I’ve written several posts on the various options for clustering molecules https://macinchem.org/?s=clustering and a recent post from NVIDIA described GPU-Accelerated Clustering with nvMolKit that uses
Tag: MLX
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
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