TabPFN is a foundation model trained on around 130,000,000 synthetically generated datasets that mimic “real world” tabular data. These datasets sampled dataset size and number
Tag: cheminformatics
A recent paper published in Nature caught my eye, Accurate predictions on small data with a tabular foundation model by Hollmann et al., Here we present
BMCS are hosting an exciting “Conformational Design in Drug Discovery” conference at the AstraZeneca DISC in Cambridge, UK on March 3, 2025. Abstract submission deadline
A very nice review of generative models for molecular design from Morgan Thomas. https://cheminformantics.blogspot.com/2024/12/structure-aware-generative-molecular.html Includes Jupyter notebooks for data and analysis.
Whilst Apple’s emulation later Rosetta2 that allows X86_64 applications to run on Apple Silicon this is not ideal especially for computationally intensive tasks. The latest
The CICAG Newsletter, which had its origins in the 1990s (when CICAG was two groups, the ‘Chemical Information Group’ and the ‘Computer Applications Subject Group’).
An interesting publication, using the IUPAC rules for naming compounds can be a challenge for for complex systems. This paper describes a transformer-based model https://doi.org/10.1186/s13321-024-00941-x
AlvaDesc v3.0.0 has been updated, it has a few new features but for Mac users it is now fully compatible with Apple Silicon!! AlvaDesc is
A really interesting preprint caught my attention from Connor Coley’s group at MIT. ShEPhERD diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design https://arxiv.org/abs/2411.04130v1 …
Sometimes when I’m comparing multiple datasets I end up with 10-20 different Vortex workspaces, for example if I’m comparing commercial screening collections from different vendors.