# HG changeset patch # User crs4 # Date 1380213592 14400 # Node ID 4b6f16a79fe4a3bfe31f439a4cc942bbbe3966d5 # Parent 95505a9fa26fb87a27df82308717fe5304a2750a Add txt output file. Use a definition list instead of a block quote in . Correct 2 dependency minimum versions. diff -r 95505a9fa26f -r 4b6f16a79fe4 prokka.py --- a/prokka.py Tue Sep 10 13:11:26 2013 -0400 +++ b/prokka.py Thu Sep 26 12:39:52 2013 -0400 @@ -21,15 +21,16 @@ 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('--gff', dest="gff", help="This is the master annotation in GFF3 format, containing both sequences and annotations") + 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('--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('--txt', dest='txt', help='Statistics relating to the annotated features found') 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: @@ -39,9 +40,9 @@ 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 + print '\nProkka command to be executed:\n %s' % cl # Run command log = open(options.log, 'w') if options.log else sys.stdout @@ -50,11 +51,11 @@ finally: if log != sys.stdout: log.close() - + # Rename output files - suffix = ['gbk', 'fna', 'faa', 'ffn', 'sqn', 'fsa', 'tbl', 'err', 'gff'] + suffix = ['gff', 'gbk', 'fna', 'faa', 'ffn', 'sqn', 'fsa', 'tbl', 'err', 'txt'] for s in suffix: - shutil.move( 'prokka.' + s, getattr(options, s)) + shutil.move('prokka.' + s, getattr(options, s)) if __name__ == "__main__": __main__() diff -r 95505a9fa26f -r 4b6f16a79fe4 prokka.xml --- a/prokka.xml Tue Sep 10 13:11:26 2013 -0400 +++ b/prokka.xml Thu Sep 26 12:39:52 2013 -0400 @@ -1,4 +1,4 @@ - + Prokaryotic Annotation blast+ @@ -34,6 +34,7 @@ --fsa=$out_fsa --tbl=$out_tbl --err=$out_err + --txt=$out_txt --log=$out_log @@ -53,45 +54,52 @@ - - - - - - - - - - + + + + + + + + + + + **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_ 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:: +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. +gff + This is the master annotation in GFF3 format, containing both sequences and annotations +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 +txt + Statistics relating to the annotated features found **License and citation** diff -r 95505a9fa26f -r 4b6f16a79fe4 tool_dependencies.xml --- a/tool_dependencies.xml Tue Sep 10 13:11:26 2013 -0400 +++ b/tool_dependencies.xml Thu Sep 26 12:39:52 2013 -0400 @@ -31,10 +31,10 @@ 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/ ); +- Perl modules: Bio::SeqIO from BioPerl ( http://search.cpan.org/dist/BioPerl/ ) >= 1.6.900, 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 ; +- GNU Parallel ( http://www.gnu.org/software/parallel/ ) >= 20130422 ; - 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).