\name{sim_fq}
%
\alias{sim_fq}
%
\title{sim_fq: Performs an experimental series of separation capabilities of
hierarchical clustering (HC) based on DNA k-mers in FASTQ files using
simulated DNA content.}
% - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %
% Description
% - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %
\description{ Writes compressed FASTQ files where sequence sections
contain concatenated k-mers which are uniformly distributed in the range
of k-mers for given k.
The function first writes a batch of randomly FASTQ files containing
randomly simulated DNA sequence.
In a second step the function repeatedly writes FASTQ files with random
DNA sequence where a fraction of the reads is 'contaminated' with given
DNA k-mers.
In a third step, for each set of simulated and contaminated files,
a hierarchical cluster (HC) tree based on DNA k-mers is calculated.
For each set of files, the size of the smaller fraction in the first
half of the tree is counted (perc).
The value can be used as measure for separation capability of the
HC algorithm.}
%
\usage{sim_fq(nRep=2, nContamVec=c(100, 1000), grSize=20, nSeq=1e4,
k=6, kIndex=1365, pos=20)}
%
\arguments{
\item{nRep}{\code{numeric}. Number of replicates for each combination of
each nContamVec value}
%
\item{nContamVec}{\code{numeric}. Vector with nContam (absolute number of
%
\item{grSize}{\code{numeric}. Number FASTQ files in control and
contamination group.}
%
\item{nSeq}{\code{numeric}. Number of reads per FASTQ file.}
%
\item{k}{\code{numeric}. k value used in fastqq function.}
%
\item{kIndex}{\code{numeric}. k-mer index of inserted k-mer(s). The k-mer
index can be retreaved for a given k-mer with 'kMerIndex'. Default
value is 1365 (="CCCCCC").}
%
\item{pos}{\code{numeric}. Determines at which position in sequence the
k-mer is inserted. 1-based (1=first position).}
}
% - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %
% Details
% - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %
\details{The function is intended to be used as explorative tool (not for
routine quality assessment). There are some files written and there will
be a lot of output on the terminal. It is therefore recommended to switch
to a separate working directory and to run this function on a separate
terminal. The function is not exported.}
%
\value{\code{data.frame} containing results of the counted perc values for
each repetition of the simulation.}
%
\author{Wolfgang Kaisers}
% - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %
% Examples
% - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - %
\examples{
kMerIndex("CCCCCC")
\dontrun{res <- seqTools:::sim_fq(nRep=2, nContamVec=c(10, 100),
grSize=4, nSeq=1e2)}
}
\keyword{sim_fq}