This training dataset gives the names, the primary structure (amino acid sequences), and the secondary structure of 15,201 individual proteins from the ASTRAL SCOP 1.75 structure set filtered at 95% sequence identity as used in the paper cited below.
bamboo.trainingA data frame containing 15,201 observations on the following 3 variables.
name: protein name;
primary: protein primary structure (amino acid sequence) in 20 letters denoting the 20 amino acids;
hetc: secondary structure in 4 letters denoting the 4 structure types: helix (H), strand (E), turn (T) and coil (C).
Q. Li, D. B. Dahl, M. Vannucci, H. Joo, J. W. Tsai (2014), Bayesian Model of Protein Primary Sequence for Secondary Structure Prediction, PLOS ONE, 9(10), e109832. <DOI:10.1371/journal.pone.0109832>