jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified December 22, 2021
jpayne@69: This script requires at least 10GB RAM.
jpayne@69: It is designed for NERSC and uses hard-coded paths.
jpayne@69: 
jpayne@69: Description:  Removes all reads that map to selected common microbial contaminant genomes.
jpayne@69: Removes approximately 98.5% of common contaminant reads, with zero false-positives to non-bacteria.
jpayne@69: NOTE!  This program uses hard-coded paths and will only run on Nersc systems.
jpayne@69: 
jpayne@69: Usage:  removemicrobes.sh in=<input file> outu=<clean output file>
jpayne@69: 
jpayne@69: Input may be fasta or fastq, compressed or uncompressed.
jpayne@69: 
jpayne@69: Parameters:
jpayne@69: in=<file>           Input reads.  Should already be adapter-trimmed.
jpayne@69: outu=<file>         Destination for clean reads.
jpayne@69: outm=<file>         Optional destination for contaminant reads.
jpayne@69: threads=auto        (t) Set number of threads to use; default is number of logical processors.
jpayne@69: overwrite=t         (ow) Set to false to force the program to abort rather than overwrite an existing file.
jpayne@69: interleaved=auto    (int) If true, forces fastq input to be paired and interleaved.
jpayne@69: trim=t              Trim read ends to remove bases with quality below minq.
jpayne@69:                     Values: t (trim both ends), f (neither end), r (right end only), l (left end only).
jpayne@69: untrim=t            Undo the trimming after mapping.
jpayne@69: minq=4              Trim quality threshold.
jpayne@69: ziplevel=6          (zl) Set to 1 (lowest) through 9 (max) to change compression level; lower compression is faster.
jpayne@69: 
jpayne@69: build=1             Choses which masking mode was used:  
jpayne@69:                     1 is most stringent and should be used for bacteria.
jpayne@69:                     2 uses fewer bacteria for masking (only RefSeq references).
jpayne@69:                     3 is only masked for plastids and entropy, for use on anything except bacteria.
jpayne@69:                     4 is unmasked.
jpayne@69: 
jpayne@69: ***** All BBMap parameters can be used; run bbmap.sh for more details. *****
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: JNI="-Djava.library.path=""$DIR""jni/"
jpayne@69: JNI=""
jpayne@69: 
jpayne@69: z="-Xmx6000m"
jpayne@69: z2="-Xms6000m"
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 removemicrobes() {
jpayne@69: 	local CMD="java $EA $EOOM $z $z2 $JNI -cp $CP align2.BBMap strictmaxindel=4 bwr=0.16 bw=12 ef=0.001 minhits=2 path=/global/cfs/cdirs/bbtools/commonMicrobes pigz unpigz zl=6 qtrim=r trimq=10 untrim idtag printunmappedcount ztd=2 kfilter=25 maxsites=1 k=13 minid=0.95 idfilter=0.95 minhits=2 build=1 bloomfilter $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: removemicrobes "$@"