Learning from 3D biological macromolecules with artificial intelligence
technologies has been an emerging area. Computational protein design, known as
the inverse of protein structure prediction, aims to generate protein sequences
that will fold into the defined structure. Analogous to protein design, RNA
design is also an important topic in synthetic biology, which aims to generate
RNA sequences by given structures. However, existing RNA design methods mainly
focus on the secondary structure, ignoring the informative tertiary structure,
which is commonly used in protein design. To explore the complex coupling
between RNA sequence and 3D structure, we introduce an RNA tertiary structure
modeling method to efficiently capture useful information from the 3D structure
of RNA. For a fair comparison, we collect abundant RNA data and split the data
according to tertiary structures. With the standard dataset, we conduct a
benchmark by employing structure-based protein design approaches with our RNA
tertiary structure modeling method. We believe our work will stimulate the
future development of tertiary structure-based RNA design and bridge the gap
between the RNA 3D structures and sequences.

通过细胞的 3D 生物大分子和人工智能技术的学习，RNA 的 Tertiary 结构建模是一个关键问题，该研究展示了该模型的有效性，有望在 RNA 的设计方面提供更大的帮助。

基于三级结构生成的 RNA 设计

Generative Tertiary Structure-based RNA Design

Computational protein design has a wide variety of applications. Despite its
remarkable success, designing a protein for a given structure and function is
still a challenging task. On the other hand, the number of solved protein
structures is rapidly increasing while the number of unique protein folds has
reached a steady number, suggesting more structural information is being
accumulated on each fold. Deep learning neural network is a powerful method to
learn such big data set and has shown superior performance in many machine
learning fields. In this study, we applied the deep learning neural network
approach to computational protein design for predicting the probability of 20
natural amino acids on each residue in a protein. A large set of protein
structures was collected and a multi-layer neural network was constructed. A
number of structural properties were extracted as input features and the best
network achieved an accuracy of 38.3%. Using the network output as residue type
restraints was able to improve the average sequence identity in designing three
natural proteins using Rosetta. Moreover, the predictions from our network show
~3% higher sequence identity than a previous method. Results from this study
may benefit further development of computational protein design methods.

本文探究将深度学习神经网络应用于蛋白质设计，以预测蛋白质中每个残基上 20 种天然氨基酸的几率，并且以网络输出为残基类型约束，顺利提高 Rosetta 工具设计三种天然蛋白质的平均序列一致性，同时相比早期方法，本研究以多层神经网络构建的方法在序列一致性方面提高了约 3% 的准确率，这些结果将推动计算蛋白质设计方法的进一步发展。