Supervised machine learning techniques are increasingly being adopted to speed up electronic structure predictions, serving as alternatives to first-principles methods like Density Functional Theory (DFT). Although current DFT datasets mainly emphasize chemical properties and atomic forces, the precise prediction of electronic charge density is essential for accurately determining a system's total energy and ground state properties. In this study, we introduce a novel electronic charge density dataset named ECD, which encompasses 140,646 stable crystal geometries with medium-precision Perdew–Burke–Ernzerhof (PBE) functional data. Within this dataset, a subset of 7,147 geometries includes high-precision electronic charge density data calculated using the Heyd–Scuseria–Ernzerhof (HSE) functional in DFT. By designing various benchmark tasks for crystalline materials and emphasizing training with large-scale PBE data while fine-tuning with a smaller subset of high-precision HSE data, we demonstrate the efficacy of current machine learning models in predicting electronic charge densities. The ECD dataset and baseline models are open-sourced to support community efforts in developing new methodologies and accelerating materials design and applications.

Aiming at the high complexity of the real-time driver detection model for highway autonomous card acceptance robots, which is difficult to be deployed on limited resource devices, this paper proposes a lightweight driver and window detection algorithm based on YOLOv5s. The algorithm combines the C3P and GS modules of PConv and GhostNet, introduces a parameter-free attention mechanism, extracts multi-scale features from the network, focuses on the target information, and the GS module performs feature fusion with DWConv to replace the feature fusion part in the original YOLOv5s network, and introduces a non-parametric attention mechanism of the PfAAMLayer in the Detect part, improving the ability to generalise models.and finally the FGS-pf-YOLOv5s network is constructed by using SIoU (Scale-Invariant Objective for Union) loss to better deal with the occlusion and overlapping problems between targets, which reduces the number of network parameters and the GFLOPs while maintaining the model recognition accuracy, and reduces the number of GFLOPs in the network. number and GFLOPs, reducing the size of the model. The experimental results show that the parameters of the PGS-pf-YOLOv5s model proposed in this paper are reduced by 68%, the GFLOPs are reduced by 51 %, and the size of the weight file is only 4.7 4M, which is reduced by 67% compared with the source code, but the Map50 is improved by 0.2% compared with the source code on the basis of lightweighting, This shows that the model in this paper can solve the model deployment problem while achieving real-time target detection and maintain the same high accuracy.

SUMMARY: VSTH is a user-friendly web server with the complete workflow for virtual screening. By self-customized visualization software, users can interactively prepare protein files, set docking sites as well as view binding conformers in a target protein in a few clicks. We provide serval purchasable ligand libraries for selection. And, we integrate six open-source docking programs as computing engine, or as conformational sampling tools for DLIGAND2. Users can select various docking methods simultaneously and personalize computing parameters. After docking processing, user can filter docking conformations by ranked scores, or cluster-based molecular similarity to find highly populated clusters of low-energy conformations. AVAILABILITY AND IMPLEMENTATION: The VSTH web server is free and open to all users at https://matgen.nscc-gz.cn/VirtualScreening.html. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.