MolFM
Implementation for NeurIPS 2023 paper "Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation"
Install / Use
/learn @GenSI-THUAIR/MolFMREADME
Implementation for the paper "Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation"
Prerequisite
You will need to have a host machine with gpu, and have a docker with nvidia-container-runtime enabled.
[!TIP]
- This repo provide an easy to use script to install docker and nvidia-container-runtime, in
./MolFM/dockerrunsudo ./setup_docker_for_host.shto setup your host machine.- You can also refer to install guide if you don't have them installed.
Quick start
Environment setup
Clone the repo with git clone,
git clone https://github.com/AlgoMole/MolFM.git
setup environment with docker,
cd ./MolFM/docker
make # a make is all you need
[!NOTE]
The
makewill automatically build the docker image and run the container. with your host home directory mounted to the${HOME}/homedirectory inside the container. highly recommendedIf you need to setup the environment manually, please refer to files
docker/Dockerfile,docker/asset/requirements.txtanddocker/asset/apt_packages.txt.
