I’ve reviewed TabPFN in the past. https://macinchem.org/2025/02/06/looking-at-tabpfn and I noticed there was a recent update. TabPFN is a foundation model trained on around 130,000,000 synthetically generated
Category: Hints and Tutorials
Tutorials, Hints, Tips and Tricks
The excellent MayChemTools has been updated MayaChemTools is a growing collection of Perl and Python scripts, modules, and classes to support a variety of day-to-day computational discovery needs. The
One of the most useful databases for anyone involved in studies involved in biologically active molecules. ChEMBL is a manually curated database of bioactive molecules
Apple just posted preprint on arxiv describing a new protein structure prediction tool SimpleFold https://arxiv.org/pdf/2509.18480. All code is available on GitHub https://github.com/apple/ml-simplefold including a simple
A couple of readers have mentioned issues with using XQuartz after upgrading to macOS Tahoe. Looking on GitHub there are a couple issues. https://github.com/XQuartz/XQuartz/issues/446 https://github.com/XQuartz/XQuartz/issues/438
An interesting post from Nvidia. nvMolKit, is a standalone, GPU-accelerated library that delivers 1-4 orders of magnitude of acceleration across five key functions: Morgan Fingerprinting,
A recent excellent blog post highlighted the use of a KNIME workflow. KNIME https://www.knime.com is a workflow platform that can be used for many cheminformatics
The ORCA Python Interface (OPI) is a Python library to create input and parse output of ORCA. It is designed as an open source community effort
When making selections from large datasets it is worth mentioning that as datasets get larger a simple random selection is often the best (and quickest)