用于设计下一代 mRNA 疗法的机器学习,Accounts of Chemical Research

当前位置： X-MOL 学术 › Acc. Chem. Res. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

用于设计下一代 mRNA 疗法的机器学习
Accounts of Chemical Research ( IF 16.4 ) Pub Date : 2021-12-14 , DOI: 10.1021/acs.accounts.1c00621
Sebastian M Castillo-Hair _{1,

2} , Georg Seelig _{1,

3}

Affiliation

在过去的两年里，mRNA 疗法和疫苗经历了从一个有趣的概念到现实世界影响的快速转变。然而，尽管 mRNA 治疗的某些方面，例如使用化学修饰来增加稳定性和降低免疫原性，已经在过去二十多年中得到了广泛的优化，但其他方面，特别是控制翻译的非编码前导和尾随序列的选择和设计效率和稳定性，受到的关注相对较少。在实践中，此类 5' 和 3' 非翻译区 (UTR) 通常是从高度表达的人类基因中借用的，几乎没有或没有修饰，例如辉瑞/BioNTech Covid 疫苗。专注于 5′UTR，我们在这里认为模型驱动设计是一种很有前途的替代方案，它提供了对 5'UTR 功能的前所未有的控制。我们回顾了最近将合成生物学与机器学习相结合的工作，以建立将核糖体加载以及翻译效率与 5'UTR 序列相关联的定量模型。我们首先介绍了一种实验方法，该方法使用多核糖体分析和高通量测序来并行量化数十万个 5'UTR 的核糖体负载。我们应用这种方法来测量合成 RNA 文库中的核糖体负载，其中随机序列插入 5'UTR。然后，我们回顾了 Optimus 5-Prime，这是一种基于实验数据训练的卷积神经网络模型。我们强调可以从具有退化 5'UTR 的合成数据集中学习非常准确的生物调节模型。我们不仅在我们的随机库中保留的数据集上验证模型预测，而且还在一个包含超过 30,000 个人类 5'UTR 片段的大型库上验证模型预测，并使用其他组独立收集的翻译报告数据。实验和模型都与常用的化学修饰核苷兼容，特别是假尿苷 (Ψ) 和 1-甲基-假尿苷 (m^1Ψ )。我们发现，一般而言，当与不同的蛋白质编码序列结合时，甚至在不同化学修饰的背景下，5'UTR 具有非常相似的影响。我们证明了 Optimus 5-Prime 可以与设计算法相结合，以生成具有精确定义的翻译效率的从头序列。我们强调了设计算法的最新发展，这些算法依赖于激活最大化和生成建模来提高设计序列的适应度和多样性。与遗传算法等先前的方法相比，我们表明这些方法不仅速度更快，而且不太可能陷入局部序列最优。最后，我们讨论了如何将这里审查的方法推广到其他基因区域和应用。

"点击查看英文标题和摘要"

Machine Learning for Designing Next-Generation mRNA Therapeutics

Over just the last 2 years, mRNA therapeutics and vaccines have undergone a rapid transition from an intriguing concept to real-world impact. However, whereas some aspects of mRNA therapeutics, such as the use of chemical modifications to increase stability and reduce immunogenicity, have been extensively optimized for over two decades, other aspects, particularly the selection and design of the noncoding leader and trailer sequences which control translation efficiency and stability, have received comparably less attention. In practice, such 5′ and 3′ untranslated regions (UTRs) are often borrowed from highly expressed human genes with few or no modifications, as in the case for the Pfizer/BioNTech Covid vaccine. Focusing on the 5′UTR, we here argue that model-driven design is a promising alternative that provides unprecedented control over 5′UTR function. We review recent work that combines synthetic biology with machine learning to build quantitative models that relate ribosome loading, and thus translation efficiency, to the 5′UTR sequence. We first introduce an experimental approach that uses polysome profiling and high-throughput sequencing to quantify ribosome loading for hundreds of thousands of 5′UTRs in parallel. We apply this approach to measure ribosome loading in synthetic RNA libraries with a random sequence inserted into the 5′UTR. We then review Optimus 5-Prime, a convolutional neural network model trained on the experimental data. We highlight that very accurate models of biological regulation can be learned from synthetic data sets with degenerate 5′UTRs. We validate model predictions not only on held-out data sets from our random library but also on a large library of over 30 000 human 5′UTR fragments and using translation reporter data collected independently by other groups. Both the experiment and model are compatible with commonly used chemically modified nucleosides, in particular, pseudouridine (Ψ) and 1-methyl-pseudouridine (m¹Ψ). We find that, in general, 5′UTRs have very similar impacts when combined with different protein-coding sequences and even in the context of different chemical modifications. We demonstrate that Optimus 5-Prime can be combined with design algorithms to generate de novo sequences with precisely defined translation efficiencies. We emphasize recent developments in design algorithms that rely on activation maximization and generative modeling to improve both the fitness and diversity of designed sequences. Compared with prior approaches such as genetic algorithms, we show that these approaches are not only faster but also less likely to get stuck in local sequence optima. Finally, we discuss how the approach reviewed here can be generalized to other gene regions and applications.

更新日期：2022-01-04

点击分享查看原文

点击收藏

公开下载

阅读更多本刊新发论文本刊介绍/投稿指南