FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929405538861056 |
|---|---|
| author | Wu, Ruidong Guo, Ruihan Wang, Rui Luo, Shitong Xu, Yue Li, Jiahan Ma, Jianzhu Liu, Qiang Luo, Yunan Peng, Jian |
| author_facet | Wu, Ruidong Guo, Ruihan Wang, Rui Luo, Shitong Xu, Yue Li, Jiahan Ma, Jianzhu Liu, Qiang Luo, Yunan Peng, Jian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_01649 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames Wu, Ruidong Guo, Ruihan Wang, Rui Luo, Shitong Xu, Yue Li, Jiahan Ma, Jianzhu Liu, Qiang Luo, Yunan Peng, Jian Quantitative Methods Machine Learning 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. |
| title | FAFE: Immune Complex Modeling with Geodesic Distance Loss on Noisy Group Frames |
| topic | Quantitative Methods Machine Learning |
| url | https://arxiv.org/abs/2407.01649 |