qca-dataset-submission icon indicating copy to clipboard operation
qca-dataset-submission copied to clipboard

Published 20 hours ago • verified publisher icon openforcefield

Potential dataset: Molecules from pharma partners in BindingDB

Open jchodera opened this issue 6 years ago • 1 comments

BindingDB contains a way to query molecule sets via patents the data was curated from, with a field populated with the name of the filing organization: https://www.bindingdb.org/bind/ByPatent.jsp

If we can grab this dataset and filter by the Organization field, we could easily create a new dataset that covers some well-studied areas of chemical space form our partners.

We may need to download the complete dataset to do this filtering.

jchodera avatar Sep 02 '19 03:09 jchodera

The Downloads page has an option to just download data curated from patents.

For example, BindingDB_USPatent_3D_2019m8.sdf.zip contains an Institution field that can be queried for our partners.

jchodera avatar Sep 03 '19 15:09 jchodera