jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified March 24, 2020
jpayne@69: 
jpayne@69: Description:  Estimates cardinality of unique kmers in sequence data.
jpayne@69: See also kmercountmulti.sh.
jpayne@69: 
jpayne@69: Usage:  loglog.sh in=<file> k=<31>
jpayne@69: 
jpayne@69: Parameters:
jpayne@69: in=<file>       (in1) Input file, or comma-delimited list of files.
jpayne@69: in2=<file>      ptional second file for paired reads.
jpayne@69: k=31            Use this kmer length for counting.
jpayne@69: buckets=2048    Use this many buckets for counting; higher decreases
jpayne@69:                 variance, for large datasets.  Must be a power of 2.
jpayne@69: seed=-1         Use this seed for hash functions.  A negative number forces
jpayne@69:                 a random seed.
jpayne@69: minprob=0       Set to a value between 0 and 1 to exclude kmers with a lower 
jpayne@69:                 probability of being correct.
jpayne@69: 
jpayne@69: 
jpayne@69: Shortcuts:
jpayne@69: The # symbol will be substituted for 1 and 2.
jpayne@69: For example:
jpayne@69: loglog.sh in=read#.fq
jpayne@69: ...is equivalent to:
jpayne@69: loglog.sh in1=read1.fq in2=read2.fq
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 out-of-memory
jpayne@69:                 exception occurs.  Requires Java 8u92+.
jpayne@69: -da             Disable assertions.
jpayne@69: 
jpayne@69: Supported input formats are fastq, fasta, scarf, sam, and bam.
jpayne@69: Supported compression formats are gzip and bz2.
jpayne@69: To read from stdin, set 'in=stdin'.  The format should be specified with an extension, like 'in=stdin.fq.gz'
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: function loglog() {
jpayne@69: 	local CMD="java $EA $EOOM $z -cp $CP cardinality.LogLogWrapper $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: loglog "$@"