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:   Prints the full taxonomy of a string.
jpayne@69: String may be a gi number, NCBI taxID, or Latin name.
jpayne@69: An NCBI identifier should just be a number or ncbi|number.
jpayne@69: A gi number should be gi|number.
jpayne@69: Please read bbmap/docs/guides/TaxonomyGuide.txt for more information.
jpayne@69: Not: It is more convenient to use taxonomy.jgi-psf.org.
jpayne@69: 
jpayne@69: Usage:  taxonomy.sh tree=<tree file> <identifier>
jpayne@69: Alternate usage: taxonomy.sh tree=<tree file> in=<file>
jpayne@69: 
jpayne@69: Usage examples:
jpayne@69: taxonomy.sh tree=tree.taxtree.gz homo_sapiens canis_lupus 9606
jpayne@69: taxonomy.sh tree=tree.taxtree.gz gi=gitable.int1.d.gz in=refseq.fasta
jpayne@69: 
jpayne@69: Processing parameters:
jpayne@69: in=<file>       A file containing named sequences, or just the names.
jpayne@69: out=<file>      Output file.  If blank, use stdout.
jpayne@69: tree=<file>     Specify a TaxTree file like tree.taxtree.gz.  
jpayne@69:                 On Genepool, use 'auto'.
jpayne@69: gi=<file>       Specify a gitable file like gitable.int1d.gz. Only needed
jpayne@69:                 if gi numbers will be used.  On Genepool, use 'auto'.
jpayne@69: accession=      Specify one or more comma-delimited NCBI accession to taxid
jpayne@69:                 files.  Only needed if accesions will be used; requires ~45GB
jpayne@69:                 of memory.  On Genepool, use 'auto'.
jpayne@69: level=null      Set to a taxonomic level like phylum to just print that level.
jpayne@69: minlevel=-1     For multi-level printing, do not print levels below this.
jpayne@69: maxlevel=life   For multi-level printing, do not print levels above this.
jpayne@69: silva=f         Parse headers using Silva or semicolon-delimited syntax.
jpayne@69: taxpath=auto    Set the path to taxonomy files; auto only works at NERSC.
jpayne@69: 
jpayne@69: Parameters without an '=' symbol will be considered organism identifiers.
jpayne@69: 
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, 
jpayne@69:                 overriding autodetection.
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="-Xmx8g"
jpayne@69: z2="-Xms8g"
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 [[ $set == 1 ]]; then
jpayne@69: 		return
jpayne@69: 	fi
jpayne@69: 	freeRam 2000m 84
jpayne@69: 	z="-Xmx${RAM}m"
jpayne@69: 	z2="-Xms${RAM}m"
jpayne@69: }
jpayne@69: calcXmx "$@"
jpayne@69: 
jpayne@69: taxonomy() {
jpayne@69: 	local CMD="java $EA $EOOM $z -cp $CP tax.PrintTaxonomy $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: taxonomy "$@"