# AgForce Enables Antigen-conditioned Generative Antibody Design

arXiv: https://arxiv.org/abs/2605.21610 · HTML: https://mlsanity.com/paper/2605.21610/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 38 references that are in the map.
- First posted on arXiv 20 May 2026.

## Builds on (most cited first, 18 of 18)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [E(n) Equivariant Graph Neural Networks](https://mlsanity.com/paper/2102.09844/) (2021)
- [Poincar'e Embeddings for Learning Hierarchical Representations](https://mlsanity.com/paper/1705.08039/) (2017)
- [On the Bottleneck of Graph Neural Networks and its Practical Implications](https://mlsanity.com/paper/2006.05205/) (2020)
- [Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design](https://mlsanity.com/paper/2110.04624/) (2021)
- [Conditional Antibody Design as 3D Equivariant Graph Translation](https://mlsanity.com/paper/2208.06073/) (2022)
- [End-to-End Full-Atom Antibody Design](https://mlsanity.com/paper/2302.00203/) (2023)
- [GDPP: Learning Diverse Generations Using Determinantal Point Process](https://mlsanity.com/paper/1812.00068/) (2018)
- [AbODE: Ab Initio Antibody Design using Conjoined ODEs](https://mlsanity.com/paper/2306.01005/) (2023)
- [VN-EGNN: E(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification](https://mlsanity.com/paper/2404.07194/) (2024)
- [Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing](https://mlsanity.com/paper/2407.15580/) (2024)
- [dyAb: Flow Matching for Flexible Antibody Design with AlphaFold-driven Pre-binding Antigen](https://mlsanity.com/paper/2503.01910/) (2025)
- [Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization](https://mlsanity.com/paper/2410.15040/) (2024)
- [Antibody Design and Optimization with Multi-scale Equivariant Graph Diffusion Models for Accurate Complex Antigen Binding](https://mlsanity.com/paper/2506.20957/) (2025)
- [Relation-Aware Equivariant Graph Networks for Epitope-Unknown Antibody Design and Specificity Optimization](https://mlsanity.com/paper/2501.00013/) (2024)
- [AbFlowNet: Optimizing Antibody-Antigen Binding Energy via Diffusion-GFlowNet Fusion](https://mlsanity.com/paper/2505.12358/) (2025)
- [CHIMERA-Bench: A Benchmark Dataset for Epitope-Specific Antibody Design](https://mlsanity.com/paper/2603.13431/) (2026)

## Abstract (arXiv)

Antibody design methods condition on antigen structure to generate complementarity-determining regions (CDR), yet a systematic evaluation of baseline methods reveals that they largely ignore the antigen input. We identify three failure modes that explain this behavior. Antigen blindness arises because models derive predictions from antibody framework context rather than antigen information, producing nearly identical CDRs regardless of the target. Vocabulary collapse reduces predicted amino acids to three to five per position, far below the ground truth distribution in native sequences. The argmax bottleneck on the cross-entropy loss via greedy decoding acts as a null predictor that sees only position and loop length and recovers almost all the residues irrespective of the model architecture and the target antigen. We propose a novel encoder-decoder architecture called AgForce that uses a graph neural network (GNN) as the encoder and specialized decoders for sequence-structure co-design. Specifically, we apply framework dropout, gated bottlenecks, and hyperbolic cross attention that prevent the antibody shortcut path. In the decoder, a Mixture Density Network (MDN) sequence head with Potts-like pairwise coupling and annealed Multiple Choice Learning (aMCL) replaces the cross-entropy objective with a multi-component distribution. An antigen cycle consistency head routes gradients through the sequence decoder, forcing predicted distributions to encode antigen identity. On the ChiMERa-Bench dataset, AgForce leads the baselines on every interface metric on all three splits (fnat, iRMSD, DockQ, and epitope F1) together with structure and sequence, while achieving roughly a 2x larger effective vocabulary compared to the GNN baselines.