Long Shiyang, Tian Pu
School of Chemistry, Jilin University Changchun China.
School of Life Science and School of Artificial Intelligence, Jilin University 2699 Qianjin Street Changchun China 130012
RSC Adv. 2019 Nov 6;9(62):36227-36233. doi: 10.1039/c9ra05168f. eCollection 2019 Nov 4.
Rapid and accurate assessment of protein structural models is essential for protein structure prediction and design. Great progress has been made in this regard, especially by recent application of "knowledge-based" potentials. Various machine learning based protein structural model quality assessment methods are also quite successful. However, performance of traditional "physics-based" models has not been as effective. Based on our analysis of the fundamental computational limitation behind unsatisfactory performance of "physics-based" models, we propose a generalized solvation free energy (GSFE) framework, which is intrinsically flexible for multi-scale treatments and is amenable for machine learning implementation. Finally, we implemented a simple example of backbone-based residue level GSFE with neural network, which was found to have competitive performance when compared with highly complex latest "knowledge-based" atomic potentials in distinguishing native structures from decoys.
对蛋白质结构模型进行快速准确的评估对于蛋白质结构预测和设计至关重要。在这方面已经取得了很大进展，特别是通过最近对“基于知识”的势函数的应用。各种基于机器学习的蛋白质结构模型质量评估方法也相当成功。然而，传统的“基于物理”的模型的性能并不那么有效。基于我们对“基于物理”模型性能不佳背后基本计算限制的分析，我们提出了一个广义溶剂化自由能（GSFE）框架，该框架本质上对于多尺度处理具有灵活性，并且适合机器学习实现。最后，我们用神经网络实现了一个基于主链的残基水平GSFE的简单示例，发现它在区分天然结构和诱饵结构方面与高度复杂的最新“基于知识”的原子势函数相比具有竞争力。
