DP_PSSM: DP_PSSM feature vector

In PSSMCOOL: Features Extracted from Position Specific Scoring Matrix (PSSM)

Description

This feature results from the connection of two vectors. The vector is the first feature of a vector with a length of 40, which calculates the average of positive and negative values for each column separately and puts them together. in the second feature vector, correspond to each column the difference between the numbers in the rows that have distance of k is calculated, and then the square average for the differences that are positive is calculated, and the same action for the differences that are negative is performed. since k varies between 1 and α, and because the value of α in this function is equal to 2, the length of the second feature vector will be 80, which by merging with the first feature vector, the total feature vector of length 120 will be obtained.

Usage

DP_PSSM(pssm_name, a = 5)

Arguments

pssm_name	name of PSSM matrix file
a	fixed parameter that user chooses which usually equals to 2

Value

feature vector of length 240

References

Juan, E.Y., et al. (2009) Predicting Protein Subcellular Localizations for Gram-Negative Bacteria using DP-PSSM and Support Vector Machines. Complex, Intelligent and Software Intensive Systems, 2009. CISIS'09. International Conference on. IEEE, pp. 836-841.

Examples

X<-DP_PSSM(system.file("extdata", "C7GQS7.txt.pssm", package="PSSMCOOL"))

PSSMCOOL documentation built on Jan. 4, 2022, 5:07 p.m.