Lack of data has hampered the building of models to accurately predict binding affinity so I’m sure everyone is super excited to see the first
Tag: machine learning
An interesting way to look for better biological foundation models. The core bet is simple: biological data is expensive. Text and image models often improve
A recent paper on ChemRxiv https://chemrxiv.org/doi/10.26434/chemrxiv-2025-9c1v6 describes ANNalog a transformer-based sequence-to-sequence generative model trained on pairs of molecules extracted from the same bioactivity assay in
The next OpenADMET blind challenge focuses on predicting human Pregnane-X Receptor (hPXR) induction. The pregnane X receptor (hPXR) is the major determinant of CYP3A gene regulation by
This looks like an amazing opportunity. Apply to lead a strategic research lab dedicated to advancing the UK’s position in fundamental artificial intelligence (AI) development.
An interesting web app that fetches ChEMBL bioactivity data for a target (via UniProt ID), computes molecular descriptors, and trains a simple predictive model (regression, with
Prediction of the metabolism of small molecules is very challenging and so having a variety of different tools is always useful. I’ve previously written Vortex
PROteolysis TArgeting Chimeras (PROTACs) technology provides an alternative to module biological function by specially using the ubiquitin proteasome system to induce degradation of the target
Next up Date: 5 February 2026 Lecture Theatre, Jeffrey Cheah Biomedical Centre, Puddicombe Way, Cambridge CB2 0AW. No need to register in advance – just
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