funbarRF (version 1.0.2)

seq_funbarRF: Conversion of barcode sequences into numeric vectors based on gap pair compositions, with user supplied barcode sequences and species labels.

Description

This function can be used to map the sequence dataset onto numeric feature vectors, based on gap pair composition features. This function requires the barcode sequences in DNAString format and the species label of each sequence as factor. The resultant output can be directly used as input to train the random forest based prediction model.

Usage

seq_funbarRF (reference_seq, seq_id)

Arguments

reference_seq

Barcode sequences of class DNAStringSet. It can also be an object generated using the function read_seq_txt.

seq_id

A vctor of species labels as factor. The length of the vector must be equal to the number of sequences in reference_seq.

Value

ref_label

Species labels of barcode sequences as factor.

ref_gpc

A matrix of dimension N*96, where N is the number of sequences and 96 columns represent the gap pair composition features for 0, 1, 2, 3, 4 and 5 gaps together.

Details

For the argument seq_id, user has to supply the species label for each sequence in the specified format. For example, the species label Absidia caerulea should written as Absidia_caerulea. The class of the seq_id must be of factor type.

References

1. Yu C.S., Chen Y.C., Lu C.H., and Hwang J.K. (2006). Prediction of protein subcellular localization. Proteins, 64(3), 643-651.

2. Meher P.K., Sahu T.K., Gahoi S., and Rao A.R. (2018). ir-HSP: Improved recognition of heat shock proteins, their families and sub-types based on g-spaced di-peptide features and support vector machine. Front. Genet., 8, 235.

3. Li H. (2016). BioSeqClass: Classification for biological Sequences. R package version 1.32.0.

See Also

seq_funbarRF_manual, featureGapPairComposition

Examples

# NOT RUN {
data(fun_dat) 
kk <- read_seq_txt (fun_dat$seq)[1:2]
zz <- as.factor (as.character(fun_dat$seq_name[1:2]))
res <- seq_funbarRF (reference_seq=kk, seq_id=zz)
print (res$ref_label)
head (res$ref_gpc)
# }