jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified September 4, 2019
jpayne@69: 
jpayne@69: Description:  Makes a representative set of taxa from all-to-all identity
jpayne@69: comparison.  Input should be in 3+ column TSV format (first 3 are required):
jpayne@69: (query, ref, ANI, qsize, rsize, qbases, rbases)
jpayne@69: ...as produced by CompareSketch with format=3 and usetaxidname.
jpayne@69: Additional columns are allowed and will be ignored.
jpayne@69: 
jpayne@69: Usage:  representative.sh in=<input file> out=<output file>
jpayne@69: 
jpayne@69: Parameters:
jpayne@69: overwrite=f     (ow) Set to false to force the program to abort rather than
jpayne@69:                 overwrite an existing file.
jpayne@69: threshold=0     Ignore edges under threshold value.  This also affects the
jpayne@69:                 choice of centroids; a high threshold gives more weight to 
jpayne@69:                 higher-value edges.
jpayne@69: minratio=0      Ignores edges with a ratio below this value.
jpayne@69: invertratio=f   Invert the ratio when greater than 1.
jpayne@69: printheader=t   Print a header line in the output.
jpayne@69: printsize=t     Print the size of retained nodes.
jpayne@69: printclusters=t Print the nodes subsumed by each retained node.
jpayne@69: minsize=0       Ignore nodes under this size (in unique kmers).
jpayne@69: maxsize=0       If positive, ignore nodes over this size (unique kmers).
jpayne@69: minbases=0      Ignore nodes under this size (in total bases).
jpayne@69: maxbases=0      If positive, ignore nodes over this size (total bases).
jpayne@69: 
jpayne@69: Taxonomy parameters:
jpayne@69: level=          Taxonomic level, such as phylum.  Filtering will operate on
jpayne@69:                 sequences within the same taxonomic level as specified ids.
jpayne@69:                 If not set, only matches to a node or its descendants will 
jpayne@69:                 be considered.
jpayne@69: ids=            Comma-delimited list of NCBI numeric IDs.  Can also be a
jpayne@69:                 file with one taxID per line.
jpayne@69: names=          Alternately, a list of names (such as 'Homo sapiens').
jpayne@69:                 Note that spaces need special handling.
jpayne@69: include=f       'f' will discard filtered sequences, 't' will keep them.
jpayne@69: tree=<file>     Specify a TaxTree file like tree.taxtree.gz.  
jpayne@69:                 On Genepool, use 'auto'.
jpayne@69: 
jpayne@69: Java Parameters:
jpayne@69: -Xmx            This will set Java's memory usage, overriding autodetection.
jpayne@69:                 -Xmx20g will
jpayne@69:                 specify 20 gigs of RAM, and -Xmx200m will specify 200 megs.
jpayne@69:                 The max is typically around 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 [[ $set == 1 ]]; then
jpayne@69: 		return
jpayne@69: 	fi
jpayne@69: 	freeRam 4000m 84
jpayne@69: 	z="-Xmx${RAM}m"
jpayne@69: 	z2="-Xms${RAM}m"
jpayne@69: }
jpayne@69: calcXmx "$@"
jpayne@69: 
jpayne@69: a_sample_mt() {
jpayne@69: 	local CMD="java $EA $EOOM $z -cp $CP jgi.RepresentativeSet $@"
jpayne@69: 	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: a_sample_mt "$@"