arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.04120q-bio.BMcs.AIcs.LG

一种用于蛋白质结构生成的潜在扩散模型

A Latent Diffusion Model for Protein Structure Generation

Texas A&M University(德克萨斯农工大学);Fujitsu Research of America(富士通美国研究院);Fujitsu Research(富士通研究院)

Cong Fu, Keqiang Yan, Limei Wang, Wing Yee Au, Michael McThrow, Tao Komikado, Koji Maruhashi, Kanji Uchino, Xiaoning Qian, Shuiwang Ji

AI总结:

本文提出结合等变蛋白质自动编码器与等变扩散模型的潜在扩散框架,在压缩潜在空间中学习蛋白质结构分布,高效生成高可设计性的新型蛋白质骨架。

摘要:

蛋白质是复杂的生物分子,在生物体内执行多种关键功能。设计和生成新型蛋白质可为包括药物发现在内的许多未来合成生物学应用铺平道路。然而,由于蛋白质结构的建模空间巨大,这仍是一项具有挑战性的计算任务。在本研究中,我们提出一种潜在扩散模型,能够降低蛋白质建模的复杂性,同时在压缩的潜在空间中灵活捕捉天然蛋白质结构的分布。具体而言,我们提出一种等变蛋白质自动编码器,将蛋白质嵌入到潜在空间中,随后使用等变扩散模型学习潜在蛋白质表示的分布。实验结果表明,我们的方法能够有效生成具有高可设计性和高效率的新型蛋白质骨架结构。代码将在 https://github.com/divelab/AIRS/tree/main/OpenProt/LatentDiff 公开发布。

英文摘要:

Proteins are complex biomolecules that perform a variety of crucial functions within living organisms. Designing and generating novel proteins can pave the way for many future synthetic biology applications, including drug discovery. However, it remains a challenging computational task due to the large modeling space of protein structures. In this study, we propose a latent diffusion model that can reduce the complexity of protein modeling while flexibly capturing the distribution of natural protein structures in a condensed latent space. Specifically, we propose an equivariant protein autoencoder that embeds proteins into a latent space and then uses an equivariant diffusion model to learn the distribution of the latent protein representations. Experimental results demonstrate that our method can effectively generate novel protein backbone structures with high designability and efficiency. The code will be made publicly available at https://github.com/divelab/AIRS/tree/main/OpenProt/LatentDiff

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑