search

plinder-org / plinder

Protein Ligand INteraction Dataset and Evaluation Resource
https://plinder.sh
Apache License 2.0
170 stars 9 forks source link

V2 Split for Plinder #27

Closed danielzeng-gt closed 3 months ago

danielzeng-gt commented 3 months ago

Dear Plinder Team,

Thank you for your excellent work in curating the dataset and extensive work creating the splits. It certainly makes for a solid benchmark with improved deleaking between the training and test sets compared to existing splits.

I wanted to inquire about the release of the V2 version of the splits/data. The README mentioned the release by August 18th, but the GCS bucket does not appear to have been updated yet.

I was wondering if there's an update on when we can expect the V2 release?

yusuf1759 commented 3 months ago

@danielzeng-gt , thank you so much for the interest! The new dataset is available for download here: gs://plinder/2024-06/v2/ And the splits can be accessed at splits/split.parquet.

We will be working in the next couple of days to update the website, repo and other documentation accordingly to the new split.