Accurate prediction of protein secondary structure (alpha‐helix, beta‐strand and coil) is a crucial step for protein inter‐residue contact prediction and ab initio tertiary structure prediction. In a previous study, we developed a deep belief network‐based protein secondary structure method (DNSS1) and successfully advanced the prediction accuracy beyond 80%. In this work, we developed multiple advanced deep learning architectures (DNSS2) to further improve secondary structure prediction. The major improvements over the DNSS1 method include (a) designing and integrating six advanced one‐dimensional deep convolutional/recurrent/residual/memory/fractal/inception networks to predict 3‐state and 8‐state secondary structure, and (b) using more sensitive profile features inferred from Hidden Markov model (HMM) and multiple sequence alignment (MSA). Most of the deep learning architectures are novel for protein secondary structure prediction. DNSS2 was systematically benchmarked on independent test data sets with eight state‐of‐art tools and consistently ranked as one of the best methods. Particularly, DNSS2 was tested on the protein targets of 2018 CASP13 experiment and achieved the Q3 score of 81.62%, SOV score of 72.19%, and Q8 score of 73.28%. DNSS2 is freely available at: https://github.com/multicom-toolbox/DNSS2.

中文翻译：

---

DNSS2：使用先进的深度学习架构改进从头算蛋白质二级结构预测。

准确预测蛋白质二级结构（α-螺旋、β-链和卷曲）是蛋白质残基间接触预测和从头算三级结构预测的关键步骤。在之前的一项研究中，我们开发了一种基于深度信念网络的蛋白质二级结构方法 (DNSS1)，并成功地将预测准确率提高到 80% 以上。在这项工作中，我们开发了多种高级深度学习架构 (DNSS2) 以进一步改进二级结构预测。对 DNSS1 方法的主要改进包括（a）设计和集成六个先进的一维深度卷积/循环/残差/内存/分形/初始网络来预测 3 态和 8 态二级结构，以及（b）使用更多从隐马尔可夫模型（HMM）和多序列比对（MSA）推断出的敏感轮廓特征。大多数深度学习架构对于蛋白质二级结构预测都是新颖的。DNSS2 使用八种最先进的工具在独立测试数据集上系统地进行了基准测试，并一直被评为最佳方法之一。特别是DNSS2在2018年CASP13实验的蛋白质靶点上进行了测试，Q3得分为81.62%，SOV得分为72.19%，Q8得分为73.28%。DNSS2 可在以下网址免费获得：https://github.com/multicom-toolbox/DNSS2。Q8 得分为 73.28%。DNSS2 可在以下网址免费获得：https://github.com/multicom-toolbox/DNSS2。Q8 得分为 73.28%。DNSS2 可在以下网址免费获得：https://github.com/multicom-toolbox/DNSS2。