DFMCA_PSSM: DMACA-PSSM feature

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

Description

In this feature each column of PSSM Matrix, can be regarded as a time series. Each PSSM contains 20 columns Hence, each PSSM can be considered as 20 time series.The detrended moving-average cross-correlation analysis (DMCA) is developed to measure the level of cross-correlation between two non-stationary time series by fusing the detrended cross-correlation analysis (DCCA) and the detrended moving average(DMA).this function utilizes this algorithm for each column and each pair of columns to produce a feature vector of length 290.

Usage

DFMCA_PSSM(pssm_name, n = 7)

Arguments

pssm_name	name of PSSM Matrix file
n	A parameter called the window size that must be smaller than the length of the sequence

Value

feature vector of length 210

Note

parameter n must be equal or greater than 3 and equal or less then L which L is length of protein

References

Y. Liang, S. Zhang, S. J. S. Ding, and Q. i. E. Research, "Accurate prediction of Gram-negative bacterial secreted protein types by fusing multiple statistical features from PSI-BLAST profile," vol. 29, no. 6, pp. 469-481, 2018.

Y. Liang and S. J. A. b. Zhang, "Prediction of apoptosis protein’s subcellular localization by fusing two different descriptors based on evolutionary information," vol. 66, no. 1, pp. 61-78, 2018.

Examples

X<-DFMCA_PSSM(system.file("extdata", "C7GQS7.txt.pssm", package="PSSMCOOL"),7)

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