jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified January 21, 2020
jpayne@69: 
jpayne@69: Description:  Generates synthetic PacBio reads to mimic the chimeric
jpayne@69: inverted repeats from 'triangle reads', aka 'ice cream cones' - 
jpayne@69: reads missing one adapter.
jpayne@69: 
jpayne@69: Usage:  icecreammaker.sh in=<file> out=<file> reads=100k minlen=500 maxlen=5000
jpayne@69: 
jpayne@69: Standard parameters:
jpayne@69: in=<file>       A reference genome fasta (optional).
jpayne@69: out=<file>      Synthetic read output.
jpayne@69: idhist=<file>   Identity histogram output.
jpayne@69: overwrite=f     (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: Length parameters:
jpayne@69: NOTE: "length" parameters dictate subread length (for normal reads).
jpayne@69: "Movie" parameters dictate sequence length (with concatenated subreads).
jpayne@69: 
jpayne@69: minlen=500      (minlength) Minimum length of genomic sequence molecules.
jpayne@69: maxlen=5000     (maxlength) Maximum length of genomic sequence molecules.
jpayne@69: len=            (length) Set minlen and maxlen to the same number.
jpayne@69: minmovie=500    (minmov) Minimum length of movies.
jpayne@69: maxmovie=40k    (maxmov) Maximum length of movies.
jpayne@69: movie=          (mov) Set minmov and maxmov to the same number.
jpayne@69: 
jpayne@69: Ice cream parameters:
jpayne@69: missingrate=0   (missing) Fraction of reads missing an adapter.
jpayne@69: hiddenrate=0    (hidden) Fraction of adapters not detected.
jpayne@69: bothends=f      Allow missing or hiddden adapters on both ends.
jpayne@69: 
jpayne@69: Other parameters:
jpayne@69: zmws            (reads) Number of ZMWs to generate.  There are actually
jpayne@69:                 multiple subreads per zmw.
jpayne@69: ccs=f           Make CCS reads (one read per ZMW, full pass only).
jpayne@69:                 You still need to specify the error rate.
jpayne@69: gc=0.6          If a random genome is generated, use this GC fraction.
jpayne@69: genomesize=10m  If a random genome is generated, make it this big.
jpayne@69: irrate=0.0      Add inverted repeats until this fraction of the genome
jpayne@69:                 is inverted repeats.
jpayne@69: irminlen=500    Minimum length of inverted repeats.
jpayne@69: irmaxlen=5000   Maximum length of inverted repeats
jpayne@69: irlen=          Set minirlen and maxirlen to the same number.
jpayne@69: miner=0.05      (minerrorrate) Minimum error rate.
jpayne@69: maxer=0.28      (maxerrorrate) Maximum error rate.
jpayne@69: er=             (errorrate) Set minerrorrate and maxerrorrate.
jpayne@69: NOTE: You can alternatively set minid, maxid, or id.
jpayne@69: 
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="-Xmx2g"
jpayne@69: z2="-Xms2g"
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: 	if [[ $set == 1 ]]; then
jpayne@69: 		return
jpayne@69: 	fi
jpayne@69: 	freeRam 2000m 42
jpayne@69: 	z="-Xmx${RAM}m"
jpayne@69: 	z2="-Xms${RAM}m"
jpayne@69: }
jpayne@69: calcXmx "$@"
jpayne@69: 
jpayne@69: icecreammaker() {
jpayne@69: 	local CMD="java $EA $EOOM $z -cp $CP icecream.IceCreamMaker $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: icecreammaker "$@"