当前位置:科学网首页 > 小柯机器人 >详情
基于深度学习设计核靶向非生物微蛋白
作者:小柯机器人 发布时间:2021/8/12 13:46:11

美国麻省理工学院设计核靶向非生物微蛋白。相关研究成果发表在2021年8月9日出版的《自然—化学》。

在一个40个残基的序列中,氨基酸的排列比地球上的原子还要多。该巨大的化学搜索空间阻碍了人类学习去设计功能性聚合物。

该文中,研究人员展示了机器学习如何使非生物核靶向微蛋白的从头设计能够将反义寡聚体输送到细胞核。研究人员将高通量实验与定向进化启发的深度学习方法相结合,其中自然和非自然残基的分子结构表示为拓扑指纹图谱。该模型能够预测训练数据集之外的活动,同时破译和可视化序列-活动预测。被称为“Mach”的预测微蛋白的平均质量达到10kDa,比细胞中任何已知的变体都更有效,并且还可以将蛋白质输送到细胞质中。Mach微蛋白无毒,能在小鼠体内有效地传递反义物质。

研究结果表明,深度学习可以破译设计原理,产生高度活跃的生物分子,而这些分子不太可能被经验方法发现。

附:英文原文

Title: Deep learning to design nuclear-targeting abiotic miniproteins

Author: Schissel, Carly K., Mohapatra, Somesh, Wolfe, Justin M., Fadzen, Colin M., Bellovoda, Kamela, Wu, Chia-Ling, Wood, Jenna A., Malmberg, Annika B., Loas, Andrei, Gmez-Bombarelli, Rafael, Pentelute, Bradley L.

Issue&Volume: 2021-08-09

Abstract: There are more amino acid permutations within a 40-residue sequence than atoms on Earth. This vast chemical search space hinders the use of human learning to design functional polymers. Here we show how machine learning enables the de novo design of abiotic nuclear-targeting miniproteins to traffic antisense oligomers to the nucleus of cells. We combined high-throughput experimentation with a directed evolution-inspired deep-learning approach in which the molecular structures of natural and unnatural residues are represented as topological fingerprints. The model is able to predict activities beyond the training dataset, and simultaneously deciphers and visualizes sequence–activity predictions. The predicted miniproteins, termed ‘Mach’, reach an average mass of 10kDa, are more effective than any previously known variant in cells and can also deliver proteins into the cytosol. The Mach miniproteins are non-toxic and efficiently deliver antisense cargo in mice. These results demonstrate that deep learning can decipher design principles to generate highly active biomolecules that are unlikely to be discovered by empirical approaches.

DOI: 10.1038/s41557-021-00766-3

Source: https://www.nature.com/articles/s41557-021-00766-3

期刊信息

Nature Chemistry:《自然—化学》,创刊于2009年。隶属于施普林格·自然出版集团,最新IF:21.687
官方网址:https://www.nature.com/nchem/
投稿链接:https://mts-nchem.nature.com/cgi-bin/main.plex