In this function at first a Matrix called smoothed-PSSM is constructed from PSSM Matrix
by applying "ws" parameter which called sliding window size and taken from user and usually is equals to 7. Then
using other window size parameter "w" which usually equals to 11 at each position smoothed feature vector is
constructed.
Usage
smoothed_PSSM(pssm_name, ws = 7, w = 50, v = NULL)
Arguments
pssm_name
name of PSSM Matrix file
ws
window size for smoothing PSSM Matrix
w
window size for extracting feature vector
v
vector of desired positions to extract their features
Value
a matrix of feature vectors
Details
In the construction of a smoothed PSSM, each row vector of a residue \(\alpha_i\) is represented and
smoothed by the summation of ws surrounding row vectors \((V_{smoothed_i}=V_{i-(ws-1)/2}+...+V_i+...+
V_{i+(ws+1)/2})\) For the N-terminal and C-terminal of a protein, (w-1)/2 ZERO vectors, are appended to the
head or tail of a smoothed PSSM profile. Using the smoothed PSSM encoding scheme the feature vector of a residue
\(\alpha_i\) is represented by \((V_{smoothed_i-(ws-1)/2},...,V_{smoothed_i},...,V_{smoothed_i+(ws+1)/2})\)
The feature values in each vector are normalized to a range between -1 and 1.
References
Cheng, C.W., et al. (2008) Predicting RNA-binding sites of proteins using support vector machines and
evolutionary information, BMC Bioinformatics, 9 Suppl 12, S6.