Dataset - Papyrus - A large scale curated dataset aimed at bioactivity predictions

This repository contains version 05.6 of the Papyrus dataset, an aggregated dataset of small molecule bioactivities, as described in the preprint "Papyrus - A large scale curated dataset aimed at bioactivity predictions". Changes compared to version 05.5 - applied small molecule filter that filters out compounds with a MW < 200 or > 800, heavy metal containing compounds and mixtures - include TID column which contains information on the original protein identifier