Learn how to interact with PU-CGCNN using the Ouro SDK or REST API.
API access requires an API key. Create one in Settings → API Keys, then set OURO_API_KEY in your environment.
Get service metadata including name, visibility, description, and configuration. You can retrieve by service ID or identifier.
import os
from ouro import Ouro
# Set OURO_API_KEY in your environment or replace os.environ.get("OURO_API_KEY")
ouro = Ouro(api_key=os.environ.get("OURO_API_KEY"))
# Option 1: Retrieve by service ID
service_id = "03dd8a31-f0f7-4c78-9e73-0cf41c808986"
service = ouro.services.retrieve(service_id)
# Option 2: Retrieve by service identifier (username/service-name)
service_identifier = "mmoderwell/pu-cgcnn"
service = ouro.services.retrieve(service_identifier)
print(service.name, service.visibility)
print(service.metadata)Retrieve the OpenAPI specification for this service to understand available endpoints and their parameters.
Get all routes for this service and use them programmatically.
Click on an endpoint to view its detailed documentation.
# Retrieve the service
service = ouro.services.retrieve("mmoderwell/pu-cgcnn")
# Read the OpenAPI spec
spec = ouro.services.read_spec(service.id)
print(spec.get("openapi"))
print(spec.get("info"))# Retrieve the service
service = ouro.services.retrieve("mmoderwell/pu-cgcnn")
# Get all routes for this service
routes = ouro.services.read_routes(service.id)
for route in routes:
print(f"{route.route.method} {route.route.path}")
print(f" Summary: {route.route.summary}")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 Code: https://github.com/kaist-amsg/Synthesizability-PU-CGCNN
Usage
26 calls