End-to-end AI framework for interpretable prediction of molecular and crystal properties
arXiv:2212.11317 · doi:10.1088/2632-2153/acd434
Abstract
We introduce an end-to-end computational framework that allows for hyperparameter optimization using the DeepHyper library, accelerated model training, and interpretable AI inference. The framework is based on state-of-the-art AI models including CGCNN, PhysNet, SchNet, MPNN, MPNN-transformer, and TorchMD-NET. We employ these AI models along with the benchmark QM9, hMOF, and MD17 datasets to showcase how the models can predict user-specified material properties within modern computing environments. We demonstrate transferable applications in the modeling of small molecules, inorganic crystals and nanoporous metal organic frameworks with a unified, standalone framework. We have deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and in the Delta supercomputer at the National Center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership-class computing environments. We release these digital assets as open source scientific software in GitLab, and ready-to-use Jupyter notebooks in Google Colab.
20 pages, 10 images, 6 tables; v2: accepted to Machine Learning: Science and Technology
References in corpus (7)
- Atomistic Line Graph Neural Network for Improved Materials Property Predictions
- Graph Neural Network Predictions of Metal Organic Framework CO2 Adsorption Properties
- Accelerated, Scalable and Reproducible AI-driven Gravitational Wave Detection
- FAIR principles for AI models with a practical application for accelerated high energy diffraction microscopy
- Roughness of molecular property landscapes and its impact on modellability
- ComENet: Towards Complete and Efficient Message Passing for 3D Molecular Graphs
- GraphTSNE: A Visualization Technique for Graph-Structured Data