SDEGen: learning to evolve molecular conformations from thermodynamic noise for conformation generation.
SDEGen: learning to evolve molecular conformations from thermodynamic noise for conformation generation.
复制标题
DOI：
10.1039/d2sc04429c
复制
发表时间：
2023-02-08
期刊：
影响因子：
8.4
通讯作者：
中科院分区：
文献类型：
--
作者：
小分子的代表性构象的生成是化学信息学和计算机辅助药物发现的基本任务，但捕获包含多个低能极小值的复杂构象分布仍然是一个巨大的挑战。深度生成建模旨在学习复杂的数据分布，是解决构象生成问题的一种很有前途的方法。在这里，受随机动力学和生成建模的最新进展的启发，我们开发了SDEGen，一种基于随机微分方程的新型构象生成模型。与现有构象生成方法相比，具有以下优点：(1)高的模型捕捉多模态构象分布的能力，从而快速搜索分子的多个低能构象；(2)更高的构象生成效率，几乎比最先进的基于分数的模型ConfGF快十倍；(3)清晰的物理解释，以了解分子如何在随机动力学系统中从噪声开始演变，最终放松到低能最小构象。大量实验表明，SDEGen在构象生成、原子间距离分布预测和热力学性质估计等不同任务中都超越了现有方法，显示出巨大的实际应用潜力。在本文中，我们开发了一种新的构象生成模型，称为SDEGen，学习分子如何在随机动力学系统中从噪声开始进化，最终放松到低能最小构象。
Generation of representative conformations for small molecules is a fundamental task in cheminformatics and computer-aided drug discovery, but capturing the complex distribution of conformations that contains multiple low energy minima is still a great challenge. Deep generative modeling, aiming to learn complex data distributions, is a promising approach to tackle the conformation generation problem. Here, inspired by stochastic dynamics and recent advances in generative modeling, we developed SDEGen, a novel conformation generation model based on stochastic differential equations. Compared with existing conformation generation methods, it enjoys the following advantages: (1) high model capacity to capture multimodal conformation distribution, thereby searching for multiple low-energy conformations of a molecule quickly, (2) higher conformation generation efficiency, almost ten times faster than the state-of-the-art score-based model, ConfGF, and (3) a clear physical interpretation to learn how a molecule evolves in a stochastic dynamics system starting from noise and eventually relaxing to the conformation that falls in low energy minima. Extensive experiments demonstrate that SDEGen has surpassed existing methods in different tasks for conformation generation, interatomic distance distribution prediction, and thermodynamic property estimation, showing great potential for real-world applications. In this paper, we developed a novel conformation generation model, termed SDEGen, learning how a molecule evolves in a stochastic dynamics system starting from noise and eventually relaxing to the conformation that falls into low energy minima.
登录
查看更多内容
DOI：
10.1007/978-1-4939-7000-1_26
发表时间：
2017
期刊：
Methods in molecular biology (Clifton, N.J.)
影响因子：
--
作者：
Burley SK;Berman HM;Kleywegt GJ;Markley JL;Nakamura H;Velankar S
通讯作者：
Velankar S
影响因子：
56.9
作者：
ANDERSON, PW
通讯作者：
ANDERSON, PW
影响因子：
56.9
作者：
Noe, Frank;Olsson, Simon;Wu, Hao
通讯作者：
Wu, Hao
影响因子：
5.6
作者：
Rai, Brajesh K.;Sresht, Vishnu;Bakken, Gregory A.
通讯作者：
Bakken, Gregory A.
CHARMM：生物分子模拟程序。
影响因子：
3
作者：
Brooks, B. R.;Brooks, C. L., III;Mackerell, A. D., Jr.;Nilsson, L.;Petrella, R. J.;Roux, B.;Won, Y.;Archontis, G.;Bartels, C.;Boresch, S.;Caflisch, A.;Caves, L.;Cui, Q.;Dinner, A. R.;Feig, M.;Fischer, S.;Gao, J.;Hodoscek, M.;Im, W.;Kuczera, K.;Lazaridis, T.;Ma, J.;Ovchinnikov, V.;Paci, E.;Pastor, R. W.;Post, C. B.;Pu, J. Z.;Schaefer, M.;Tidor, B.;Venable, R. M.;Woodcock, H. L.;Wu, X.;Yang, W.;York, D. M.;Karplus, M.
通讯作者：
Karplus, M.