jpayne@69: #!/bin/bash
jpayne@69: 
jpayne@69: usage(){
jpayne@69: echo "
jpayne@69: Written by Brian Bushnell
jpayne@69: Last modified October 15, 2019
jpayne@69: 
jpayne@69: Description:  Cuts out features defined by a gff file, and writes them
jpayne@69: to a new fasta.  Features are output in their sense strand.
jpayne@69: 
jpayne@69: Usage:  cutgff.sh in=<fna file> gff=<gff file> out=<fna file>
jpayne@69: 
jpayne@69: in= is optional, and gff filenames will be automaitically assumed based on
jpayne@69: the fasta name if not specified.  This allows running on multiple files
jpayne@69: like this:
jpayne@69: 
jpayne@69: cutgff.sh types=rRNA out=16S.fa minlen=1440 maxlen=1620 attributes=16S bacteria/*.fna.gz
jpayne@69: 
jpayne@69: 
jpayne@69: File Parameters:
jpayne@69: in=<file>           Input FNA (fasta) file.
jpayne@69: gff=<file>          Input GFF file (optional).
jpayne@69: out=<file>          Output FNA file.
jpayne@69: 
jpayne@69: Other Parameters:
jpayne@69: types=CDS           Types of features to cut.
jpayne@69: invert=false        Invert selection: rather outputting the features,
jpayne@69:                     mask them with Ns in the original sequences.
jpayne@69: attributes=         A comma-delimited list of strings.  If present, one of
jpayne@69:                     these strings must be in the gff line attributes.
jpayne@69: bannedattributes=   A comma-delimited list of banned strings.
jpayne@69: banpartial=t        Ignore lines with 'partial=true' in attributes.
jpayne@69: minlen=1            Ignore lines shorter than this.
jpayne@69: maxlen=2147483647   Ignore lines longer than this.
jpayne@69: renamebytaxid=f     Rename sequences with their taxID.  Input sequences
jpayne@69:                     must be named appropriately, e.g. in NCBI format.
jpayne@69: taxmode=accession   Valid modes are:
jpayne@69:                        accession: Sequence names must start with an accession.
jpayne@69:                        gi:        Seqence names must start with gi|number
jpayne@69:                        taxid:     Sequence names must start with tid|number
jpayne@69:                        header:    Best effort for various header formats.
jpayne@69: requirepresent=t    Crash if a taxID cannot be found for a sequence.
jpayne@69: oneperfile=f        Only output one sequence per file.
jpayne@69: align=f             Align ribosomal sequences to consensus (if available);
jpayne@69:                     discard those with low identity, and flip those
jpayne@69:                     annotated on the wrong strand.
jpayne@69: maxns=-1            If non-negative, ignore features with more than this many
jpayne@69:                     undefined bases (Ns or IUPAC symbols).
jpayne@69: maxnfraction=-1.0   If non-negative, ignore features with more than this
jpayne@69:                     fraction of undefined bases (Ns or IUPAC symbols).
jpayne@69:                     Should be 0.0 to 1.0.
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="-Xmx200m"
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: gff() {
jpayne@69: 	local CMD="java $EA $EOOM $z -cp $CP gff.CutGff $@"
jpayne@69: #	echo $CMD >&2
jpayne@69: 	eval $CMD
jpayne@69: }
jpayne@69: 
jpayne@69: gff "$@"