Skip to content

Chem & Materials AI Resources

This site collects free, open, and community-friendly resources for people starting at the interface between:

  • chemistry and machine learning / AI
  • materials science and machine learning / AI

Use this as a jumping-off point for self-study, group reading lists, or onboarding new researchers to the field.

Use the navigation on the left to explore resources by topic area, or browse the full resource index.

If you have suggestions for new resources to add, please open an issue or read the contribution guidelines to submit a pull request.

Starting from Scratch?

If you're new to programming, machine learning, or chemistry/materials science, consider starting with some foundational resources:

  • Learn basic Python, specifically for chemists
    Start with Introduction to Python for Chemists (Imperial College) – a very gentle, notebook-based introduction aimed at chemistry students, with exercises and chemical examples.

  • Have an official reference that always matches the latest Python version
    Use The Python Tutorial (Official Documentation) alongside the Imperial notes as a companion reference. It’s maintained with each Python release and gives a clean, language-level view of the core concepts.

  • Get an intuition for what “machine learning” means in plain language
    Read Machine Learning for Everyone (In Simple Words) – a long-form blog post that explains ML concepts without equations, focusing on analogies and real-world examples.

  • Work through a structured, project-based ML course
    Once you’re comfortable with basic Python and high-level ideas, follow Machine Learning for Beginners (Microsoft) – a 12-week, project-driven curriculum using scikit-learn, with notebooks, quizzes and assignments.

  • Apply Python and ML ideas directly to chemistry data
    When you want to connect this back to real chemical problems, try Data-Driven Chemistry (University of Edinburgh), which uses Jupyter notebooks and chemistry datasets to practise Python, plotting and basic data analysis in a chemistry context.

Acknowledgements

This project is maintained by Dan Davies and the AIchemy Hub.

Thanks to Austin Mroz whose ML4Chem Starter Resources formed a starting point for this collection.

Thanks also to Aron Walsh for his list of resources for machine learning and materials.

Other contributors:

  • Alex Ganose
  • Kim Jelfs

Last updated: 2026-03-03 11:48 UTC