ViewTube

Welcome to PracticalCheminformatics!  Machine-learning (ML) and automation are becoming prevalent in academic and industrial research, from pharmaceuticals and agrochemicals, to solar cells and batteries. Cheminformatics has the potential to drastically improve the efficiency of chemists, however many scientists are not trained in the implementation of these tools (Python, GPUs, etc). To fill in this gap, I started PracticalCheminformatics, a practical guide to running free-to-use, open-source cheminformatics software. Using cloud computing resources via Google Colab notebooks, you will learn how to design new drug molecules, run automated molecular dynamics simulations, ML-assisted virtual screening, predict AI-based ADMET properties, use AI-guided retrosynthesis to guide your chemistry, use Bayesian Optimisation to guide your experiments, and much more! Whether you are new to the field or an experienced computational chemist, join the learning journey and enjoy the process!