The prediction of interresidue contacts and distances from coevolutionary data using deep learning has considerably advanced protein structure prediction. Here, we build on these advances by developing a deep residual network for predicting interresidue orientations, in addition to distances, and a Rosetta-constrained energy-minimization protocol for rapidly and accurately generating structure models guided by these restraints. In benchmark tests on 13th Community-Wide Experiment on the Critical Assessment of Techniques for Protein Structure Prediction (CASP13)- and Continuous Automated Model Evaluation (CAMEO)-derived sets, the method outperforms all previously described structure-prediction methods. Although trained entirely on native proteins, the network consistently assigns higher probability to de novo-designed proteins, identifying the key fold-determining residues and providing an independent quantitative measure of the "ideality" of a protein structure. The method promises to be useful for a broad range of protein structure prediction and design problems.

中文翻译：

---

使用预测的残基间方向改进的蛋白质结构预测。

使用深度学习预测残基间接触和与进化数据的距离，具有相当先进的蛋白质结构预测。在这里，我们通过开发深度的残差网络（用于预测距离之间的残基间方向）以及罗塞塔约束的能量最小化协议来快速，准确地生成受这些约束指导的结构模型，从而在这些进步的基础上进一步发展。在第13个社区范围内对蛋白质结构预测技术（CASP13）和连续自动模型评估（CAMEO）的技术进行关键性评估的实验的基准测试中，该方法的性能优于先前描述的所有结构预测方法。尽管网络完全是针对天然蛋白质进行训练的，但网络始终为从头设计的蛋白质分配更高的概率，鉴定决定关键折叠的残基并提供蛋白质结构“理想性”的独立定量度量。该方法有望用于广泛的蛋白质结构预测和设计问题。