# HG changeset patch # User crs4 # Date 1378833086 14400 # Node ID 95505a9fa26fb87a27df82308717fe5304a2750a Uploaded diff -r 000000000000 -r 95505a9fa26f COPYING --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/COPYING Tue Sep 10 13:11:26 2013 -0400 @@ -0,0 +1,23 @@ +Copyright © 2013 CRS4 Srl. http://www.crs4.it/ +Created by: +Paolo Uva +Nicola Soranzo + +Permission is hereby granted, free of charge, to any person obtaining a +copy of this software and associated documentation files (the +"Software"), to deal in the Software without restriction, including +without limitation the rights to use, copy, modify, merge, publish, +distribute, sublicense, and/or sell copies of the Software, and to +permit persons to whom the Software is furnished to do so, subject to +the following conditions: + +The above copyright notice and this permission notice shall be included +in all copies or substantial portions of the Software. + +THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS +OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF +MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. +IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY +CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, +TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE +SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. diff -r 000000000000 -r 95505a9fa26f prokka.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/prokka.py Tue Sep 10 13:11:26 2013 -0400 @@ -0,0 +1,60 @@ +# -*- coding: utf-8 -*- +""" +Wrapper for Prokka - Prokaryotic annotation tool +Author: Paolo Uva paolo dot uva at crs4 dot it +Date: February 14, 2013 +Update: March 14, 2013 - Added more options +""" + +import optparse +import shutil +import subprocess +import sys + + +def __main__(): + #Parse Command Line + parser = optparse.OptionParser() + parser.add_option('--cpus', dest='cpus', type='int', help='Number of CPUs to use [0=all]') + parser.add_option('--fasta', dest='fasta', help='FASTA file with contigs') + parser.add_option('--kingdom', dest='kingdom', choices=['Archaea', 'Bacteria', 'Viruses'], default='Bacteria', help='Kingdom') + parser.add_option('--mincontig', dest='mincontig', type='int', help='Minimun contig size') + parser.add_option('--rfam', action="store_true", dest="rfam", help="Enable searching for ncRNAs") + parser.add_option('--centre', dest="centre", default="CRS4", help="Sequencing centre") + parser.add_option('--gff', dest="gff", help="This is the master annotation in GFF3 format, containing both sequences and annotations. It can be viewed directly in Artemis or IGV") + parser.add_option('--gbk', dest="gbk", help="This is a standard Genbank file derived from the master .gff. If the input to prokka was a multi-FASTA, then this will be a multi-Genbank, with one record for each sequence") + parser.add_option('--fna', dest="fna", help="Nucleotide FASTA file of the input contig sequences") + parser.add_option('--faa', dest="faa", help="Protein FASTA file of the translated CDS sequences") + parser.add_option('--ffn', dest="ffn", help="Nucleotide FASTA file of all the annotated sequences, not just CDS") + parser.add_option('--sqn', dest="sqn", help="An ASN1 format Sequin file for submission to Genbank. It needs to be edited to set the correct taxonomy, authors, related publication etc") + parser.add_option('--fsa', dest="fsa", help="Nucleotide FASTA file of the input contig sequences, used by tbl2asn to create the .sqn file. It is mostly the same as the .fna file, but with extra Sequin tags in the sequence description lines") + parser.add_option('--tbl', dest="tbl", help="Feature Table file, used by tbl2asn to create the .sqn file") + parser.add_option('--err', dest="err", help="Unacceptable annotations - the NCBI discrepancy report") + parser.add_option('--log', dest="log", help="Contains all the output that Prokka produced during its run") + (options, args) = parser.parse_args() + if len(args) > 0: + parser.error('Wrong number of arguments') + + # Build command + cpus = "--cpus %d" % (options.cpus) if options.cpus is not None else '' + rfam = '--rfam' if options.rfam else '' + mincontig = "--mincontig %d" % options.mincontig if options.mincontig is not None else '' + + cl = "prokka --force --outdir . --prefix prokka --kingdom %s %s --centre %s %s %s %s" % (options.kingdom, mincontig, options.centre, rfam, cpus, options.fasta) + print '\nProkka command to be executed: \n %s' % cl + + # Run command + log = open(options.log, 'w') if options.log else sys.stdout + try: + subprocess.check_call(cl, stdout=log, stderr=subprocess.STDOUT, shell=True) # need to redirect stderr because prokka writes many logging info there + finally: + if log != sys.stdout: + log.close() + + # Rename output files + suffix = ['gbk', 'fna', 'faa', 'ffn', 'sqn', 'fsa', 'tbl', 'err', 'gff'] + for s in suffix: + shutil.move( 'prokka.' + s, getattr(options, s)) + +if __name__ == "__main__": + __main__() diff -r 000000000000 -r 95505a9fa26f prokka.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/prokka.xml Tue Sep 10 13:11:26 2013 -0400 @@ -0,0 +1,112 @@ + + Prokaryotic Annotation + + blast+ + hmmer + aragorn + infernal + prokka + + prokka --version + + prokka.py + \${PROKKA_SITE_OPTIONS:---cpus 8} + ## Reads in FASTA format + --fasta=$fasta_file + ## Additional inputs + --kingdom $kingdom_type.kingdom + #if str($mincontig) + --mincontig $mincontig + #end if + #if $rfam + --rfam + #end if + #if $centre + --centre "$centre" + #end if + ## Output files + --gff=$out_gff + --gbk=$out_gbk + --fna=$out_fna + --faa=$out_faa + --ffn=$out_ffn + --sqn=$out_sqn + --fsa=$out_fsa + --tbl=$out_tbl + --err=$out_err + --log=$out_log + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +**What it does** + +Prokka_ is a software tool to annotate bacterial, archaeal and viral genomes very rapidly, and produce output files that require only minor tweaking to submit to Genbank/ENA/DDBJ. + +.. _Prokka: http://www.vicbioinformatics.com/software.prokka.shtml + +**Output files** + +Prokka creates several output files:: + + gff This is the master annotation in GFF3 format, containing both sequences and annotations. + It can be viewed directly in Artemis or IGV + gbk This is a standard Genbank file derived from the master .gff + If the input to prokka was a multi-FASTA, then this will be a multi-Genbank, + with one record for each sequence + fna Nucleotide FASTA file of the input contig sequences + faa Protein FASTA file of the translated CDS sequences + ffn Nucleotide FASTA file of all the annotated sequences, not just CDS + sqn An ASN1 format "Sequin" file for submission to Genbank. + It needs to be edited to set the correct taxonomy, authors, related publication etc. + fsa Nucleotide FASTA file of the input contig sequences, used by "tbl2asn" to create the .sqn file. + It is mostly the same as the .fna file, but with extra Sequin tags in the sequence description lines + tbl Feature Table file, used by "tbl2asn" to create the .sqn file. + err Unacceptable annotations - the NCBI discrepancy report. + log Contains all the output that Prokka produced during its run. + This is a record of what settings you used. + +**License and citation** + +This Galaxy tool is Copyright © 2013 `CRS4 Srl.`_ and is released under the `MIT license`_. + +.. _CRS4 Srl.: http://www.crs4.it/ +.. _MIT license: http://opensource.org/licenses/MIT + +If you use this tool in Galaxy, please cite |Cuccuru2013|_. + +.. |Cuccuru2013| replace:: Cuccuru, G., Orsini, M., Pinna, A., Sbardellati, A., Soranzo, N., Travaglione, A., Uva, P., Zanetti, G., Fotia, G. (2013) Orione, a web-based framework for NGS analysis in microbiology. *Submitted* +.. _Cuccuru2013: http://orione.crs4.it/ + +This tool uses `Prokka`_, which is licensed separately. Please cite Seemann T. Prokka: Prokaryotic Genome Annotation System (in preparation). + +.. _Prokka: http://www.vicbioinformatics.com/software.prokka.shtml + + diff -r 000000000000 -r 95505a9fa26f tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Tue Sep 10 13:11:26 2013 -0400 @@ -0,0 +1,45 @@ + + + + + + + + + + + + + + + + + + http://www.vicbioinformatics.com/prokka-1.7.tar.gz + + . + $INSTALL_DIR + + + $INSTALL_DIR/bin + + + "--cpus 8" + + + + +Dependencies of Prokka which needs to be installed separately: +- Perl core modules: File::Copy, FindBin, Getopt::Long, List::Util, Scalar::Util, Time::Piece, Time::Seconds; +- Perl modules: Bio::SeqIO from BioPerl ( http://search.cpan.org/dist/BioPerl/ ) >= 1.6.1, XML::Simple ( http://search.cpan.org/dist/XML-Simple/ ); +- Prodigal ( http://prodigal.ornl.gov/ ) >= 2.60 ; +- tbl2asn ( http://www.ncbi.nlm.nih.gov/genbank/tbl2asn2/ ) >= 21.0 ; +- GNU Parallel ( http://www.gnu.org/software/parallel/ ) >= 20120322 ; +- Barrnap ( http://www.vicbioinformatics.com/software.barrnap.shtml ) >= 0.1 . + +Change the PROKKA_SITE_OPTIONS variable in the installed env.sh file to adjust the number of CPUs to use (--cpus). + +Note: Prokka is about a 2.0 GB download due to included custom databases. + + +