A while back Apple published a paper entitled LLM in a flash: Efficient Large Language Model Inference with Limited Memory [DOI] This paper tackles the
Month: March 2026
This meeting will be held at Burlington House, London, UK on Wednesday 8th April 2026. A one-day conference on Chemical Structure Representations will bring together
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
OpenFold3-preview is a biomolecular structure prediction model aiming to be a bitwise reproduction of DeepMind’sAlphaFold3, developed by the AlQuraishi Lab at Columbia University and the
ChemeleonSMD distills the CheMeleon pretrained Directed Message Passing Neural Network (DMPNN) into a SCORE-style architecture running natively on MLX. The SCORE Euler skip connection replaces ChemProp’s hard-overwrite message passing
The Protein Data Bank is an invaluable resource for protein structural information. As well as being a resource used by structural biologists, medicinal chemists and
Recently a guest post from NVIDIA described GPU-Accelerated Clustering with nvMolKit that uses CUDA. A recent post no describes a port of the nvMolKit (CUDA) molecular clustering
In 2020 as a result of lockdown I was asked to help create a course for MRes students as an introduction to computer-aided drug design.
AI/ML have reignited our thoughts on how we represent chemical structures and so it is very timely that we have a conference on Structural Representation.
Just got this message. We’re happy to announce the release of macOS-native MOE 2024.0604 for macOS Tahoe, also compatible with Big Sur and later versions