jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified July 31, 2018
jpayne@69: 
jpayne@69: Description:  Subsamples reads to reach a target unique kmer limit.
jpayne@69: 
jpayne@69: Differences between versions:
jpayne@69: kmerlimit.sh uses 1 pass and outputs all reads until a limit is hit,
jpayne@69: meaning the input reads should be in random order with respect to sequence.
jpayne@69: kmerlimit2.sh uses 2 passes and randomly subsamples from the file, so
jpayne@69: it works with reads in any order.
jpayne@69: 
jpayne@69: Usage:  kmerlimit2.sh in=<input file> out=<output file> limit=<number>
jpayne@69: 
jpayne@69: Standard parameters:
jpayne@69: in=<file>       Primary input, or read 1 input.
jpayne@69: in2=<file>      Read 2 input if reads are in two files.
jpayne@69: out=<file>      Primary output, or read 1 output.
jpayne@69: out2=<file>     Read 2 output if reads are in two files.
jpayne@69: overwrite=t     (ow) Set to false to force the program to abort rather than
jpayne@69:                 overwrite an existing file.
jpayne@69: ziplevel=2      (zl) Set to 1 (lowest) through 9 (max) to change compression
jpayne@69:                 level; lower compression is faster.
jpayne@69: 
jpayne@69: Processing parameters:
jpayne@69: k=31            Kmer length, 1-32.
jpayne@69: limit=          The number of unique kmers to produce.
jpayne@69: mincount=1      Ignore kmers seen fewer than this many times.
jpayne@69: minqual=0       Ignore bases with quality below this.
jpayne@69: minprob=0.2     Ignore kmers with correctness probability below this.
jpayne@69: trials=25       Simulation trials.
jpayne@69: seed=-1         Set to a positive number for deterministic output.
jpayne@69: maxlen=50m      Max length of a temp array used in simulation.
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
jpayne@69:                 specify 200 megs. The max is typically 85% of physical memory.
jpayne@69: -eoom           This flag will cause the process to exit if an out-of-memory
jpayne@69:                 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="-Xmx1000m"
jpayne@69: z2="-Xms1000m"
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: kmerlimit2() {
jpayne@69: 	local CMD="java $EA $EOOM $z -cp $CP sketch.KmerLimit2 $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: kmerlimit2 "$@"