Reproduce “RangeFinder: Predicting Ligand Property Ranges from Protein Pockets” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Alan Nadelsticher Ruvalcaba, Chris Alvin, Supratik Mukhopadhyay, Adam Bess
RangeFinder predicts property ranges for nine ligand properties from protein pockets, rather than generating or scoring individual molecules. It learns intervals from known ligands and uses pocket structure to estimate them. On 564 held-out BioLiP2 pockets, it improves Range-IoU and RRF over APoc, while APoc achieves greater library reduction; evaluation requires at least three known ligands per pocket.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.