Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms
Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms
复制标题
DOI：
10.48550/arxiv.2312.04323
复制
发表时间：
2023-12
期刊：
影响因子：
--
通讯作者：
Bowen Jing;T. Jaakkola;Bonnie Berger
中科院分区：
文献类型：
--
作者：
Bowen Jing;T. Jaakkola;Bonnie Berger
分子对接是基于结构的虚拟筛选的关键，然而这种工作流的吞吐量受到大多数对接算法中涉及的评分函数的昂贵优化的限制。我们探索机器学习如何通过学习具有函数形式的评分函数来加速这一过程，该函数允许更快速的优化。具体地说，我们将评分函数定义为多通道配体和蛋白质标量场的互相关，由等变图神经网络参数化，通过快速傅立叶变换实现对刚体自由度的快速优化。我们方法的运行时可以在几个抽象级别上摊销，并且对于具有公共绑定口袋的虚拟筛选设置特别有利。我们在两个简化的对接相关任务上对我们的评分函数进行了基准测试：诱饵姿势评分和刚性形体对接。与广泛使用的VINA和GNINA评分函数相比，我们的方法在晶体结构上获得了类似但更快的性能，并且在计算预测结构上更加稳健。代码可在https://github.com/bjing2016/scalar-fields.上找到
Molecular docking is critical to structure-based virtual screening, yet the throughput of such workflows is limited by the expensive optimization of scoring functions involved in most docking algorithms. We explore how machine learning can accelerate this process by learning a scoring function with a functional form that allows for more rapid optimization. Specifically, we define the scoring function to be the cross-correlation of multi-channel ligand and protein scalar fields parameterized by equivariant graph neural networks, enabling rapid optimization over rigid-body degrees of freedom with fast Fourier transforms. The runtime of our approach can be amortized at several levels of abstraction, and is particularly favorable for virtual screening settings with a common binding pocket. We benchmark our scoring functions on two simplified docking-related tasks: decoy pose scoring and rigid conformer docking. Our method attains similar but faster performance on crystal structures compared to the widely-used Vina and Gnina scoring functions, and is more robust on computationally predicted structures. Code is available at https://github.com/bjing2016/scalar-fields.