Designing protein sequences that fold to a given three‐dimensional (3D) structure has long been a challenging problem in computational structural biology with significant theoretical and practical implications. In this study, we first formulated this problem as predicting the residue type given the 3D structural environment around the C _α atom of a residue, which is repeated for each residue of a protein. We designed a nine‐layer 3D deep convolutional neural network (CNN) that takes as input a gridded box with the atomic coordinates and types around a residue. Several CNN layers were designed to capture structure information at different scales, such as bond lengths, bond angles, torsion angles, and secondary structures. Trained on a very large number of protein structures, the method, called ProDCoNN (protein design with CNN), achieved state‐of‐the‐art performance when tested on large numbers of test proteins and benchmark datasets.

中文翻译：

---

ProDCoNN：使用卷积神经网络进行蛋白质设计。

长期以来，设计折叠成给定三维（3D）结构的蛋白质序列一直是计算结构生物学中一个具有挑战性的问题，具有重要的理论和实践意义。在这项研究中，我们首先制定了这个问题，因为预测残留类型给定的C周围的三维结构环境_α 残基的原子，对蛋白质的每个残基重复。我们设计了一个9层3D深度卷积神经网络（CNN），该网络将带有原子坐标和残基类型的网格框作为输入。设计了多个CNN层以捕获不同比例的结构信息，例如粘结长度，粘结角，扭转角和二级结构。经过大量蛋白质结构训练的方法，称为ProDCoNN（带有CNN的蛋白质设计），当在大量测试蛋白质和基准数据集上进行测试时，达到了最先进的性能。