Vina-GPU 2.0: Further Accelerating AutoDock Vina and Its Derivatives with Graphics Processing Units.

Modern drug discovery typically faces large virtual screens from huge compound databases where multiple docking tools are involved for meeting various real scenes or improving the precision of virtual screens. Among these tools, AutoDock Vina and its numerous derivatives are the most popular and have become the standard pipeline for molecular docking in modern drug discovery. Our recent Vina-GPU method realized 14-fold acceleration against AutoDock Vina on a piece of NVIDIA RTX 3090 GPU in one virtual screening case. Further speedup of AutoDock Vina and its derivatives with graphics processing units (GPUs) is beneficial to systematically push their popularization in large-scale virtual screens due to their high benefit-cost ratio and easy operation for users. Thus, we proposed the Vina-GPU 2.0 method to further accelerate AutoDock Vina and the most common derivatives with new docking algorithms (QuickVina 2 and QuickVina-W) with GPUs. Caused by the discrepancy in their docking algorithms, our Vina-GPU 2.0 adopts different GPU acceleration strategies. In virtual screening for two hot protein kinase targets, RIPK1 and RIPK3, from the DrugBank database, our Vina-GPU 2.0 reaches an average of 65.6-fold, 1.4-fold, and 3.6-fold docking acceleration against the original AutoDock Vina, QuickVina 2, and QuickVina-W while ensuring their comparable docking accuracy. In addition, we develop a friendly and installation-free graphical user interface tool for their convenient usage. The codes and tools of Vina-GPU 2.0 are freely available at https://github.com/DeltaGroupNJUPT/Vina-GPU-2.0, coupled with explicit instructions and examples.

Transfer learning with molecular graph convolutional networks for accurate modeling and representation of bioactivities of ligands targeting GPCRs without sufficient data.

There are many new or potential drug targets in G protein-coupled receptors (GPCRs) without sufficient ligand associations, and it is essential and urgent to implement drug discovery targeting these GPCRs. Precise modeling and representing ligand bioactivities are essential for screening and optimizing these GPCR targeted drugs, yet insufficient samples made it difficult to achieve. Transfer learning intends to solve this by introducing rich information from related source domains with sufficient ligand training samples. In addition, ligand molecules naturally constitute a graph structure, which can be utilized by molecular graph convolutional networks to form an end-to-end multiple-level representation learning. This study proposed a novel method, TL-MGCN, using transfer learning with molecular graph convolutional networks to precisely model and represent bioactivities of ligands targeting GPCRs without sufficient data. The study tested TL-MGCN on a series of 54 representative target domain datasets which cover most human subfamilies, and 44 out of them have less than 600 ligand associations. TL-MGCN obtained an average improvement of 28.74%, 17.28%, 10.05%, 77.83%, 43.65% and 14.65% on correlation coefficient (r2) and 11.90%, 7.43%, 14.86%, 41.46%, 31.02% and 22.94% on root-mean-square error (RMSE) compared with the WDL-RF, transfer learning version of WDL-RF (TR-WDL-RF), attentive FP, GIN, Weave and MPNN predictors, respectively. Users have free access to the web server of TL-MGCN, along with the source codes and datasets, at http://www.noveldelta.com/TL_MGCN for academic purposes.