DiffDock and DiffPack
About DiffDock
gcorso/DiffDock
Implementation of DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
DiffDock helps drug discovery scientists and computational chemists predict how a small molecule (ligand) binds to a protein, which is crucial for drug design. You input a protein structure (or sequence) and a ligand (as a SMILES string or file), and it generates the likely 3D binding poses of the ligand within the protein's active site. This is used by researchers in pharmaceutical and biotech fields to screen potential drug candidates.
About DiffPack
DeepGraphLearning/DiffPack
Implementation of DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing
This tool helps computational biologists and drug designers predict the precise 3D structure of protein side-chains, which are crucial for protein function. You provide protein backbone structures (PDB files), and it outputs the predicted side-chain conformations. This helps researchers understand how proteins interact and design new molecules.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work