VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.

529-0150-00L 6 Credits MSC D-CHAB , D-MATH

Digital Chemistry

Lecturers & Examiners: Prof. Dr. Kjell Jorner
VVZ CR n/a

Last Updated: 2026-06-03 00:14:04

Abstract

This course introduces the topic of digital chemistry, an emerging interdisciplinary field that intersects machine learning, cheminformatics, computational chemistry and software development. In contrast to specialized courses on these separate topics, this course focuses on how to combine the best tools and approaches of each field to solve chemical problems.

Objective

Students will gain fundamental knowledge of digital chemistry and will be well-prepared to engage with subject specialists in academia or industry. They will know how to work with and visualize chemical data and train predictive and generative machine learning models. Students will learn how to apply critical thinking and sound skepticism to build well-grounded and validated models. By completing a hands-on project, students will get practical experience of leading a machine learning project from start to finish.

Content

- Introduction to Python for chemists - Practical cheminformatics - Introduction to data curation, extraction, and management - Generating representations and simulated data with computational chemistry methods - Classical supervised and unsupervised machine learning - Advanced machine learning: neural networks, graph models, language models - Explainable AI - Applications of digital chemistry to property and reaction prediction, molecular design and experimental design

Resources

Lecture Notes

Lecture notes will be provided.

Literature

The course is based on the lectures notes, and accompanying code notebooks, but the following books can be used as reference: - K. A. Tanemura, D. Sierra-Costa, K. M. Merz Jr., Python for Chemists - J. P. Janet, H. J. Kulik, Machine Learning in Chemistry - G. M. Jones, B. Story, V. Maroulas, K. D. Vogiatzis, Molecular Representations for Machine Learning - S. Raschka, Y. Liu, V. Mirjalili, Machine Learning with PyTorch and Scikit-Learn - A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd Edition - A. D. White, Deep Learning for Molecules & Materials - G. James, D. Witten, T. Hastie, R. Tibshirani, An Introduction to Statistical Learning - T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning - Y. S. Abu-Mostafa, M. Magdon-Ismail, H.-T. Lin, Learning From Data

General Information

Language
English
Levels
MSC
Frequency
Yearly recurring

Examination

Type
session examination
Mode
oral 30 minutes
The session examination counts for 70% of the final grade and the project for 30%. The project is also graded from 1.0 to 6.0 and must be passed on its own. It involves a (a) report and (b) a poster presentation.

Course Components

Type Title Time & Place Hours
lecture with exercise Digital Chemistry
  • Tue 12:45-13:30 (HCI D 2)
  • Thu 13:45-15:30 (HPV G 5)
3 h weekly

Offered In