About This Course

Welcome to the Materials Informatics Advanced Practical course! This repository contains a comprehensive set of tutorials and exercises designed to help you explore the exciting intersection of materials science, machine learning, and artificial intelligence. You will learn how to leverage computational tools to accelerate the discovery of new materials, focusing primarily on the SMACT (Semiconducting Materials from Analogy and Chemical Theory) toolkit. SMACT offers a collection of rapid screening and informatics tools utilizing chemical element data to facilitate materials exploration.

Beyond SMACT, this course provides comprehensive coverage of advanced computational methods including Machine Learning Force Fields (MACE) and Density Functional Theory (DFT), giving you a complete toolkit for modern materials research. Whether you're screening millions of compositions, generating crystal structures with AI, or running quantum mechanical simulations, this course has you covered.

Course Overview

This course covers:

• Combinatorial explosion in materials discovery
• Chemical filtering techniques
• Compositional and stoichiometry screening
• Structure prediction and generation
• Advanced computational methods including:
  • Machine Learning Force Fields (MACE)
  • Density Functional Theory (DFT)
  • VASP computational framework

Repository Structure

• Pre-course/: Setup instructions and course overview
• Combinatorial Explosion/: Understanding vast chemical spaces
• Chemical Filters/: Applying chemical rules for screening
• Compositional Screening/: Systematic materials exploration
• Stoichiometry Screening/: Structure-based screening
• Composition to Structure/: Prediction and generation methods
• Advanced Methods/: Advanced computational techniques
  • DFT/: Density Functional Theory fundamentals and VASP overview
  • MLFF/: Machine Learning Force Fields with MACE tutorials

Getting Started

Please refer to the Setup Instructions for installation and configuration details.

License

This project is licensed under the MIT License - see the LICENSE file for details.

References

H. Park et al., "Exploration of crystal chemical space using text-guided generative artificial intelligence" Nat. Commun. (2025)

H. Park et al., "Mapping inorganic crystal chemical space" Faraday Discuss. (2024)

D. W. Davies et al., "SMACT: Semiconducting Materials by Analogy and Chemical Theory" JOSS 4, 1361 (2019)

D. W. Davies et al., "Materials discovery by chemical analogy: role of oxidation states in structure prediction" Faraday Discuss. 211, 553 (2018)

D. W. Davies et al., "Computational screening of all stoichiometric inorganic materials" Chem 1, 617 (2016)

Acknowledgments

• SMACT & Chemeleon developers

• The open source community that build many of the libraries used herein, especially the jupyter-book community

• The Materials Design Group and especially Aron Walsh, Hyunsoo Park and Anthony Onwuli for their guidance, mentorship and supervision.