test.train.nc: test.train.nc function

In prodakt/lncRna: Long Non-coding RNA Identification

test.train.nc function

Description

This function allows you to split a sequences \(from FASTA file\) into two sets: test and train. As a result, the function outputs a list consisting of two elements "test" and "train" containing sequence names.

Usage

test.train.nc(nc.fa, percent_train = 0.6)

Arguments

nc.fa	the variable containing sequences in fasta format (from read.fasta() function from seqinr library)
percent_train	the ratio value to divide the input set (he default is 0.6, which means that 60% of the sequence is to be allocated to the training set)

Examples

nc <- read.fasta("lncRNA/Mus_musculus.GRCm39.ncrna.fa", seqtype = "DNA", as.string = T, set.attributes = F)
nc_tt <- test.train.nc(nc.fa = nc, percent_train = 0.6)

prodakt/lncRna documentation built on June 1, 2025, 1:05 p.m.