Codes for our paper "Programming Biomolecular Interactions with All-Atom Generative Model"

Comprehensive library for fast, GPU accelerated molecular gridding for deep learning workflows

Code for running RFdiffusion

Toward High-Accuracy Open-Source Biomolecular Structure Prediction.

[NeurIPS2025 Spotlight 🔥 ] Official implementation of "UniSite: The First Cross-Structure Dataset and Learning Framework for End-to-End Ligand Binding Site Detection"

Differentiable, Hardware Accelerated, Molecular Dynamics

A Euclidean diffusion model for structure-based drug design.

MaSIF- Molecular surface interaction fingerprints. Geometric deep learning to decipher patterns in molecular surfaces.

Knowledge-Guided Diffusion Model for 3D Ligand-Pharmacophore Mapping

Extensible Surrogate Potential of Ab initio Learned and Optimized by Message-passing Algorithm 🍹https://arxiv.org/abs/2010.01196

Official Github for "PharmacoNet: deep learning-guided pharmacophore modeling for ultra-large-scale virtual screening" (Chemical Science)

End-To-End Molecular Dynamics (MD) Engine using PyTorch

EquiBind: geometric deep learning for fast predictions of the 3D structure in which a small molecule binds to a protein

A deep learning framework for molecular docking

Deep Site and Docking Pose (DSDP) is a blind docking strategy accelerated by GPUs, developed by Gao Group. For the site prediction part, several modifications are introduced to PUResNet program. The pose sampling part is similar as AutoDock Vina combined with a number of modifications.

IF-SitePred is a method for predicting ligand-binding sites on protein structures. It first generates an embedding for each residue of the protein using the ESM-IF1 (inverse folding) model, then performs point cloud clustering to identify binding site centers.

Prediction of binding residues for metal ions, nucleic acids, and small molecules.

NequIP is a code for building E(3)-equivariant interatomic potentials