AbDiffuser: full-atom generation of in-vitro functioning antibodies
Karolis Martinkus, Jan Ludwiczak, Wei-Ching Liang, Julien Lafrance-Vanasse, Isidro Hötzel, Arvind Rajpal, Yan Wu, Kyunghyun Cho, Richard Bonneau, Vladimir Gligorijevic, Andreas Loukas
Abstract
We introduce AbDiffuser, an equivariant and physics-informed diffusion model for the joint generation of antibody 3D structures and sequences. AbDiffuser is built on top of a new representation of protein structure, relies on a novel architecture for aligned proteins, and utilizes strong diffusion priors to improve the denoising process. Our approach improves protein diffusion by taking advantage of domain knowledge and physics-based constraints; handles sequence-length changes; and reduces memory complexity by an order of magnitude, enabling backbone and side chain generation. We validate AbDiffuser in silico and in vitro. Numerical experiments showcase the ability of AbDiffuser to generate antibodies that closely track the sequence and structural properties of a reference set. Laboratory experiments confirm that all 16 HER2 antibodies discovered were expressed at high levels and that 57.1% of the selected designs were tight binders.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext d1748f5c-4c1d-469f-b811-dcc32f2fb91eCited by top-tier papers30
- Protein Conformation Generation via Force-Guided SE(3) Diffusion ModelsYan Wang, Lihao Wang, Yuning Shen, Yiqun Wang et al.ICML 2024 · 65 citations
- Protein Discovery with Discrete Walk-Jump SamplingNathan C. Frey, Daniel Berenberg, Karina Zadorozhny, Joseph Kleinhenz et al.ICLR 2024 · 54 citations
- Full-Atom Peptide Design with Geometric Latent DiffusionXiangzhe Kong, Yinjun Jia, Wenbing Huang, Yang LiuNeurIPS 2024 · 48 citations
- Antigen-Specific Antibody Design via Direct Energy-based Preference OptimizationXiangxin Zhou, Dongyu Xue, Ruizhe Chen, Zaixiang Zheng et al.NeurIPS 2024 · 48 citations
- Harmonic Self-Conditioned Flow Matching for joint Multi-Ligand Docking and Binding Site DesignHannes Stärk, Bowen Jing, Regina Barzilay, Tommi S. JaakkolaICML 2024 · 43 citations
Builds on22
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Improved Denoising Diffusion Probabilistic ModelsAlexander Quinn Nichol, Prafulla DhariwalICML 2021 · 5,234 citations
- MLP-Mixer: An all-MLP Architecture for VisionIlya O. Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer et al.NeurIPS 2021 · 3,862 citations
- Structured Denoising Diffusion Models in Discrete State-SpacesJacob Austin, Daniel D. Johnson, Jonathan Ho, Daniel Tarlow et al.NeurIPS 2021 · 2,256 citations
- E(n) Equivariant Graph Neural NetworksVictor Garcia Satorras, Emiel Hoogeboom, Max WellingICML 2021 · 1,432 citations
Related papers
- Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric ConstraintsTian Zhu, Milong Ren, Haicang ZhangICML 2024 · 13 citations
- Antigen-Specific Antibody Design and Optimization with Diffusion-Based Generative Models for Protein StructuresShitong Luo, Yufeng Su, Xingang Peng, Sheng Wang et al.NeurIPS 2022 · 331 citations
- Repurposing AlphaFold3-like Protein Folding Models for Antibody Sequence and Structure Co-designNianzu Yang, Songlin Jiang, Jian Ma, Huaijin Wu et al.NeurIPS 2025 · 3 citations
- Dynamic Geometric Equivariant Network for Full-Atom Antibody DesignWeihong Huang, Feng Yang, Qiang Zhang, Juan LiuAAAI 2026
- Towards All-Atom Foundation Models for Biomolecular Binding Affinity PredictionLiang Shi, Zuobai Zhang, Huiyu Cai, Santiago Miret et al.ICLR 2026
