scientific-graph-neural-networks

What problem does it solve?

Graph-based deep learning workflows enable predictive modeling and insight extraction from complex scientific data, unifying molecular graphs, protein structures, and knowledge graphs under a single GNN-centric approach.

Core Features & Use Cases

• GNN model implementations for molecular property prediction, protein function prediction, and knowledge-graph inference.
• End-to-end workflows covering data construction, model selection, training, evaluation, and interpretation.
• Use Case: predict solubility or activity on molecular graphs or infer relationships in biological knowledge graphs.

Quick Start

Train a graph neural network on your molecular or protein graph data to predict properties and perform knowledge-graph reasoning.