Digital Chemistry

Preface

About

This is a preliminary script for course 529-0150-00L Digital Chemistry. Feedback on the content and its presentation is very welcome.

How to read this script

The chapters follow the machine-learning pipeline for chemistry: data, representation, model, validation, application. One point is worth stating before any of it, because it governs where effort is best spent:

⚠️ Order of impact: good data > good representations > good models.

Resources

This script cannot cover everything, but we refer the interested student to the following books for further study of the presented topics:

• 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