English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multiple sequence alignments (MSAs) of proteins encode rich biologicalinformation and have been workhorses in bioinformatic methods for tasks likeprotein design and protein structure prediction for decades. Recentbreakthroughs like AlphaFold2 that use transformers to attend directly overlarge quantities of raw MSAs have reaffirmed their importance. Generation ofMSAs is highly computationally intensive, however, and no datasets comparableto those used to train AlphaFold2 have been made available to the researchcommunity, hindering progress in machine learning for proteins. To remedy thisproblem, we introduce OpenProteinSet, an open-source corpus of more than 16million MSAs, associated structural homologs from the Protein Data Bank, andAlphaFold2 protein structure predictions. We have previously demonstrated theutility of OpenProteinSet by successfully retraining AlphaFold2 on it. Weexpect OpenProteinSet to be broadly useful as training and validation data for1) diverse tasks focused on protein structure, function, and design and 2)large-scale multimodal machine learning research.

OpenProteinSet: Training data for structural biology at scale