human_cleave: Human signal peptides cleavage sites

In biogram: N-Gram Analysis of Biological Sequences

Description

A set of 648 cleavage sites and 648 parts of mature proteins shortly after cleavage sites derived from human proteome.

Format

A data frame with 1296 observations on the following 10 variables. Columns from P1 to P9 describes positions in an extracted peptide. tar is a target vector. It has value 1 if a peptide is a cleavage site and 0 if not.

Details

Each peptide in the data set is nine amino acid residues long. In case of cleavage sites, the clevage is located between fifth and sixth peptide. The non-cleavage sites are parts of mature proteins starting five positions after cleavage site.

Note

Amino acid residues were recoded as integers.

Source

UniProt

Examples

data(human_cleave)
table(human_cleave[, 1])

biogram documentation built on March 31, 2020, 5:14 p.m.