Spatio-temporal learning from molecular dynamics simulations for protein-ligand binding affinity prediction

This Zenodo repository provides comprehensive resources for the paper titled "Spatio-temporal learning from molecular dynamics simulations for protein-ligand binding affinity prediction" published on Bioinformatics. We created a dataset of 63,000 molecular dynamics simulations by performing 10 simulations of 10 ns on 6,300 complexes. Neural networks were developed to learn from this data in order to predict the binding affinities of protein-ligand complexes. The implementation of these neural networks are available on github. Our collection includes training/benchmark datasets, trained statistical models, and results on test sets (CSV & PDF files). Training/benchmark datasets: Training, validation and test sets are provided to train and evaluate the following neural networks: Pafnucy, Proli and Densenucy without MD data augmentation (dataset file names contain "initial") Pafnucy, Proli and Densenucy with MD data augmentation (dataset file names contain "MDDA") Pafnucy with/without MD data augmentation and Proli and Densenucy with MD data augmentation were also evaluated on the fep test set (test set file name contain "fep") Timenucy and Videonucy using spatiotemporal learning methods (dataset file names contain "4D") Pafnucy without MD data augmentation and on a reduced training set (dataset file names contain "reduced") For each training methodology (MD data augmentation and spatiotemporal learning), we provide the data for the whole complex, only the ligand or only the protein. Additionally for spatiotemporal learning, we provide the data with only the ligand using the tracking mode. Statistical models: We provide the models trained with Pafnucy, Proli, Densenucy, Timenucy and Videonucy. Each models were trained in 10 replicates. For Pafnucy, Proli, Densenucy, we provide the models trained with random and systematic rotations, as well as with or without MD data augmentation. For Proli, Densenucy, Timenucy and Videonucy, we provide the models trained on the whole complex, only the ligand or only the protein. For Pafnucy we also provide the models trained on the reduced set (5932 complexes). Results on test sets (CSV & PDF files): We provide the predictions on the PDBbind v.2016 core set. For spatiotemporal learning methods (Timenucy and Videonucy), there are predictions for only 83 complexes, as we did not perform simulations on the whole test set. For models trained with MD DA, predictions were carried on the crystallographic structures as well as on the frames extracted from the simulations performed on the test set (augmented test). Results on the FEP dataset are also provided for Pafnucy, Proli and Densenucy. The Raw MD data (~4.5 To) are stored, and can be visualized/downloaded, on the MDDB. This work was performed using HPC resources from GENCI-IDRIS (Grant 2021-A0100712496 & 2022-AD011013521) and CRIANN (Grant 2021002).本泽诺多（Zenodo）仓库为发表于《生物信息学（Bioinformatics）》的论文《基于分子动力学模拟的时空学习用于蛋白质-配体结合亲和力预测》提供了全面的研究资源。 我们通过对6300个复合物开展10次时长10纳秒的分子动力学模拟（molecular dynamics simulations），构建了包含63000组模拟数据的数据集。后续开发了神经网络（neural networks）以从该数据中学习，实现蛋白质-配体复合物的结合亲和力预测。相关神经网络的实现代码已托管至GitHub。本数据集涵盖训练/基准数据集、已训练的统计模型以及测试集结果（CSV与PDF格式文件）。 ## 训练与基准数据集 我们提供训练集、验证集与测试集，用于训练和评估以下神经网络： 1. 未使用分子动力学数据增强（MD data augmentation）的Pafnucy、Proli与Densenucy（数据集文件名包含"initial"） 2. 使用分子动力学数据增强的Pafnucy、Proli与Densenucy（数据集文件名包含"MDDA"） 3. 带/不带分子动力学数据增强的Pafnucy，以及使用分子动力学数据增强的Proli与Densenucy，均在FEP测试集上完成评估（测试集文件名包含"fep"） 4. 采用时空学习方法的Timenucy与Videonucy（数据集文件名包含"4D"） 5. 未使用分子动力学数据增强且基于缩减训练集的Pafnucy（数据集文件名包含"reduced"） 针对每种训练范式（分子动力学数据增强与时空学习），我们分别提供完整复合物、仅配体或仅蛋白质的数据集。此外针对时空学习任务，我们还提供了采用追踪模式、仅基于配体的数据集。 ## 统计模型 我们提供了基于Pafnucy、Proli、Densenucy、Timenucy与Videonucy训练得到的模型，所有模型均进行了10次重复训练。 - 针对Pafnucy、Proli与Densenucy，我们提供了采用随机旋转与系统旋转训练，且带/不带分子动力学数据增强的模型版本。 - 针对Proli、Densenucy、Timenucy与Videonucy，我们提供了基于完整复合物、仅配体或仅蛋白质训练得到的模型。 - 针对Pafnucy，我们还提供了基于缩减训练集（5932个复合物）训练得到的模型。 ## 测试集结果（CSV与PDF格式文件） 我们提供了在PDBbind v.2016核心集上的预测结果。 - 针对时空学习方法（Timenucy与Videonucy），由于未对全部测试集开展模拟，仅提供了83个复合物的预测结果。 - 针对使用分子动力学数据增强训练的模型，我们分别在晶体结构以及从测试集模拟中提取的轨迹帧（增强测试集）上完成了预测。 我们还提供了Pafnucy、Proli与Densenucy在FEP数据集上的预测结果。 原始分子动力学数据（约4.5太字节）已存储于MDDB平台，可在此进行可视化与下载。 本研究使用了来自GENCI-IDRIS（资助号2021-A0100712496与2022-AD011013521）以及CRIANN（资助号2021002）的高性能计算（High Performance Computing，HPC）资源。