Yuan Yuchen, Cui Qiang
Department of Chemistry, Boston University, 590 Commonwealth Avenue, Boston, Massachusetts 02215, United States.
Department of Physics, Boston University, 590 Commonwealth Avenue, Boston, Massachusetts 02215, United States.
J Chem Theory Comput. 2023 Aug 22;19(16):5394-5406. doi: 10.1021/acs.jctc.3c00591. Epub 2023 Aug 1.
Free energy differences (Δ) are essential to quantitative characterization and understanding of chemical and biological processes. Their direct estimation with an accurate quantum mechanical potential is of great interest and yet impractical due to high computational cost and incompatibility with typical alchemical free energy protocols. One promising solution is the multilevel free energy simulation in which the estimate of Δ at an inexpensive low level of theory is combined with the correction toward a higher level of theory. The poor configurational overlap generally expected between the two levels of theory, however, presents a major challenge. We overcome this challenge by using a deep neural network model and enhanced sampling simulations. An adversarial autoencoder is used to identify a low-dimensional (latent) space that compactly represents the degrees of freedom that encode the distinct distributions at the two levels of theory. Enhanced sampling in this latent space is then used to drive the sampling of configurations that predominantly contribute to the free energy correction. Results for both gas phase and condensed phase systems demonstrate that this data-driven approach offers high accuracy and efficiency with great potential for scalability to complex systems.
自由能差（Δ）对于化学和生物过程的定量表征和理解至关重要。使用精确的量子力学势直接估计自由能差极具意义，但由于计算成本高且与典型的炼金术自由能协议不兼容，这一方法并不实际。一个有前景的解决方案是多级自由能模拟，即在廉价的低理论水平下估计Δ，并结合向更高理论水平的校正。然而，通常预期的两个理论水平之间较差的构型重叠构成了一项重大挑战。我们通过使用深度神经网络模型和增强采样模拟克服了这一挑战。对抗自编码器用于识别一个低维（潜在）空间，该空间紧凑地表示编码两个理论水平上不同分布的自由度。然后在这个潜在空间中进行增强采样，以驱动对主要贡献于自由能校正的构型进行采样。气相和凝聚相系统的结果表明，这种数据驱动的方法具有高精度和高效率，并且具有扩展到复杂系统的巨大潜力。
