4 datasets found

Filter Results

  • ProtST

    The ProtST dataset is a collection of protein sequences and their corresponding biomedical text descriptions.

  • DeepSF dataset

    The DeepSF dataset is a benchmark for protein sequence analysis.

  • Pfam protein families database

    The Pfam protein families database in 2019. The dataset is used for protein sequence analysis and contains 31 million protein domains.

  • Lattice Proteins

    Lattice-protein (LP) models were introduced in the 90s to investigate the properties of proteins, particularly how their structure depend on their sequences. They were recently...