3D structure-based drug design (SBDD) is considered a challenging and rational way for innovative drug discovery. Geometric deep learning is a promising approach that solves the accurate model training of 3D SBDD through building neural network models to learn non-Euclidean data, such as 3D molecular graphs and manifold data. Here, we summarize geometric deep learning methods and applications that contain 3D molecular representations, equivariant graph neural networks (EGNNs), and six generative model methods [diffusion model, flow-based model, generative adversarial networks (GANs), variational autoencoder (VAE), autoregressive models, and energy-based models]. Our review provides insights into geometric deep learning methods and advanced applications of 3D SBDD that will be of relevance for the drug discovery community.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.drudis.2024.104024 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Deep reinforcement learning and robust SLAM based robotic control algorithm for self-driving path optimization.
Front Neurorobot
January 2025
School of Information and Communication Engineering, Hainan University, Haikou, China.
A reward shaping deep deterministic policy gradient (RS-DDPG) and simultaneous localization and mapping (SLAM) path tracking algorithm is proposed to address the issues of low accuracy and poor robustness of target path tracking for robotic control during maneuver. RS-DDPG algorithm is based on deep reinforcement learning (DRL) and designs a reward function to optimize the parameters of DDPG to achieve the required tracking accuracy and stability. A visual SLAM algorithm based on semantic segmentation and geometric information is proposed to address the issues of poor robustness and susceptibility to interference from dynamic objects in dynamic scenes for SLAM based on visual sensors.
View Article and Find Full Text PDFPowerful generative AI models of protein-ligand structure have recently been proposed, but few of these methods support both flexible protein-ligand docking and affinity estimation. Of those that do, none can directly model multiple binding ligands concurrently or have been rigorously benchmarked on pharmacologically relevant drug targets, hindering their widespread adoption in drug discovery efforts. In this work, we propose FlowDock, the first deep geometric generative model based on conditional flow matching that learns to directly map unbound (apo) structures to their bound (holo) counterparts for an arbitrary number of binding ligands.
View Article and Find Full Text PDFDevelopment of a handheld GPU-assisted DSC-TransNet model for the real-time classification of plant leaf disease using deep learning approach.
Sci Rep
January 2025
Amal Jyothi College of Engineering (Autonomous), Kanjirappally, Kerala, India.
In agriculture, promptly and accurately identifying leaf diseases is crucial for sustainable crop production. To address this requirement, this research introduces a hybrid deep learning model that combines the visual geometric group version 19 (VGG19) architecture features with the transformer encoder blocks. This fusion enables the accurate and précised real-time classification of leaf diseases affecting grape, bell pepper, and tomato plants.
View Article and Find Full Text PDFA Hybrid Approach for Sports Activity Recognition Using Key Body Descriptors and Hybrid Deep Learning Classifier.
Sensors (Basel)
January 2025
Cognitive Systems Lab, University of Bremen, 28359 Bremen, Germany.
This paper presents an approach for event recognition in sequential images using human body part features and their surrounding context. Key body points were approximated to track and monitor their presence in complex scenarios. Various feature descriptors, including MSER (Maximally Stable Extremal Regions), SURF (Speeded-Up Robust Features), distance transform, and DOF (Degrees of Freedom), were applied to skeleton points, while BRIEF (Binary Robust Independent Elementary Features), HOG (Histogram of Oriented Gradients), FAST (Features from Accelerated Segment Test), and Optical Flow were used on silhouettes or full-body points to capture both geometric and motion-based features.
View Article and Find Full Text PDFPredicting and synthesizing terahertz spoof surface plasmon polariton devices with a convolutional neural network model.
Sci Rep
January 2025
Department of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, 14115-194, Iran.
With the increasing global attention to deep learning and the advancements made in applying convolutional neural networks in electromagnetics, we have recently witnessed the utilization of deep learning-based networks for predicting the spectrum and electromagnetic properties of structures instead of traditional tools like fully numerical-based methods. In this study, a Convolutional Neural Network (CNN is proposed for predicting spoof surface plasmon polaritons, enabling the examination of the absorption spectrum of metallic multilevel-grating structures (MMGS) and designing various sensor devices and absorbers in the shortest time possible. To expedite the training process of this network, a semi-analytical method of rigorous coupled-wave analysis (RCWA) enhanced with the fast Fourier factorization (FFF) technique has been employed, significantly reducing the data generation time for training.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!