A universal deep-learning model for zinc finger design enables transcription factor reprogramming.
A universal deep-learning model for zinc finger design enables transcription factor reprogramming.
复制标题
DOI：
10.1038/s41587-022-01624-4
复制
发表时间：
2023-08
影响因子：
46.9
通讯作者：
Noyes, Marcus B.
中科院分区：
文献类型：
--
作者：
Ichikawa, David M.;Abdin, Osama;Alerasool, Nader;Kogenaru, Manjunatha;Mueller, April L.;Wen, Han;Giganti, David O.;Goldberg, Gregory W.;Adams, Samantha;Spencer, Jeffrey M.;Razavi, Rozita;Nim, Satra;Zheng, Hong;Gionco, Courtney;Clark, Finnegan T.;Strokach, Alexey;Hughes, Timothy R.;Lionnet, Timothee;Taipale, Mikko;Kim, Philip M.;Noyes, Marcus B.
Cys 2 His 2锌指（ZF）结构域被工程化以结合基因组中的特异性靶序列，为基因表达的可编程调控提供了有效的策略，具有许多潜在的治疗应用。然而，ZF结构域与DNA的结构复杂接合使其设计具有挑战性。在这里，我们描述了490亿蛋白质-DNA相互作用的筛选和深度学习模型ZFDesign的开发，该模型解决了任何基因组靶点的ZF设计。ZFDesign是一种现代机器学习方法，它对由一系列库环境引起的全局和目标特定差异进行建模，并特别考虑到使用新型分层Transformer架构的相邻手指的兼容性。我们证明了设计的ZFs作为核酸酶以及激活剂和抑制剂的多功能性，通过无缝重编程人类转录因子。这些因子可用于上调单倍不足的等位基因，下调功能获得性突变或测试与转录因子通常会影响的许多基因相反的单个基因的调节的结果。通过深度学习模型促进锌指设计。
Cys2His2 zinc finger (ZF) domains engineered to bind specific target sequences in the genome provide an effective strategy for programmable regulation of gene expression, with many potential therapeutic applications. However, the structurally intricate engagement of ZF domains with DNA has made their design challenging. Here we describe the screening of 49 billion protein–DNA interactions and the development of a deep-learning model, ZFDesign, that solves ZF design for any genomic target. ZFDesign is a modern machine learning method that models global and target-specific differences induced by a range of library environments and specifically takes into account compatibility of neighboring fingers using a novel hierarchical transformer architecture. We demonstrate the versatility of designed ZFs as nucleases as well as activators and repressors by seamless reprogramming of human transcription factors. These factors could be used to upregulate an allele of haploinsufficiency, downregulate a gain-of-function mutation or test the consequence of regulation of a single gene as opposed to the many genes that a transcription factor would normally influence. Zinc finger design is facilitated with a deep-learning model.
登录
查看更多内容
影响因子：
46.9
作者：
Isalan, M;Klug, A;Choo, Y
通讯作者：
Choo, Y
影响因子：
64.8
作者：
Anders, Carolin;Niewoehner, Ole;Duerst, Alessia;Jinek, Martin
通讯作者：
Jinek, Martin
影响因子：
82.9
作者：
Charlesworth, Carsten T.;Deshpande, Priyanka S.;Porteus, Matthew H.
通讯作者：
Porteus, Matthew H.
影响因子：
56.9
作者：
Jinek, Martin;Chylinski, Krzysztof;Charpentier, Emmanuelle
通讯作者：
Charpentier, Emmanuelle
影响因子：
4.5
作者：
Emerson RO;Thomas JH
通讯作者：
Thomas JH