diff CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/callgenes.sh @ 69:33d812a61356

planemo upload commit 2e9511a184a1ca667c7be0c6321a36dc4e3d116d
author jpayne
date Tue, 18 Mar 2025 17:55:14 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/CSP2/CSP2_env/env-d9b9114564458d9d-741b3de822f2aaca6c6caa4325c4afce/opt/bbmap-39.01-1/callgenes.sh	Tue Mar 18 17:55:14 2025 -0400
@@ -0,0 +1,84 @@
+#!/bin/bash
+
+usage(){
+echo "
+Written by Brian Bushnell
+Last modified February 10, 2020
+
+Description:  Finds orfs and calls genes in unspliced prokaryotes.
+This includes bacteria, archaea, viruses, and mitochondria.
+Can also predict 16S, 23S, 5S, and tRNAs.
+
+Usage:  callgenes.sh in=contigs.fa out=calls.gff outa=aminos.faa out16S=16S.fa
+
+File parameters:
+in=<file>       A fasta file; the only required parameter.
+out=<file>      Output gff file.
+outa=<file>     Amino acid output.
+out16s=<file>   16S output.
+model=<file>    A pgm file or comma-delimited list.
+                If unspecified a default model will be used.
+stats=stderr    Stats output (may be stderr, stdin, a file, or null).
+hist=null       Gene length histogram.
+compareto=      Optional reference gff file to compare with the gene calls.
+                'auto' will name it based on the input file name.
+
+Formatting parameters:
+json=false      Print stats in JSON.
+binlen=20       Histogram bin length.
+bins=2000       Maximum histogram bins.
+pz=f            (printzero) Print histogram lines with zero count.
+
+
+
+Other parameters:
+minlen=60       Don't call genes shorter than this.
+trd=f           (trimreaddescription) Set to true to trim read headers after
+                the first whitespace.  Necessary for IGV.
+merge=f         For paired reads, merge before calling.
+detranslate=f   Output canonical nucleotide sequences instead of amino acids.
+recode=f        Re-encode nucleotide sequences over called genes, leaving
+                non-coding regions unchanged.
+
+Please contact Brian Bushnell at bbushnell@lbl.gov if you encounter any problems.
+"
+}
+
+#This block allows symlinked shellscripts to correctly set classpath.
+pushd . > /dev/null
+DIR="${BASH_SOURCE[0]}"
+while [ -h "$DIR" ]; do
+  cd "$(dirname "$DIR")"
+  DIR="$(readlink "$(basename "$DIR")")"
+done
+cd "$(dirname "$DIR")"
+DIR="$(pwd)/"
+popd > /dev/null
+
+#DIR="$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/"
+CP="$DIR""current/"
+
+z="-Xmx6g"
+z2="-Xms6g"
+set=0
+
+if [ -z "$1" ] || [[ $1 == -h ]] || [[ $1 == --help ]]; then
+	usage
+	exit
+fi
+
+calcXmx () {
+	source "$DIR""/calcmem.sh"
+	setEnvironment
+	parseXmx "$@"
+}
+calcXmx "$@"
+
+function callgenes() {
+	local CMD="java $EA $EOOM $z $z2 -cp $CP prok.CallGenes $@"
+	#Too long to echo sometimes since wildcards can be expanded
+	#echo $CMD >&2
+	eval $CMD
+}
+
+callgenes "$@"