4 datasets found

Filter Results
  • Class700

    The dataset used for protein classification, consisting of 700 proteins with at most 20% sequence identity.
  • Fold95

    The dataset used for protein classification, consisting of 95 protein structures with no more than 10% sequence identity.
  • D&D dataset

    The dataset D&D is used for protein classification. It contains amino acids and edges representing distances between them.
  • ENZYMES

    The ENZYMES dataset contains 600 proteins from each of the 6 Enzyme Commission top-level enzyme classes (EC classes) and the goal was to correctly predict enzyme class...