jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified February 10, 2020
jpayne@69: 
jpayne@69: Description:  Finds orfs and calls genes in unspliced prokaryotes.
jpayne@69: This includes bacteria, archaea, viruses, and mitochondria.
jpayne@69: Can also predict 16S, 23S, 5S, and tRNAs.
jpayne@69: 
jpayne@69: Usage:  callgenes.sh in=contigs.fa out=calls.gff outa=aminos.faa out16S=16S.fa
jpayne@69: 
jpayne@69: File parameters:
jpayne@69: in=<file>       A fasta file; the only required parameter.
jpayne@69: out=<file>      Output gff file.
jpayne@69: outa=<file>     Amino acid output.
jpayne@69: out16s=<file>   16S output.
jpayne@69: model=<file>    A pgm file or comma-delimited list.
jpayne@69:                 If unspecified a default model will be used.
jpayne@69: stats=stderr    Stats output (may be stderr, stdin, a file, or null).
jpayne@69: hist=null       Gene length histogram.
jpayne@69: compareto=      Optional reference gff file to compare with the gene calls.
jpayne@69:                 'auto' will name it based on the input file name.
jpayne@69: 
jpayne@69: Formatting parameters:
jpayne@69: json=false      Print stats in JSON.
jpayne@69: binlen=20       Histogram bin length.
jpayne@69: bins=2000       Maximum histogram bins.
jpayne@69: pz=f            (printzero) Print histogram lines with zero count.
jpayne@69: 
jpayne@69: 
jpayne@69: 
jpayne@69: Other parameters:
jpayne@69: minlen=60       Don't call genes shorter than this.
jpayne@69: trd=f           (trimreaddescription) Set to true to trim read headers after
jpayne@69:                 the first whitespace.  Necessary for IGV.
jpayne@69: merge=f         For paired reads, merge before calling.
jpayne@69: detranslate=f   Output canonical nucleotide sequences instead of amino acids.
jpayne@69: recode=f        Re-encode nucleotide sequences over called genes, leaving
jpayne@69:                 non-coding regions unchanged.
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="-Xmx6g"
jpayne@69: z2="-Xms6g"
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 callgenes() {
jpayne@69: 	local CMD="java $EA $EOOM $z $z2 -cp $CP prok.CallGenes $@"
jpayne@69: 	#Too long to echo sometimes since wildcards can be expanded
jpayne@69: 	#echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: callgenes "$@"