Accompanying data - Papyrus - A large scale curated dataset aimed at bioactivity predictions
DOI10.5281/zenodo.10943207Zenodo10943207MaRDI QIDQ6697735FDOQ6697735
Dataset published at Zenodo repository.
Bob van de Water, Brandon J. Bongers, Willem Jespers, Gerard J. P. van Westen, Ad P. Ijzerman, Olivier J. M. Béquignon
Publication date: 8 April 2024
Copyright license: Creative Commons Attribution-ShareAlike 4.0 International
Addition of supporting files:- LICENSE.txt- data_types.json- data_size.json Fixed version of Papyrus++ 05.5:- In the previous 05.5 versiondata was incorrectlyduplicated based on assay type. This resulted in unintended data augmentation.- In thisfixed 05.5 versionthe duplicates have been eliminated, now reporting the correct amount of data per assay type. This repository contains the version 05.5 of the Papyrus dataset, an aggregated dataset of small molecule bioactivities, as described in the article "Papyrus - A large scale curated dataset aimed at bioactivity predictions" http://doi.org/10.1186/s13321-022-00672-x. With the ongoing rapid growth of publicly available ligand-protein bioactivity data, there is a trove of valuable data that can be used to train a plethora of machine learning algorithms. However, not all data is equal in terms of size and quality and a significant portion of researchers time is needed to adapt the data to their needs. On top of that, finding the right data for a research question can often be a challenge on its own. To meet these challenges we have constructed the Papyrus dataset. Papyrus is comprised of around 60 million datapoints. This dataset contains multiple large publicly available datasets such as ChEMBL and ExCAPE-DB combined with several smaller datasets containing high-quality data. The aggregated data has been standardised and normalised in a manner that is suitable for machine learning. We show how data can be filtered in a variety of ways and also perform some example quantitative structure-activity relationship analyses and proteochemometric modelling. Our ambition is that this pruned data collection constitutes a benchmark set that can be used for constructing predictive models, while also providing a solid baseline for related research.
This page was built for dataset: Accompanying data - Papyrus - A large scale curated dataset aimed at bioactivity predictions
