Skip to main content
zenodoopen

Convolutions are competitive with transformers for protein sequence pretraining

<p>- Pretrained models of protein sequences. See&nbsp;https://github.com/microsoft/protein-sequence-models for instructions on how to load models.</p> <p>- IDR datasets used for evaluation.&nbsp;</p> <p>- March 2020 version of UniRef50 with splits used for training.&nbsp;</p>

ShareScore

32/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
4
Harmonization
4
Access
12
Reuse readiness
8
Engagement
4