featureDOMAIN: Feature Coding by doamin organization
Description
Protein sequences are coded based on their domains.
Usage
featureDOMAIN(domain) # Protein Pfam domain prediction predictPFAM(seq, hmmpfam.path, pfam.path, Evalue=10^-5)
Arguments
domain
a list of protein domains. It can be produced by function
predictPFAM.
seq
a string vector for the protein, DNA, or RNA sequences.
hmmpfam.path
a string for the path of hammpfam program in HMMER.
hammpfam will be employed to predict domains using models in Pfam database.
pfam.path
a string for the path of pfam domain database.
Evalue
a numeric value for the E-value cutoff of perdicted Pfam domain.
Details
featureDOMAIN uses Pfam domains to code 0-1 feature vector.
predictPFAM predict Pfam domains by hmmpfam program. It returns
a list, each element is a vector which denotes the domain composition of a
protein.