jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified February 17, 2015
jpayne@69: 
jpayne@69: Description:  Separates paired reads into files of 'good' pairs and 'good' singletons by removing 'bad' reads that are shorter than a min length.
jpayne@69: Designed to handle situations where reads become too short to be useful after trimming.  This program also optionally performs quality trimming.
jpayne@69: 
jpayne@69: Usage:        bbsplitpairs.sh in=<input file> out=<pair output file> outs=<singleton output file> minlen=<minimum read length, an integer>
jpayne@69: 
jpayne@69: Input may be fasta or fastq, compressed or uncompressed.
jpayne@69: 
jpayne@69: Optional parameters (and their defaults)
jpayne@69: 
jpayne@69: in=<file>           The 'in=' flag is needed if the input file is not the first parameter.  'in=stdin' will pipe from standard in.
jpayne@69: in2=<file>          Use this if 2nd read of pairs are in a different file.
jpayne@69: out=<file>          The 'out=' flag is needed if the output file is not the second parameter.  'out=stdout' will pipe to standard out.
jpayne@69: out2=<file>         Use this to write 2nd read of pairs to a different file.
jpayne@69: outsingle=<file>    (outs) Write singleton reads here.
jpayne@69: 
jpayne@69: overwrite=t         (ow) Set to false to force the program to abort rather than overwrite an existing file.
jpayne@69: showspeed=t         (ss) Set to 'f' to suppress display of processing speed.
jpayne@69: interleaved=auto    (int) If true, forces fastq input to be paired and interleaved.
jpayne@69: qtrim=f             Trim read ends to remove bases with quality below trimq.
jpayne@69:                     Values: rl (trim both ends), f (neither end), r (right end only), l (left end only).
jpayne@69: trimq=6             Trim quality threshold.
jpayne@69: minlen=20           (ml) Reads shorter than this after trimming will be discarded.
jpayne@69: ziplevel=2          (zl) Set to 1 (lowest) through 9 (max) to change compression level; lower compression is faster.
jpayne@69: fixinterleaving=f   (fint) Fixes corrupted interleaved files by examining pair names.  Only use on files with broken interleaving.
jpayne@69: repair=f            (rp) Fixes arbitrarily corrupted paired reads by examining read names.  High memory.
jpayne@69: ain=f               (allowidenticalnames) When detecting pair names, allows identical names, instead of requiring /1 and /2 or 1: and 2:
jpayne@69: 
jpayne@69: Java Parameters:
jpayne@69: -Xmx                This will set Java's memory usage, overriding autodetection.
jpayne@69:                     -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will specify 200 megs.
jpayne@69:                     The max is typically 85% of physical memory.
jpayne@69: -eoom               This flag will cause the process to exit if an
jpayne@69:                     out-of-memory exception occurs.  Requires Java 8u92+.
jpayne@69: -da                 Disable assertions.
jpayne@69: 
jpayne@69: Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems.
jpayne@69: "
jpayne@69: }
jpayne@69: 
jpayne@69: #This block allows symlinked shellscripts to correctly set classpath.
jpayne@69: pushd . > /dev/null
jpayne@69: DIR="${BASH_SOURCE[0]}"
jpayne@69: while [ -h "$DIR" ]; do
jpayne@69:   cd "$(dirname "$DIR")"
jpayne@69:   DIR="$(readlink "$(basename "$DIR")")"
jpayne@69: done
jpayne@69: cd "$(dirname "$DIR")"
jpayne@69: DIR="$(pwd)/"
jpayne@69: popd > /dev/null
jpayne@69: 
jpayne@69: #DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
jpayne@69: CP="$DIR""current/"
jpayne@69: 
jpayne@69: z="-Xmx200m"
jpayne@69: set=0
jpayne@69: 
jpayne@69: if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
jpayne@69: 	usage
jpayne@69: 	exit
jpayne@69: fi
jpayne@69: 
jpayne@69: calcXmx () {
jpayne@69: 	source "$DIR""/calcmem.sh"
jpayne@69: 	setEnvironment
jpayne@69: 	parseXmx "$@"
jpayne@69: }
jpayne@69: calcXmx "$@"
jpayne@69: 
jpayne@69: splitpairs() {
jpayne@69: 	local CMD="java $EA $EOOM $z -cp $CP jgi.SplitPairsAndSingles $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: splitpairs "$@"