arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2406.14347physics.chem-phcs.LGstat.ML
收藏

$\nabla^2$DFT:一个通用的类药分子量子化学数据集及神经网络势基准

$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials

AIRI;EPFL(洛桑联邦理工学院);St. Petersburg Department of the Steklov Institute of Mathematics(斯捷克洛夫数学研究所圣彼得堡分所);St. Petersburg State University(圣彼得堡国立大学);ISP RAS Research Center for Trusted Artificial Intelligence(俄罗斯科学院信息学研究所可信人工智能研究中心)
Kuzma Khrabrov, Anton Ber, Artem Tsypin, Konstantin Ushenin, Egor Rumiantsev, Alexander Telepov, Dmitry Protasov, Ilya Shenbin, Anton Alekseev, Mikhail Shirokik… 展开作者

Kuzma Khrabrov, Anton Ber, Artem Tsypin, Konstantin Ushenin, Egor Rumiantsev, Alexander Telepov, Dmitry Protasov, Ilya Shenbin, Anton Alekseev, Mikhail Shirokikh, Sergey Nikolenko, Elena Tutubalina, Artur Kadurin

AI总结:

本研究提出基于nablaDFT的$\nabla^2$DFT数据集与基准,扩充了类药分子的结构、构象及多种量子化学数据,构建了多任务NNP评估基准与可扩展训练框架,为神经网络势的研发提供支撑。

摘要:

计算量子化学方法可为计算机辅助药物发现及其他化学科学领域所需的分子性质提供精确近似,但高计算复杂度限制了其应用的可扩展性。神经网络势(NNPs)是量子化学方法的一种极具潜力的替代方案,但其训练需要大规模且多样化的数据集。本工作提出了一个基于nablaDFT的新型数据集与基准,名为$\nabla^2$DFT。该数据集包含的分子结构数量是原数据集的两倍,构象数量为其三倍,还新增了数据类型与任务,并纳入了前沿模型。数据集涵盖能量、受力、17种分子性质、哈密顿量与重叠矩阵,以及一个波函数对象。所有计算均针对每个构象在DFT水平($ω$B97X-D/def2-SVP)下完成。此外,$\nabla^2$DFT是首个包含大量类药分子弛豫轨迹的数据集。我们还引入了一个新型基准,用于评估神经网络势在分子性质预测、哈密顿量预测和构象优化任务中的表现。最后,我们提出了一个可扩展的神经网络势训练框架,并在其中实现了10个模型。

英文摘要:

Methods of computational quantum chemistry provide accurate approximations of molecular properties crucial for computer-aided drug discovery and other areas of chemical science. However, high computational complexity limits the scalability of their applications. Neural network potentials (NNPs) are a promising alternative to quantum chemistry methods, but they require large and diverse datasets for training. This work presents a new dataset and benchmark called $\nabla^2$DFT that is based on the nablaDFT. It contains twice as much molecular structures, three times more conformations, new data types and tasks, and state-of-the-art models. The dataset includes energies, forces, 17 molecular properties, Hamiltonian and overlap matrices, and a wavefunction object. All calculations were performed at the DFT level ($ω$B97X-D/def2-SVP) for each conformation. Moreover, $\nabla^2$DFT is the first dataset that contains relaxation trajectories for a substantial number of drug-like molecules. We also introduce a novel benchmark for evaluating NNPs in molecular property prediction, Hamiltonian prediction, and conformational optimization tasks. Finally, we propose an extendable framework for training NNPs and implement 10 models within it.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑