A new release of FEgrow that adds active learning together with acceleration powered by Dask (multi -cpu, -node, -cluster).
To get started with the new functionality, see the tutorials folder, which contains examples of i) basic interactive molecular design, ii) an introduction to the chemspace functionality, and iii) an example of active learning for inhibitor design.
Cree B, Bieniek M, Amin S, Kawamura A, Cole D. Active learning driven prioritisation of compounds from on-demand libraries targeting the SARS-CoV-2 main protease. ChemRxiv. 2024; doi:10.26434/chemrxiv-2024-xczfb This content is a preprint and has not been peer-reviewed.
https://doi.org/10.26434/chemrxiv-2024-xczfb
An interactive workflow for building user-defined congeneric series of ligands in protein binding pockets for input to free energy calculations.
Bieniek, Mateusz K., Ben Cree, Rachael Pirie, Joshua T. Horton, Natalie J. Tatum, and Daniel J. Cole. "An open-source molecular builder and free energy preparation workflow." Communications Chemistry 5, no. 1 (2022): 136.
https://doi.org/10.1038/s42004-022-00754-9
Please see cole-group.github.io/fegrow for full installation instructions, documentation and acknowledgements.