File Coverage

lib/Bio/Roary/CommandLine/CreatePanGenome.pm
Criterion Covered Total %
statement 18 20 90.0
branch n/a
condition n/a
subroutine 6 7 85.7
pod 0 1 0.0
total 24 28 85.7


line stmt bran cond sub pod time code
1             undef $VERSION;
2             package Bio::Roary::CommandLine::CreatePanGenome;
3             $Bio::Roary::CommandLine::CreatePanGenome::VERSION = '3.11.0';
4             # ABSTRACT: Take in FASTA files of proteins and cluster them
5              
6              
7 1     1   1039 use Moose;
  1         3  
  1         7  
8 1     1   5532 use Getopt::Long qw(GetOptionsFromArray);
  1         2  
  1         7  
9 1     1   130 use Bio::Roary;
  1         2  
  1         16  
10 1     1   5 use Bio::Roary::PrepareInputFiles;
  1         2  
  1         18  
11 1     1   4 use Bio::Roary::QC::Report;
  1         2  
  1         118  
12             extends 'Bio::Roary::CommandLine::Roary';
13              
14             has 'job_runner' => ( is => 'rw', isa => 'Str', default => 'Local' );
15             has 'output_multifasta_files' => ( is => 'rw', isa => 'Bool', default => 1 );
16             has 'dont_create_rplots' => ( is => 'rw', isa => 'Bool', default => 0 );
17             has 'core_definition' => ( is => 'rw', isa => 'Num', default => 0.99 );
18             has 'run_qc' => ( is => 'rw', isa => 'Bool', default => 1 );
19              
20             sub usage_text {
21 0     0 0   my ($self) = @_;
22              
23 0           return <<USAGE;
24             Usage: create_pan_genome [options] *.gff
25             Build a pan genome with WTSI defaults.
26              
27             Options: -p INT number of threads [1]
28             -o STR clusters output filename [clustered_proteins]
29             -f STR output directory [.]
30             -e create a multiFASTA alignment of core genes
31             -n fast core gene alignement with MAFFT, use with -e
32             -i minimum percentage identity for blastp [95]
33             -cd FLOAT percentage of isolates a gene must be in to be core [99]
34             -z dont delete intermediate files
35             -t INT translation table [11]
36             -v verbose output to STDOUT
37             -y add gene inference information to spreadsheet, doesnt work with -e
38             -g INT maximum number of clusters [50000]
39             -qc generate QC report with Kraken
40             -k STR path to Kraken database for QC, use with -qc
41             -w print version and exit
42             -a check dependancies and print versions
43             -h this help message
44              
45             Example: Quickly generate a core gene alignment using 16 threads
46              
47             bsub.py --threads 16 10 log create_pan_genome -e --mafft -p 16 *.gff
48            
49             Example: Allow Roary to bsub the jobs to LSF - you cant bsub this command itself
50              
51             create_pan_genome -j LSF -e --mafft -p 16 *.gff
52            
53             Example: Create a tree and visualise with iCANDY
54              
55             annotationfind –t file –i file_of_lanes -symlink .
56             bsub.py --threads 16 10 log create_pan_genome -e --mafft -p 16 *.gff
57             ~sh16/scripts/run_RAxML.py -a core_gene_alignment.aln -q normal -M 8 -n 8 -V AVX -o tree
58             bsub.py 10 log ~sh16/scripts/iCANDY.py -t RAxML_bipartitions.tree -q taxa -l 1 -E 30 -o accessory.pdf -M -L left -p A1 -g 90 accessory.tab accessory.header.embl
59              
60             For further info see: http://mediawiki.internal.sanger.ac.uk/index.php/Pathogen_Informatics_Pan_Genome_Pipeline
61              
62             USAGE
63             }
64              
65             __PACKAGE__->meta->make_immutable;
66 1     1   5 no Moose;
  1         3  
  1         4  
67             1;
68              
69             __END__
70              
71             =pod
72              
73             =encoding UTF-8
74              
75             =head1 NAME
76              
77             Bio::Roary::CommandLine::CreatePanGenome - Take in FASTA files of proteins and cluster them
78              
79             =head1 VERSION
80              
81             version 3.11.0
82              
83             =head1 SYNOPSIS
84              
85             Take in FASTA files of proteins and cluster them
86              
87             =head1 AUTHOR
88              
89             Andrew J. Page <ap13@sanger.ac.uk>
90              
91             =head1 COPYRIGHT AND LICENSE
92              
93             This software is Copyright (c) 2013 by Wellcome Trust Sanger Institute.
94              
95             This is free software, licensed under:
96              
97             The GNU General Public License, Version 3, June 2007
98              
99             =cut