a fine-tuned inverse folding model that is specifically optimised for antibody structures and outperforms generic protein models on sequence recovery and structure robustness when applied on antibodies, with notable improvement on the hypervariable CDR-H3 loop. We study the canonical conformations of complementarity-determining regions and find improved encoding of these loops into known clusters. Finally, we consider the applications of our model to drug discovery and binder design and evaluate the quality of proposed sequences using physics-based methods.