Motivation With the breakthrough of AlphaFold2, the protein structure prediction problem has made remarkable progress through deep learning end-to-end techniques, in which correct folds could be built for nearly all single-domain proteins. However, the full-chain modelling appears to be lower on average accuracy than that for the constituent domains and requires higher demand on computing hardware, indicating the performance of full-chain modelling still needs to be improved. In this study, we investigate whether the predicted accuracy of the full-chain model can be further improved by domain assembly assisted by deep learning. Results In this article, we developed a structural analogue-based protein structure domain assembly method assisted by deep learning, named SADA. In SADA, a multi-domain protein structure database (MPDB) was constructed for the full-chain analogue detection using individual domain models. Starting from the initial model constructed from the analogue, the domain assembly simulation was performed to generate the full-chain model through a two-stage differential evolution algorithm guided by the energy function with an inter-residue distance potential predicted by deep learning. SADA was compared with the state-of-the-art domain assembly methods on 356 benchmark proteins, and the average TM-score of SADA models is 8.1% and 27.0% higher than that of DEMO and AIDA, respectively. We also assembled 293 human multi-domain proteins, where the average TM-score of the full-chain model after the assembly by SADA is 1.1% higher than that of the model by AlphaFold2. To conclude, we find that the domains often interact in the similar way in the quaternary orientations if the domains have similar tertiary structures. Furthermore, homologous templates and structural analogues are complementary for multi-domain protein full-chain modelling. Availability http://zhanglab-bioinf.com/SADA Supplementary information Supplementary data are available at Bioinformatics online.

中文翻译：

---

深度学习辅助的基于结构类似物的蛋白质结构域组装

动机 随着 AlphaFold2 的突破，蛋白质结构预测问题通过深度学习端到端技术取得了显着进展，其中可以为几乎所有单域蛋白质建立正确的折叠。然而，全链建模的平均准确率似乎低于组成域，对计算硬件的要求更高，表明全链建模的性能仍有待提高。在这项研究中，我们研究了是否可以通过深度学习辅助的域组装进一步提高全链模型的预测精度。结果在本文中，我们开发了一种基于结构类似物的深度学习辅助的蛋白质结构域组装方法，命名为 SADA。在萨达，构建了一个多域蛋白质结构数据库（MPDB），用于使用单个域模型进行全链类似物检测。从模拟构建的初始模型开始，通过深度学习预测的残基间距离势能函数引导的两阶段差分进化算法，进行域组装模拟以生成全链模型。SADA 在 356 个基准蛋白上与最先进的域组装方法进行了比较，SADA 模型的平均 TM 分数分别比 DEMO 和 AIDA 高 8.1% 和 27.0%。我们还组装了 293 个人类多域蛋白，其中 SADA 组装后全链模型的平均 TM 分数比 AlphaFold2 模型高 1.1%。总而言之，我们发现，如果域具有相似的三级结构，则这些域通常以类似的方式在四元方向上相互作用。此外，同源模板和结构类似物对于多域蛋白质全链建模是互补的。可用性 http://zhanglab-bioinf.com/SADA 补充信息 补充数据可在 Bioinformatics 在线获取。