Cambridge Open Engage is the collaborative platform to upload, share and advance early and open research and a recent post caught my eye.
Molecular set representation learning https://doi.org/10.26434/chemrxiv-2023-fk7kf MolSetRep is a Python library that provides encoders and machine learning models for molecular set representation learning.
Here, we propose a framework for molecular machine learning tasks based on set representation learning. We show that learning on sets of atomic invariants alone reaches the performance of state-of-the-art graph-based models on the most-used chemical benchmark data sets and that introducing a set representation layer into graph neural networks can surpass the performance of established methods in the domains of chemistry, biology, and material science.
All code and example jupyter notebooks for Molsetrep are on GitHub and it can be installed using pip
https://github.com/daenuprobst/molsetrep
|
1 |
pip install molsetrep |
The code has been tested on Windows 11, Ubuntu 22.04, and macOS 13.
The examples include Molecular property prediction, Protein-ligand binding affinity prediction and Reaction yield prediction.