Accurate Estimation of Solvent Accessible Surface Area for Coarse-Grained Biomolecular Structures with Deep Learning

Abstract

Coarse-grained (CG) models of biomolecules have been widely used in protein/ribonucleic acid (RNA) three-dimensional structure prediction, docking, drug design, and molecular simulations due to their superiority in computational efficiency. Most of these applications strongly depend on the reasonable estimation of solvation free energy, which requires the accurate calculation of solvent accessible surface area (SASA). Although algorithms for SASA calculations with all-atom protein and RNA structures have been well-established, accurately estimating the SASA based on CG structures is extremely challenging. In this work, we developed a deep learning-based SASA estimator (DeepCGSA), which can provide almost perfect SASA estimation based on CG structures of protein and RNA molecules. Extensive testing analysis showed that for three types of widely used CG protein models, including the Cα-based, Cα–Cβ, and Martini models, the correlation coefficients between the predicted values and the reference values can be as high as 0.95–0.99, which perform dramatically better than available methods. In addition, the new method can be used for CG RNA structures and unfolded protein structures with much improved accuracy. We anticipate that DeepCGSA will be highly useful in the protein/RNA structure prediction, drug design, and other applications, in which accurate estimations of SASA for CG biomolecular structures are critically important.

A computational investigation on Rho-related GTP-binding protein RhoB through molecular modeling and molecular dynamics simulation study

“…To compute the solvent-accessible surface area of each atom or residue in each simulation frame. In our analytical part, SASA analysis revealed the solvent-exposed area, which may decrease the solubility of the protein and can modulate protein-protein interactions [3], [79]–[81]. Prediction of protein solubility is gaining importance with the growing use of protein molecules as therapeutics, and ongoing requirements for high-level expression [75].…”

A Computational Investigation on Rho-related GTP-binding Protein RhoB through Molecular Modeling and Molecular Dynamics Simulation Study

“…To compute the solvent-accessible surface area of each atom or residue in each simulation frame. In our analytical part, SASA analysis revealed the solvent-exposed area, which may decrease the solubility of the protein and can modulate protein-protein interactions [3,[78][79][80]. Prediction of protein solubility is gaining importance with the growing use of protein molecules as therapeutics, and ongoing requirements for high-level expression [74].…”

Machine learning in molecular simulations of biomolecules

“…"自下而上"策略的基本思路是基于高精度力 场模型的计算结果来确定粗粒化力场参数, 主要方 法有玻尔兹曼反演法 (Boltzmann inversion method) [65] 、力匹配法 (force matching) [66] 、涨落匹配法 (fluctuating matching) [67] 以及能量分解法 (energy decomposition) [68,69] 工作越来越多地见诸于发表的论文中 [34,52,[70][71][72][73][74] . 例 如, DeePMD团队同时开发出与DeePMD具有相 似网络架构与结构特征提取策略的深度学习粗粒 化力场方案 --DeePCG [52] .…”

“…同样是基于前 馈神经网络架构和力匹配方法, Wang等 [70] 在2019 案 的 选 择 具 有 更 高 要 求 [75,76] . 近 期 Clementi和 Noé等 [34,71] [72] 和使用对抗训练思 想的VADE [73] 同样可以被用于描述粗粒化坐标下 的构象分布. 精度地估算蛋白质、核酸等生物大分子的溶剂可及 性表面积(图3) [74] .…”