ProteinAE: Protein Diffusion Autoencoders for Structure Encoding

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Shaoning, Zhuo, Le, Wang, Yusong, Li, Mingyu, He, Xinheng, Wu, Fandi, Li, Hongsheng, Heng, Pheng-Ann
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914089584820224
author Li, Shaoning
Zhuo, Le
Wang, Yusong
Li, Mingyu
He, Xinheng
Wu, Fandi
Li, Hongsheng
Heng, Pheng-Ann
author_facet Li, Shaoning
Zhuo, Le
Wang, Yusong
Li, Mingyu
He, Xinheng
Wu, Fandi
Li, Hongsheng
Heng, Pheng-Ann
contents Developing effective representations of protein structures is essential for advancing protein science, particularly for protein generative modeling. Current approaches often grapple with the complexities of the SE(3) manifold, rely on discrete tokenization, or the need for multiple training objectives, all of which can hinder the model optimization and generalization. We introduce ProteinAE, a novel and streamlined protein diffusion autoencoder designed to overcome these challenges by directly mapping protein backbone coordinates from E(3) into a continuous, compact latent space. ProteinAE employs a non-equivariant Diffusion Transformer with a bottleneck design for efficient compression and is trained end-to-end with a single flow matching objective, substantially simplifying the optimization pipeline. We demonstrate that ProteinAE achieves state-of-the-art reconstruction quality, outperforming existing autoencoders. The resulting latent space serves as a powerful foundation for a latent diffusion model that bypasses the need for explicit equivariance. This enables efficient, high-quality structure generation that is competitive with leading structure-based approaches and significantly outperforms prior latent-based methods. Code is available at https://github.com/OnlyLoveKFC/ProteinAE_v1.
format Preprint
id arxiv_https___arxiv_org_abs_2510_10634
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ProteinAE: Protein Diffusion Autoencoders for Structure Encoding
Li, Shaoning
Zhuo, Le
Wang, Yusong
Li, Mingyu
He, Xinheng
Wu, Fandi
Li, Hongsheng
Heng, Pheng-Ann
Machine Learning
Developing effective representations of protein structures is essential for advancing protein science, particularly for protein generative modeling. Current approaches often grapple with the complexities of the SE(3) manifold, rely on discrete tokenization, or the need for multiple training objectives, all of which can hinder the model optimization and generalization. We introduce ProteinAE, a novel and streamlined protein diffusion autoencoder designed to overcome these challenges by directly mapping protein backbone coordinates from E(3) into a continuous, compact latent space. ProteinAE employs a non-equivariant Diffusion Transformer with a bottleneck design for efficient compression and is trained end-to-end with a single flow matching objective, substantially simplifying the optimization pipeline. We demonstrate that ProteinAE achieves state-of-the-art reconstruction quality, outperforming existing autoencoders. The resulting latent space serves as a powerful foundation for a latent diffusion model that bypasses the need for explicit equivariance. This enables efficient, high-quality structure generation that is competitive with leading structure-based approaches and significantly outperforms prior latent-based methods. Code is available at https://github.com/OnlyLoveKFC/ProteinAE_v1.
title ProteinAE: Protein Diffusion Autoencoders for Structure Encoding
topic Machine Learning
url https://arxiv.org/abs/2510.10634