dwt_PSSM: discrete wavelet transform feature vector

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

Description

In construction of this feature vector, the dwt.nondyadic function is used from "waveslim", package to calculate the discrete wavelet transform for each column of the PSSM matrix, which considers it as a discrete signal. At last, 4 levels DWT is used to analysis of these discrete signals of PSSM (each column) and extracted the PSSM-DWT feature from PSSM of protein.

Usage

dwt_PSSM(pssm_name)

Arguments

pssm_name

name of pssm Matrix file

Value

feature vector of length 80

References

Y. Wang, Y. Ding, F. Guo, L. Wei, and J. J. P. o. Tang, "Improved detection of DNA-binding proteins via compression technology on PSSM information," vol. 12, no. 9, 2017.

Y. Wang, Y. Ding, J. Tang, Y. Dai, F. J. I. A. t. o. c. b. Guo, and bioinformatics, "CrystalM: a multi-view fusion approach for protein crystallization prediction," 2019.

Examples

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

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