ml4bio / Dense-Homolog-Retrieval

Nature Biotechnology: Ultra-fast, sensitive detection of protein remote homologs using deep dense retrieval
BSD 3-Clause "New" or "Revised" License
63 stars 1 forks source link

UniRef90 70M embeddings database #13

Open igortru opened 1 month ago

igortru commented 1 month ago

Could you, please, provide url?

heathcliff233 commented 4 weeks ago

Thank you for the question. The 70M database is UniRef90 released on 201803. It was not provided since it was too large. Let me try to find a way to transfer it. I will keep you updated.

igortru commented 4 weeks ago

https://ftp.uniprot.org/pub/databases/uniprot/uniref/uniref90/ just clarification:

I am interested download your uniref90 database with embeddings, not uniref90 fastas itself.