# FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames

arXiv: https://arxiv.org/abs/2407.01649 · HTML: https://mlsanity.com/paper/2407.01649/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 46 references that are in the map.
- First posted on arXiv 1 Jul 2024.

## Builds on (most cited first, 7 of 7)

- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Towards a Unified View of Parameter-Efficient Transfer Learning](https://mlsanity.com/paper/2110.04366/) (2021)
- [Independent SE(3)-Equivariant Models for End-to-End Rigid Protein Docking](https://mlsanity.com/paper/2111.07786/) (2021)
- [Chain of LoRA: Efficient Fine-tuning of Language Models via Residual Learning](https://mlsanity.com/paper/2401.04151/) (2024)
- [DiffDock-PP: Rigid Protein-Protein Docking with Diffusion Models](https://mlsanity.com/paper/2304.03889/) (2023)
- [Visual Navigation for Autonomous Vehicles: An Open-source Hands-on Robotics Course at MIT](https://mlsanity.com/paper/2206.00777/) (2022)

## Built on by (most cited first, 2 of 2)

- [Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension](https://mlsanity.com/paper/2411.18463/) (2024)
- [EpiBench: Can LLMs Understand Epitopes for Antibody Drug Discovery?](https://mlsanity.com/paper/2608.06022/) (2026)

## Abstract (arXiv)

Despite the striking success of general protein folding models such as AlphaFold2(AF2, Jumper et al. (2021)), the accurate computational modeling of antibody-antigen complexes remains a challenging task. In this paper, we first analyze AF2's primary loss function, known as the Frame Aligned Point Error (FAPE), and raise a previously overlooked issue that FAPE tends to face gradient vanishing problem on high-rotational-error targets. To address this fundamental limitation, we propose a novel geodesic loss called Frame Aligned Frame Error (FAFE, denoted as F2E to distinguish from FAPE), which enables the model to better optimize both the rotational and translational errors between two frames. We then prove that F2E can be reformulated as a group-aware geodesic loss, which translates the optimization of the residue-to-residue error to optimizing group-to-group geodesic frame distance. By fine-tuning AF2 with our proposed new loss function, we attain a correct rate of 52.3% (DockQ > 0.23) on an evaluation set and 43.8% correct rate on a subset with low homology, with substantial improvement over AF2 by 182% and 100% respectively.