---
title: "PU-CGCNN"
description: "Predicts a Crystal-Likeness Score (CLscore) for inorganic crystal structures using positive–unlabeled learning with bagged crystal graph convolutional neural networks (PU-CGCNN). CLscore ∈ [0, 1] estimates how “crystal-like” / synthesizable a structure is relative to experimentally reported material"
url: "https://ouro.foundation/services/mmoderwell/pu-cgcnn"
id: "03dd8a31-f0f7-4c78-9e73-0cf41c808986"
type: "service"
---

# PU-CGCNN

Service by @mmoderwell in #materials-science (all) · 0 public routes

- Asset id: `03dd8a31-f0f7-4c78-9e73-0cf41c808986`
- Page: https://ouro.foundation/services/mmoderwell/pu-cgcnn

Predicts a Crystal-Likeness Score (CLscore) for inorganic crystal structures using positive–unlabeled learning with bagged crystal graph convolutional neural networks (PU-CGCNN).

CLscore ∈ [0, 1] estimates how “crystal-like” / synthesizable a structure is relative to experimentally reported materials. It is complementary to thermodynamic filters such as energy above hull — high CLscore does not guarantee experimental success, but is a useful soft prior for screening and generative filtering.

Model: Jang et al., JACS 2020 (pretrained 100-bag ensemble). Paper: [https://doi.org/10.1021/jacs.0c07384](https://doi.org/10.1021/jacs.0c07384) Code: [https://github.com/kaist-amsg/Synthesizability-PU-CGCNN](https://github.com/kaist-amsg/Synthesizability-PU-CGCNN)

## Routes

A service is an API; each of its endpoints is a route you can run. Each route's page has a markdown twin with its inputs and parameters.