This is a systems pharmacology workflow that builds compound-target-disease networks to find drug repurposing candidates and analyze multi-target effects. It pulls data from STRING, ChEMBL, DGIdb, OpenTargets, and other databases, then runs Python to compute network proximity scores, identify hub genes, and rank repurposing opportunities on a 0-100 scale weighted toward clinical evidence and network distance. The framework explicitly distinguishes desired polypharmacology from off-target promiscuity, which is useful when you need to argue whether hitting multiple targets is therapeutic or just messy. Best for mechanistic hypotheses about existing drugs in new indications. If you just want repurposing candidates without the network math, there's a simpler skill for that.
npx skills add https://github.com/mims-harvard/tooluniverse --skill tooluniverse-network-pharmacology