End-to-end AI framework for interpretable prediction of molecular and crystal properties
This provides researchers with a unified, open-source tool for accelerated AI-driven material discovery in high-performance computing environments, though it is incremental as it combines existing models into a framework.
The authors tackled the challenge of predicting molecular and crystal properties by developing an end-to-end AI framework that integrates hyperparameter optimization, accelerated training, and interpretable inference, demonstrating its application on benchmark datasets like QM9, hMOF, and MD17 for small molecules, crystals, and metal-organic frameworks.
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.