jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified July 16, 2018
jpayne@69: 
jpayne@69: Description:  Compresses sequence data into a fasta file containing each kmer
jpayne@69: exactly once.  Allows arbitrary kmer set operations via multiple passes.
jpayne@69: 
jpayne@69: Usage:  kcompress.sh in=<reads> out=<contigs> min=<1> max=<2147483647>
jpayne@69: 
jpayne@69: Input parameters:
jpayne@69: in=<file>           Primary input file for reads to use as kmer data.
jpayne@69: in2=<file>          Second input file for paired data.
jpayne@69: reads=-1            Only process this number of reads, then quit (-1 means all).
jpayne@69: 
jpayne@69: Output parameters:
jpayne@69: out=<file>          Write contigs (in contig mode).
jpayne@69: showstats=t         Print assembly statistics after writing contigs.
jpayne@69: fuse=0              Fuse output sequences into chunks at least this long,
jpayne@69:                     padded with 1 N between sequences.
jpayne@69: 
jpayne@69: Prefiltering parameters:
jpayne@69: prefilter=0         If set to a positive integer, use a countmin sketch
jpayne@69:                     to ignore kmers with depth of that value or lower.
jpayne@69: prehashes=2         Number of hashes for prefilter.
jpayne@69: prefiltersize=0.2   (pff) Fraction of memory to use for prefilter.
jpayne@69: minprobprefilter=t  (mpp) Use minprob for the prefilter.
jpayne@69: prepasses=1         Use this many prefiltering passes; higher be more thorough
jpayne@69:                     if the filter is very full.  Set to 'auto' to iteratively 
jpayne@69:                     prefilter until the remaining kmers will fit in memory.
jpayne@69: 
jpayne@69: Hashing parameters:
jpayne@69: k=31                Kmer length (1 to 31).
jpayne@69: prealloc=t          Pre-allocate memory rather than dynamically growing; 
jpayne@69:                     faster and more memory-efficient.  A float fraction (0-1)
jpayne@69:                     may be specified; default is 1.
jpayne@69: minprob=0.5         Ignore kmers with overall probability of correctness below this.
jpayne@69: minprobmain=t       (mpm) Use minprob for the primary kmer counts.
jpayne@69: threads=X           Spawn X threads (default is number of logical processors).
jpayne@69: 
jpayne@69: Assembly parameters:
jpayne@69: mincount=1          (min) Only retain kmers that occur at least this many times.
jpayne@69: maxcount=BIG        (max) Only retain kmers that occur at most this many times.
jpayne@69: requiresamecount    (rsc) Only build contigs from kmers with exactly the same count.
jpayne@69: rcomp=t             Store forward and reverse kmers together.  Setting this to
jpayne@69:                     false will only use forward kmers.
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 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: }
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="-Xmx14g"
jpayne@69: z2="-Xms14g"
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 [[ $set == 1 ]]; then
jpayne@69: 		return
jpayne@69: 	fi
jpayne@69: 	freeRam 15000m 84
jpayne@69: 	z="-Xmx${RAM}m"
jpayne@69: 	z2="-Xms${RAM}m"
jpayne@69: }
jpayne@69: calcXmx "$@"
jpayne@69: 
jpayne@69: kcompress() {
jpayne@69: 	local CMD="java $EA $EOOM $z $z2 -cp $CP assemble.KmerCompressor $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: kcompress "$@"