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

Ruidong Wu, Ruihan Guo, Rui Wang, Shitong Luo, Yue Xu, Jiahan Li, Jianzhu Ma, Qiang Liu, Yunan Luo, Jian Peng
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:53422-53442, 2024.

Abstract

Despite the striking success of general protein folding models such as AlphaFold2 (AF2), 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 improvement over AF2 by 182% and 100% respectively.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-wu24g, title = {{FAFE}: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames}, author = {Wu, Ruidong and Guo, Ruihan and Wang, Rui and Luo, Shitong and Xu, Yue and Li, Jiahan and Ma, Jianzhu and Liu, Qiang and Luo, Yunan and Peng, Jian}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {53422--53442}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/wu24g/wu24g.pdf}, url = {https://proceedings.mlr.press/v235/wu24g.html}, abstract = {Despite the striking success of general protein folding models such as AlphaFold2 (AF2), 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 improvement over AF2 by 182% and 100% respectively.} }
Endnote
%0 Conference Paper %T FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames %A Ruidong Wu %A Ruihan Guo %A Rui Wang %A Shitong Luo %A Yue Xu %A Jiahan Li %A Jianzhu Ma %A Qiang Liu %A Yunan Luo %A Jian Peng %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-wu24g %I PMLR %P 53422--53442 %U https://proceedings.mlr.press/v235/wu24g.html %V 235 %X Despite the striking success of general protein folding models such as AlphaFold2 (AF2), 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 improvement over AF2 by 182% and 100% respectively.
APA
Wu, R., Guo, R., Wang, R., Luo, S., Xu, Y., Li, J., Ma, J., Liu, Q., Luo, Y. & Peng, J.. (2024). FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:53422-53442 Available from https://proceedings.mlr.press/v235/wu24g.html.

Related Material