pse_hmm

The first twenty numbers of this feature correspond to the means of each column of the HMM matrix \(H\). The rest of the features in the feature vector are given by correlation of the \(ith\) most contiguous values along the chain per each amino acid column, where \(0<i<g+1\). This creates a vector of 20 \(\times\) g, and this combines with the first 20 features to create the final feature vector.

Usage

pse_hmm(hmm, g = 15)

Arguments

hmm

The name of a profile hidden markov model file.

g

The contiguous distance between residues.

Value

A vector of length \(20 + g \times 20\), by default this is 320.

Note

g must be less than the length of the protein sequence

References

Chou, K., & Shen, H. (2007). MemType-2L: A Web server for predicting membrane proteins and their types by incorporating evolution information through Pse-PSSM. Biochemical and Biophysical Research Communications, 360(2), 339–345.

Examples

h<- pse_hmm(system.file("extdata", "1DLHA2-7", package="protHMM"))