arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2308.09482q-bio.BMcs.LG
收藏

利用语言模型逐原子生成蛋白质及其他

Atom-by-atom protein generation and beyond with language models

University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(矢量人工智能研究院);Canadian Institute for Advanced Research(加拿大高等研究院)

Daniel Flam-Shepherd, Kevin Zhu, Alán Aspuru-Guzik

AI总结:

本文提出用化学语言模型逐原子表示并生成蛋白质,使其突破标准氨基酸与遗传密码限制,可生成非天然氨基酸及新型蛋白质-药物偶联物。

摘要:

蛋白质语言模型直接从氨基酸序列中学习强大的表示。然而,它们受到限制,只能使用其词表中所表示的氨基酸集合来生成蛋白质。相比之下,化学语言模型学习较小分子的原子级表示,其中包含每个原子、键和环。在这项工作中,我们表明化学语言模型可以学习蛋白质的原子级表示,从而实现不受标准遗传密码限制、并远远超越该限制的蛋白质生成。通过这样做,我们表明语言模型可以逐原子生成完整蛋白质——实际上学习了定义蛋白质的多层分子信息层级,从其一级序列到二级和三级结构。我们证明语言模型能够探索蛋白质空间之外——生成带有修饰侧链、构成非天然氨基酸的蛋白质。更进一步,我们发现语言模型可以同时探索化学空间和蛋白质空间,并生成蛋白质-药物偶联物的新型示例。这些结果展示了利用语言模型在原子层面进行生物分子设计的潜力。

英文摘要:

Protein language models learn powerful representations directly from sequences of amino acids. However, they are constrained to generate proteins with only the set of amino acids represented in their vocabulary. In contrast, chemical language models learn atom-level representations of smaller molecules that include every atom, bond, and ring. In this work, we show that chemical language models can learn atom-level representations of proteins enabling protein generation unconstrained to the standard genetic code and far beyond it. In doing so, we show that language models can generate entire proteins atom by atom -- effectively learning the multiple hierarchical layers of molecular information that define proteins from their primary sequence to their secondary, and tertiary structure. We demonstrate language models are able to explore beyond protein space -- generating proteins with modified sidechains that form unnatural amino acids. Even further, we find that language models can explore chemical space and protein space simultaneously and generate novel examples of protein-drug conjugates. The results demonstrate the potential for biomolecular design at the atom level using language models.

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。

↑