DD-GUI

DD-GUI applies Deep Docking (DD) deep learning methods to accelerate virtual screening of ultra-large chemical libraries for drug discovery.

Key Features:

• Deep Docking (DD) integration: Implements the Deep Docking (DD) methodology for prioritizing compounds in virtual screens.
• Deep learning-accelerated screening: Uses deep learning to accelerate virtual screening and compound prioritization compared with conventional workflows.
• Binding affinity prediction: Predicts binding affinities with high accuracy and speed using learned models.
• Scalability to ultra-large libraries: Enables screening of ultra-large chemical libraries, including evaluation of billions of compounds.
• Reduced computational burden: Lowers computational cost and time relative to traditional docking approaches.

Scientific Applications:

• Early-stage lead identification: Supports identification of potential lead compounds in early-stage drug discovery by prioritizing candidates from very large libraries.
• Large-scale virtual screening campaigns: Facilitates large-scale virtual screening projects that require evaluation of billions of molecules.

Methodology:

Based on the Deep Docking (DD) deep learning approach, which predicts binding affinities to prioritize compounds and thereby reduces the computational burden of traditional docking to enable screening of billions of molecules.