---
title: README
emoji: 🚀
colorFrom: green
colorTo: yellow
sdk: static
pinned: false
---

<div align="center">

# MISATO - Machine learning dataset of protein-ligand complexes for structure-based drug discovery 

</div>
 
## 🌏  Where we are:
- Quantum Mechanics: 19443 ligands, curated and refined
- Molecular Dynamics: 16972 simulated protein-ligand structures, 10 ns each 
- AI: pytorch dataloaders, 2 base line models for MD and QM

## ⚛️ Vision:
We are a drug discovery community project :hugs:
- highest possible accuracy for ligand molecules
- represent the systems dynamics in reasonable timescales
- innovative AI models for drug discovery predictions
- lets build useful and fun spaces for everyone 🚀

Lets crack the **100+ ns** MD, **30000+ protein-ligand structures** and a whole new world of **AI models for drug discovery** together.

[Check out the paper!](https://www.biorxiv.org/content/10.1101/2023.05.24.542082v2)

![Alt text](logo.jpg?raw=true "MISATO")

## 💜 Community

Want to get hands-on for drug discovery using AI?


[Join our discord server!](https://discord.gg/tGaut92VYB)


## 📌  Introduction 
 

You can freely download the **MISATO-dataset** from [Zenodo](https://zenodo.org/record/7711953):

- MD (133 GiB)
- QM (0.3 GiB)
- electronic densities (6 GiB)
- MD restart and topology files (55 GiB)