InDeepNet

InDeepNet predicts functional binding sites in proteins using deep learning models InDeep and InDeepHolo.

Key Features:

• Binding Site Prediction: InDeep predicts potential binding sites for proteins or small molecules from uploaded protein structures.
• Holo Conformation Assessment: InDeepHolo evaluates a site's propensity to adopt a ligand-bound (holo) conformation, helping select conformations optimal for small-molecule binding.
• Structure Input Support: Accepts protein structures from in-house data, the Protein Data Bank (PDB), or AlphaFold.
• Interactive 3D Visualization: Results are presented as interactive 3D visualizations via Mol*.

Scientific Applications:

• Protein-Protein Interaction Analysis: Predicts functional binding sites to understand protein-protein interactions (PPIs).
• Drug Target Identification: Assesses PPI ligandability to identify potential drug targets.
• Structure-Based Drug Design: Improves structure-based drug design by selecting conformations optimal for small-molecule binding.
• Therapeutic Development: Supports therapeutic development targeting PPIs by streamlining PPI target assessment and ligandability prediction.

Methodology:

InDeepNet integrates InDeep, a deep-learning model for binding site prediction, with InDeepHolo, which evaluates a site's propensity to adopt a ligand-bound (holo) conformation.