jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified Jan 7, 2020
jpayne@69: 
jpayne@69: Description:   Splits sequences according to their taxonomy,
jpayne@69: as determined by the sequence name.  Sequences should
jpayne@69: be labeled with a gi number, NCBI taxID, or species name.
jpayne@69: 
jpayne@69: Usage:  splitbytaxa.sh in=<input file> out=<output pattern> tree=<tree file> table=<table file> level=<name or number>
jpayne@69: 
jpayne@69: Input may be fasta or fastq, compressed or uncompressed.
jpayne@69: 
jpayne@69: 
jpayne@69: Standard parameters:
jpayne@69: in=<file>       Primary input.
jpayne@69: out=<file>      Output pattern; must contain % symbol.
jpayne@69: overwrite=f     (ow) Set to false to force the program to abort rather than
jpayne@69:                 overwrite an existing file.
jpayne@69: showspeed=t     (ss) Set to 'f' to suppress display of processing speed.
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: level=phylum    Taxonomic level, such as phylum.  Filtering will operate on
jpayne@69:                 sequences within the same taxonomic level as specified ids.
jpayne@69: tree=           A taxonomic tree made by TaxTree, such as tree.taxtree.gz.
jpayne@69: table=          A table translating gi numbers to NCBI taxIDs.
jpayne@69:                 Only needed if gi numbers will be used.
jpayne@69:                 On Genepool, use 'tree=auto table=auto'.
jpayne@69: * Note *
jpayne@69: Tree and table files are in /global/projectb/sandbox/gaag/bbtools/tax
jpayne@69: For non-Genepool users, or to make new ones, use taxtree.sh and gitable.sh
jpayne@69: 
jpayne@69: Java Parameters:
jpayne@69: -Xmx            This will set Java's memory usage, overriding automatic
jpayne@69:                 memory detection.
jpayne@69:                 -Xmx20g will specify 20 gigs of RAM, and -Xmx200m will specify
jpayne@69:                 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="-Xmx4g"
jpayne@69: z2="-Xms4g"
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 [[ $set == 1 ]]; then
jpayne@69: 		return
jpayne@69: 	fi
jpayne@69: 	freeRam 1000m 84
jpayne@69: 	z="-Xmx${RAM}m"
jpayne@69: 	z2="-Xms${RAM}m"
jpayne@69: }
jpayne@69: calcXmx "$@"
jpayne@69: 
jpayne@69: splitbytaxa() {
jpayne@69: 	local CMD="java $EA $EOOM $z -cp $CP tax.SplitByTaxa $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: splitbytaxa "$@"