---
title: "A Universal Graph Deep Learning Interatomic Potential for the Periodic Table"
description: "Here, we report a universal IAP for materials based on graph neural networks with three-body interactions (M3GNet). The M3GNet IAP was trained on the massive database of structural relaxations performed by the Materials Project over the past 10 years and has broad applications in structural relaxati"
url: "https://ouro.foundation/files/mmoderwell/a-universal-graph-deep-learning-interatomic-potential-for-the-periodic-table"
id: "31bc8f4d-0e5a-45d3-94de-5f5c11fef14d"
type: "file"
---

# A Universal Graph Deep Learning Interatomic Potential for the Periodic Table

File by @mmoderwell in #superconductors (all) · .pdf · 12.4 MB

- Asset id: `31bc8f4d-0e5a-45d3-94de-5f5c11fef14d`
- Page: https://ouro.foundation/files/mmoderwell/a-universal-graph-deep-learning-interatomic-potential-for-the-periodic-table

Here, we report a universal IAP for materials based on graph neural networks with three-body interactions (M3GNet). The M3GNet IAP was trained on the massive database of structural relaxations performed by the Materials Project over the past 10 years and has broad applications in structural relaxation, dynamic simulations and property prediction of materials across diverse chemical spaces.

Chi Chen & Shyue Ping Ong

https://www.nature.com/articles/s43588-022-00349-3

Preprint version from arXiv

## Use it

- Download: https://database.ouro.foundation/storage/v1/object/public/public-files/847f4445-78ee-41b1-913b-5bd155c71b13/033291b1-74dd-4eb1-8a47-0a322e5f9639.pdf?v=1735702404544
- Over Ouro MCP: `download_asset(id="31bc8f4d-0e5a-45d3-94de-5f5c11fef14d")` returns the file or a download link.
- Find routes that take it: `get_compatible_routes(asset_id="31bc8f4d-0e5a-45d3-94de-5f5c11fef14d")`, then pass it as `input_assets={"file": "31bc8f4d-0e5a-45d3-94de-5f5c11fef14d"}`.
- From Python: `ouro.files.retrieve("31bc8f4d-0e5a-45d3-94de-5f5c11fef14d")`
