Commit c6fdb3ca02cf16028191b815709c50e118f94643 - roary

New upstream version 3.9.1+dfsg Sascha Steinbiss 6 years ago

10 changed file(s) with 193 addition(s) and 138 deletion(s). Raw diff Collapse all Expand all

-1

dist.ini less more

0	0	name = Bio-Roary
1		version = 3.9.0
	1	version = 3.9.1
2	2	author = Andrew J. Page <ap13@sanger.ac.uk>
3	3	license = GPL_3
4	4	copyright_holder = Wellcome Trust Sanger Institute

-3

lib/Bio/Roary/CommandLine/Roary.pm less more

46	46	has 'verbose_stats' => ( is => 'rw', isa => 'Bool', default => 0 );
47	47	has 'translation_table' => ( is => 'rw', isa => 'Int', default => 11 );
48	48	has 'mafft' => ( is => 'rw', isa => 'Bool', default => 0 );
	49	has 'allow_paralogs' => ( is => 'rw', isa => 'Bool', default => 0 );
49	50	has 'group_limit' => ( is => 'rw', isa => 'Num', default => 50000 );
50	51	has 'core_definition' => ( is => 'rw', isa => 'Num', default => 0.99 );
51	52	has 'verbose' => ( is => 'rw', isa => 'Bool', default => 0 );

70	71	$job_runner, $makeblastdb_exec, $mcxdeblast_exec, $mcl_exec, $blastp_exec,
71	72	$apply_unknowns_filter, $cpus, $output_multifasta_files, $verbose_stats, $translation_table,
72	73	$run_qc, $core_definition, $help, $kraken_db, $cmd_version,
73		$mafft, $output_directory, $check_dependancies, $inflation_value,
	74	$mafft, $output_directory, $check_dependancies, $inflation_value, $allow_paralogs,
74	75	);
75	76
76	77	GetOptionsFromArray(

97	98	'cd\|core_definition=f' => \$core_definition,
98	99	'v\|verbose' => \$verbose,
99	100	'n\|mafft' => \$mafft,
	101	'ap\|allow_paralogs' => \$allow_paralogs,
100	102	'k\|kraken_db=s' => \$kraken_db,
101	103	'w\|version' => \$cmd_version,
102	104	'a\|check_dependancies' => \$check_dependancies,

301	303	core_definition => $self->core_definition,
302	304	verbose => $self->verbose,
303	305	mafft => $self->mafft,
304		inflation_value => $self->inflation_value,
	306	allow_paralogs => $self->allow_paralogs,
	307	inflation_value => $self->inflation_value,
305	308	);
306	309	$pan_genome_obj->run();
307	310

342	345	-r create R plots, requires R and ggplot2
343	346	-s dont split paralogs
344	347	-t INT translation table [11]
	348	-ap allow paralogs in core alignment
345	349	-z dont delete intermediate files
346	350	-v verbose output to STDOUT
347	351	-w print version and exit
348	352	-y add gene inference information to spreadsheet, doesnt work with -e
349		-iv STR Change the MCL inflation value [1.5]
	353	-iv STR Change the MCL inflation value [1.5]
350	354	-h this help message
351	355
352	356	Example: Quickly generate a core gene alignment using 8 threads

-2

lib/Bio/Roary/CommandLine/RoaryCoreAlignment.pm less more

26	26	has 'output_filename' => ( is => 'rw', isa => 'Str', default => 'core_gene_alignment.aln' );
27	27	has 'core_definition' => ( is => 'rw', isa => 'Num', default => 0.99 );
28	28	has 'dont_delete_files' => ( is => 'rw', isa => 'Bool', default => 0 );
	29	has 'allow_paralogs' => ( is => 'rw', isa => 'Bool', default => 0 );
29	30	has '_error_message' => ( is => 'rw', isa => 'Str' );
30	31	has 'verbose' => ( is => 'rw', isa => 'Bool', default => 0 );
31	32
32	33	sub BUILD {
33	34	my ($self) = @_;
34	35
35		my ( $multifasta_base_directory, $spreadsheet_filename, $output_filename, $core_definition,$verbose, $help, $mafft, $dont_delete_files );
	36	my ( $multifasta_base_directory, $spreadsheet_filename, $output_filename, $core_definition,$verbose, $help, $mafft, $allow_paralogs, $dont_delete_files );
36	37
37	38	GetOptionsFromArray(
38	39	$self->args,

41	42	'o\|output_filename=s' => \$output_filename,
42	43	'cd\|core_definition=f' => \$core_definition,
43	44	'z\|dont_delete_files' => \$dont_delete_files,
	45	'p\|allow_paralogs' => \$allow_paralogs,
44	46	'v\|verbose' => \$verbose,
45	47	'h\|help' => \$help,
46	48	);

50	52	$self->logger->level(10000);
51	53	}
52	54	$self->help($help) if(defined($help));
	55	$self->allow_paralogs($allow_paralogs) if(defined($allow_paralogs));
53	56
54	57	if ( defined($multifasta_base_directory) && ( -d $multifasta_base_directory ) ) {
55	58	$self->multifasta_base_directory( abs_path($multifasta_base_directory));

94	97	$self->logger->info("Extract core genes from spreadsheet");
95	98	my $core_genes_obj = Bio::Roary::ExtractCoreGenesFromSpreadsheet->new(
96	99	spreadsheet => $self->spreadsheet_filename,
97		core_definition => $self->core_definition
	100	core_definition => $self->core_definition,
	101	allow_paralogs => $self->allow_paralogs
98	102	);
99	103
100	104	$self->logger->info("Looking up genes in files");

129	133	-cd FLOAT percentage of isolates a gene must be in to be core [99]
130	134	-m STR directory containing gene multi-FASTAs [pan_genome_sequences]
131	135	-s STR gene presence and absence spreadsheet [gene_presence_absence.csv]
	136	-p allow paralogs
132	137	-z dont delete intermediate files
133	138	-v verbose output to STDOUT
134	139	-h this help message

-1

lib/Bio/Roary/CommandLine/RoaryPostAnalysis.pm less more

40	40	has 'core_definition' => ( is => 'rw', isa => 'Num', default => 0.99 );
41	41	has 'verbose' => ( is => 'rw', isa => 'Bool', default => 0 );
42	42	has 'mafft' => ( is => 'rw', isa => 'Bool', default => 0 );
	43	has 'allow_paralogs' => ( is => 'rw', isa => 'Bool', default => 0 );
43	44
44	45	sub BUILD {
45	46	my ($self) = @_;

47	48	my (
48	49	$output_filename, $dont_create_rplots, $dont_delete_files, $dont_split_groups, $output_pan_geneome_filename,
49	50	$job_runner, $output_statistics_filename, $output_multifasta_files, $clusters_filename, $core_definition,
50		$fasta_files, $input_files, $verbose_stats, $translation_table, $help, $cpus,$group_limit,$verbose,$mafft
	51	$fasta_files, $input_files, $verbose_stats, $translation_table, $help, $cpus,$group_limit,$verbose,$mafft, $allow_paralogs
51	52	);
52	53
53	54

71	72	'cd\|core_definition=f' => \$core_definition,
72	73	'v\|verbose' => \$verbose,
73	74	'n\|mafft' => \$mafft,
	75	'q\|allow_paralogs' => \$allow_paralogs,
74	76	'h\|help' => \$help,
75	77	);
76	78

92	94	$self->group_limit($group_limit) if ( defined($group_limit) );
93	95	$self->core_definition( $core_definition/100 ) if ( defined($core_definition) );
94	96	$self->mafft($mafft) if ( defined($mafft) );
	97	$self->allow_paralogs($allow_paralogs) if ( defined($allow_paralogs) );
95	98	if ( defined($verbose) ) {
96	99	$self->verbose($verbose);
97	100	$self->logger->level(10000);

157	160	cpus => $self->cpus,
158	161	verbose => $self->verbose,
159	162	mafft => $self->mafft,
	163	allow_paralogs => $self->allow_paralogs,
160	164	dont_delete_files => $self->dont_delete_files,
161	165	num_input_files => $#{$input_files},
162	166	);

221	225	-n fast core gene alignement with MAFFT instead of PRANK
222	226	-o STR clusters output filename [clustered_proteins]
223	227	-p STR output pan genome filename [pan_genome.fa]
	228	-q allow paralogs in core alignment
224	229	-s STR output gene presence and absence filename [gene_presence_absence.csv]
225	230	-t INT translation table [11]
226	231	-z INT number of threads [1]

-0

lib/Bio/Roary/External/GeneAlignmentFromNucleotides.pm less more

28	28	has 'core_definition' => ( is => 'ro', isa => 'Num', default => 1 );
29	29	has 'mafft' => ( is => 'ro', isa => 'Bool', default => 0 );
30	30	has 'dont_delete_files' => ( is => 'rw', isa => 'Bool', default => 0 );
	31	has 'allow_paralogs' => ( is => 'rw', isa => 'Bool', default => 0 );
31	32	has 'num_input_files' => ( is => 'ro', isa => 'Int', required => 1);
32	33
33	34	# Overload Role`

84	85	my $core_cmd = "pan_genome_core_alignment";
85	86	$core_cmd .= " -cd " . ($self->core_definition*100) if ( defined $self->core_definition );
86	87	$core_cmd .= " --dont_delete_files " if ( defined $self->dont_delete_files && $self->dont_delete_files == 1 );
	88	$core_cmd .= " --allow_paralogs " if ( defined $self->allow_paralogs && $self->allow_paralogs == 1 );
87	89
88	90	return $core_cmd;
89	91	}

-0

lib/Bio/Roary/External/PostAnalysis.pm less more

36	36	has 'core_definition' => ( is => 'ro', isa => 'Num', default => 1.0 );
37	37	has 'verbose' => ( is => 'rw', isa => 'Bool', default => 0 );
38	38	has 'mafft' => ( is => 'ro', isa => 'Bool', default => 0 );
	39	has 'allow_paralogs' => ( is => 'ro', isa => 'Bool', default => 0 );
39	40	has '_working_directory' => ( is => 'ro', isa => 'File::Temp::Dir', default => sub { File::Temp->newdir( DIR => getcwd, CLEANUP => 1 ); } );
40	41	has '_gff_fofn' => ( is => 'ro', isa => 'Str', lazy => 1, builder => '_build__gff_fofn' );
41	42	has '_fasta_fofn' => ( is => 'ro', isa => 'Str', lazy => 1, builder => '_build__fasta_fofn' );

136	137
137	138	my $verbose_flag = '';
138	139	$verbose_flag = '-v' if ( defined($self->verbose) && $self->verbose == 1 );
	140
	141	my $allow_paralogs_flag = '';
	142	$allow_paralogs_flag = '--allow_paralogs' if ( defined($self->allow_paralogs) && $self->allow_paralogs == 1 );
139	143
140	144	return join(
141	145	" ",

155	159	$verbose_stats_flag,
156	160	$verbose_flag,
157	161	$mafft_flag,
	162	$allow_paralogs_flag,
158	163	'-j', $self->job_runner,
159	164	'--processors', $self->cpus,
160	165	'--group_limit', $self->group_limit,

+111

-114

lib/Bio/Roary/ExtractCoreGenesFromSpreadsheet.pm less more

18	18	use Bio::Roary::GroupStatistics;
19	19	use POSIX;
20	20
21		has 'spreadsheet' => ( is => 'ro', isa => 'Str', required => 1 );
22		has '_csv_parser' => ( is => 'ro', isa => 'Text::CSV',lazy => 1, builder => '_build__csv_parser' );
23		has '_input_spreadsheet_fh' => ( is => 'ro', lazy => 1, builder => '_build__input_spreadsheet_fh' );
24		has 'ordered_core_genes' => ( is => 'ro', isa => 'ArrayRef', lazy => 1, builder => '_build_ordered_core_genes' );
25		has 'core_definition' => ( is => 'ro', isa => 'Num', default => 1 );
26		has 'sample_names' => ( is => 'rw', isa => 'ArrayRef', default => sub {[]} );
27		has 'sample_names_to_genes' => ( is => 'rw', isa => 'HashRef', default => sub {{}} );
	21	has 'spreadsheet' => ( is => 'ro', isa => 'Str', required => 1 );
	22	has '_csv_parser' => ( is => 'ro', isa => 'Text::CSV', lazy => 1, builder => '_build__csv_parser' );
	23	has '_input_spreadsheet_fh' => ( is => 'ro', lazy => 1, builder => '_build__input_spreadsheet_fh' );
	24	has 'ordered_core_genes' => ( is => 'ro', isa => 'ArrayRef', lazy => 1, builder => '_build_ordered_core_genes' );
	25	has 'core_definition' => ( is => 'ro', isa => 'Num', default => 1 );
	26	has 'sample_names' => ( is => 'rw', isa => 'ArrayRef', default => sub { [] } );
	27	has 'sample_names_to_genes' => ( is => 'rw', isa => 'HashRef', default => sub { {} } );
	28	has 'allow_paralogs' => ( is => 'rw', isa => 'Bool', default => 0 );
28	29
29		has '_number_of_isolates' => ( is => 'rw', isa => 'Int');
30		has '_gene_column' => ( is => 'rw', isa => 'Int');
31		has '_num_isolates_column' => ( is => 'rw', isa => 'Int');
32		has '_avg_sequences_per_isolate_column' => ( is => 'rw', isa => 'Int');
33		has '_genome_fragement_column' => ( is => 'rw', isa => 'Int');
34		has '_order_within_fragement_column' => ( is => 'rw', isa => 'Int');
35		has '_min_no_isolates_for_core' => ( is => 'rw', isa => 'Num', lazy => 1, builder => '_build__min_no_isolates_for_core' );
	30	has '_number_of_isolates' => ( is => 'rw', isa => 'Int' );
	31	has '_gene_column' => ( is => 'rw', isa => 'Int' );
	32	has '_num_isolates_column' => ( is => 'rw', isa => 'Int' );
	33	has '_avg_sequences_per_isolate_column' => ( is => 'rw', isa => 'Int' );
	34	has '_genome_fragement_column' => ( is => 'rw', isa => 'Int' );
	35	has '_order_within_fragement_column' => ( is => 'rw', isa => 'Int' );
	36	has '_min_no_isolates_for_core' => ( is => 'rw', isa => 'Num', lazy => 1, builder => '_build__min_no_isolates_for_core' );
36	37
37	38	sub _build__min_no_isolates_for_core {
38		my ($self) = @_;
39		my $threshold = $self->_number_of_isolates * $self->core_definition;
	39	my ($self) = @_;
	40	my $threshold = $self->_number_of_isolates * $self->core_definition;
40	41
41		return $threshold;
	42	return $threshold;
42	43	}
43	44
44		sub _build__csv_parser
45		{
46		my ($self) = @_;
47		return Text::CSV->new( { binary => 1, always_quote => 1} );
	45	sub _build__csv_parser {
	46	my ($self) = @_;
	47	return Text::CSV->new( { binary => 1, always_quote => 1 } );
48	48	}
49	49
50	50	sub _build__input_spreadsheet_fh {

53	53	return $fh;
54	54	}
55	55
56		sub _update_number_of_isolates
57		{
58		my ($self, $header_row) = @_;
59		my $number_of_isolates = @{$header_row} - @{Bio::Roary::GroupStatistics->fixed_headers};
60		$self->_number_of_isolates($number_of_isolates);
	56	sub _update_number_of_isolates {
	57	my ( $self, $header_row ) = @_;
	58	my $number_of_isolates = @{$header_row} - @{ Bio::Roary::GroupStatistics->fixed_headers };
	59	$self->_number_of_isolates($number_of_isolates);
61	60	}
62	61
63		sub _setup_column_mappings
64		{
65		my ($self, $header_row) = @_;
66		# current ordering
67		my %columns_of_interest_mappings = (
68		'Gene' => 0,
69		'No. isolates' => 3,
70		'Avg sequences per isolate' => 5,
71		'Genome Fragment' => 6,
72		'Order within Fragment' => 7,
73		'QC' => 10,
	62	sub _setup_column_mappings {
	63	my ( $self, $header_row ) = @_;
	64
	65	# current ordering
	66	my %columns_of_interest_mappings = (
	67	'Gene' => 0,
	68	'No. isolates' => 3,
	69	'Avg sequences per isolate' => 5,
	70	'Genome Fragment' => 6,
	71	'Order within Fragment' => 7,
	72	'QC' => 10,
74	73	);
75
76		# Dynamically overwrite the default ordering
77		for(my $i = 0; $i < @{$header_row}; $i++)
78		{
79		for my $col_name (%columns_of_interest_mappings)
80		{
81		if($header_row->[$i] eq $col_name)
82		{
83		$columns_of_interest_mappings{$col_name} = $i;
84		last;
85		}
	74
	75	# Dynamically overwrite the default ordering
	76	for ( my $i = 0 ; $i < @{$header_row} ; $i++ ) {
	77	for my $col_name (%columns_of_interest_mappings) {
	78	if ( $header_row->[$i] eq $col_name ) {
	79	$columns_of_interest_mappings{$col_name} = $i;
	80	last;
	81	}
	82	}
86	83	}
87		}
88		$self->_gene_column($columns_of_interest_mappings{'Gene'});
89		$self->_num_isolates_column($columns_of_interest_mappings{'No. isolates'});
90		$self->_avg_sequences_per_isolate_column($columns_of_interest_mappings{'Avg sequences per isolate'});
91		$self->_genome_fragement_column($columns_of_interest_mappings{'Genome Fragment'});
92		$self->_order_within_fragement_column($columns_of_interest_mappings{'Order within Fragment'});
93		$self->_update_number_of_isolates($header_row);
94
95		# Get the sample_names
96		my @sample_names;
97		for(my $i = $self->_length_of_fixed_headers(); $i < @{$header_row}; $i++)
98		{
99		push(@sample_names,$header_row->[$i]);
100		}
101		$self->sample_names(\@sample_names);
	84	$self->_gene_column( $columns_of_interest_mappings{'Gene'} );
	85	$self->_num_isolates_column( $columns_of_interest_mappings{'No. isolates'} );
	86	$self->_avg_sequences_per_isolate_column( $columns_of_interest_mappings{'Avg sequences per isolate'} );
	87	$self->_genome_fragement_column( $columns_of_interest_mappings{'Genome Fragment'} );
	88	$self->_order_within_fragement_column( $columns_of_interest_mappings{'Order within Fragment'} );
	89	$self->_update_number_of_isolates($header_row);
	90
	91	# Get the sample_names
	92	my @sample_names;
	93	for ( my $i = $self->_length_of_fixed_headers() ; $i < @{$header_row} ; $i++ ) {
	94	push( @sample_names, $header_row->[$i] );
	95	}
	96	$self->sample_names( \@sample_names );
102	97	}
103	98
104		sub _length_of_fixed_headers
105		{
106		my ($self) = @_;
107		return @{Bio::Roary::GroupStatistics->fixed_headers()};
	99	sub _length_of_fixed_headers {
	100	my ($self) = @_;
	101	return @{ Bio::Roary::GroupStatistics->fixed_headers() };
108	102	}
109	103
110		sub _populate_sample_to_gene_lookup_with_row
111		{
112		my ($self, $row) = @_;
113
114		for(my $i = $self->_length_of_fixed_headers(); $i < @{$row}; $i++ )
115		{
116		if(defined($row->[$i]) && $row->[$i] ne "" )
117		{
118		my $sample_name = $self->sample_names->[$i - $self->_length_of_fixed_headers()];
119
120		$self->sample_names_to_genes->{$sample_name}->{$row->[$i]} = 1;
121		}
122		}
123		return 1;
	104	sub _populate_sample_to_gene_lookup_with_row {
	105	my ( $self, $row ) = @_;
	106
	107	for ( my $i = $self->_length_of_fixed_headers() ; $i < @{$row} ; $i++ ) {
	108	if ( defined( $row->[$i] ) && $row->[$i] ne "" ) {
	109	my $sample_name = $self->sample_names->[ $i - $self->_length_of_fixed_headers() ];
	110
	111	$self->sample_names_to_genes->{$sample_name}->{ $row->[$i] } = 1;
	112	}
	113	}
	114	return 1;
124	115	}
125	116
	117	sub _ordered_core_genes {
	118	my ($self) = @_;
	119	my %ordered_genes;
	120	while ( my $row = $self->_csv_parser->getline( $self->_input_spreadsheet_fh ) ) {
	121	next if ( @{$row} < 12 ); # no genes in group
	122	next if ( !defined( $row->[ $self->_gene_column ] ) \|\| $row->[ $self->_gene_column ] eq '' ); # no gene name
	123	next
	124	if ( !defined( $row->[ $self->_avg_sequences_per_isolate_column ] ) \|\| $row->[ $self->_avg_sequences_per_isolate_column ] eq '' )
	125	; # no average
	126	next
	127	if ( !defined( $row->[ $self->_genome_fragement_column ] ) \|\| $row->[ $self->_genome_fragement_column ] eq '' )
	128	; # fragment not defined
126	129
127		sub _ordered_core_genes
128		{
129		my ($self) = @_;
130		my %ordered_genes;
131		while ( my $row = $self->_csv_parser->getline( $self->_input_spreadsheet_fh ) )
132		{
133		next if(@{$row} < 12); # no genes in group
134		next if(!defined($row->[$self->_gene_column]) \|\| $row->[$self->_gene_column] eq '' ); # no gene name
135		next if(!defined($row->[$self->_avg_sequences_per_isolate_column]) \|\| $row->[$self->_avg_sequences_per_isolate_column] eq '' ); # no average
136		next if(!defined($row->[$self->_genome_fragement_column]) \|\| $row->[$self->_genome_fragement_column] eq '' ); # fragment not defined
137
138		# next if($self->_number_of_isolates != $row->[$self->_num_isolates_column]); # if gene is not in all isolates
139		next if ( $row->[$self->_num_isolates_column] < $self->_min_no_isolates_for_core );
140		next if($row->[$self->_avg_sequences_per_isolate_column] != 1);
141		$ordered_genes{$row->[$self->_genome_fragement_column]}{$row->[$self->_order_within_fragement_column]} = $row->[$self->_gene_column];
142		$self->_populate_sample_to_gene_lookup_with_row($row);
143		}
144
145		my @ordered_core_genes ;
146		for my $fragment_key(sort {$a <=> $b } keys %ordered_genes)
147		{
148		for my $order_within_fragement(sort {$a <=> $b } keys %{$ordered_genes{$fragment_key}})
149		{
150		push(@ordered_core_genes,$ordered_genes{$fragment_key}{$order_within_fragement});
	130	# next if($self->_number_of_isolates != $row->[$self->_num_isolates_column]); # if gene is not in all isolates
	131	next if ( $row->[ $self->_num_isolates_column ] < $self->_min_no_isolates_for_core );
	132
	133	if ( $self->allow_paralogs ) {
	134	# should never happen
	135	next if ( $row->[ $self->_avg_sequences_per_isolate_column ] < 1 );
	136	}
	137	else {
	138	next if ( $row->[ $self->_avg_sequences_per_isolate_column ] != 1 );
	139	}
	140
	141	$ordered_genes{ $row->[ $self->_genome_fragement_column ] }{ $row->[ $self->_order_within_fragement_column ] } =
	142	$row->[ $self->_gene_column ];
	143	$self->_populate_sample_to_gene_lookup_with_row($row);
151	144	}
152		}
153		return \@ordered_core_genes;
	145
	146	my @ordered_core_genes;
	147	for my $fragment_key ( sort { $a <=> $b } keys %ordered_genes ) {
	148	for my $order_within_fragement ( sort { $a <=> $b } keys %{ $ordered_genes{$fragment_key} } ) {
	149	push( @ordered_core_genes, $ordered_genes{$fragment_key}{$order_within_fragement} );
	150	}
	151	}
	152	return \@ordered_core_genes;
154	153	}
155	154
156		sub _build_ordered_core_genes
157		{
158		my ($self) = @_;
159		my $header_row = $self->_csv_parser->getline( $self->_input_spreadsheet_fh );
160		$self->_setup_column_mappings($header_row);
	155	sub _build_ordered_core_genes {
	156	my ($self) = @_;
	157	my $header_row = $self->_csv_parser->getline( $self->_input_spreadsheet_fh );
	158	$self->_setup_column_mappings($header_row);
161	159
162		return $self->_ordered_core_genes();
	160	return $self->_ordered_core_genes();
163	161	}
164
165	162
166	163	no Moose;
167	164	__PACKAGE__->meta->make_immutable;

-1

lib/Bio/Roary/MergeMultifastaAlignments.pm less more

71	71	my ( $self, $sample_name, $gene_file ) = @_;
72	72
73	73	# loop over this to get the geneIDs
74		for my $gene_id ( keys %{ $self->_gene_to_sequence->{$gene_file} } ) {
	74	for my $gene_id ( sort keys %{ $self->_gene_to_sequence->{$gene_file} } ) {
75	75	if ( defined( $self->sample_names_to_genes->{$sample_name}->{$gene_id} ) ) {
76	76	return $self->_gene_to_sequence->{$gene_file}->{$gene_id};
77	77	}

-0

lib/Bio/Roary.pm less more

47	47	has 'verbose' => ( is => 'rw', isa => 'Bool', default => 0 );
48	48	has 'mafft' => ( is => 'ro', isa => 'Bool', default => 0 );
49	49	has 'inflation_value' => ( is => 'rw', isa => 'Num', default => 1.5 );
	50	has 'allow_paralogs' => ( is => 'rw', isa => 'Bool', default => 0 );
50	51
51	52	has 'output_multifasta_files' => ( is => 'ro', isa => 'Bool', default => 0 );
52	53

135	136	core_definition => $self->core_definition,
136	137	verbose => $self->verbose,
137	138	mafft => $self->mafft,
	139	allow_paralogs => $self->allow_paralogs,
138	140	);
139	141	$post_analysis->run();
140	142

+51

-16

t/Bio/Roary/ExtractCoreGenesFromSpreadsheet.t less more

12	12
13	13	my $obj;
14	14
15		ok($obj = Bio::Roary::ExtractCoreGenesFromSpreadsheet->new(
16		spreadsheet => 't/data/core_group_statistics.csv',
17		),'initalise obj');
18		is_deeply($obj->ordered_core_genes, ['argF','speH','group_5'], 'Correct ordering');
19		is_deeply($obj->sample_names_to_genes, {
20		'query_2' => {
21		'2_3' => 1,
22		'2_7' => 1,
23		'2_2' => 1
24		},
25		'query_1' => {
26		'1_6' => 1,
27		'1_3' => 1,
28		'1_2' => 1
29		}
30		}, 'Correct of sample names to genes is correct');
	15	ok(
	16	$obj = Bio::Roary::ExtractCoreGenesFromSpreadsheet->new(
	17	spreadsheet => 't/data/core_group_statistics.csv',
	18	),
	19	'initalise obj'
	20	);
	21	is_deeply( $obj->ordered_core_genes, [ 'argF', 'speH', 'group_5' ], 'Correct ordering' );
	22	is_deeply(
	23	$obj->sample_names_to_genes,
	24	{
	25	'query_2' => {
	26	'2_3' => 1,
	27	'2_7' => 1,
	28	'2_2' => 1
	29	},
	30	'query_1' => {
	31	'1_6' => 1,
	32	'1_3' => 1,
	33	'1_2' => 1
	34	}
	35	},
	36	'Correct of sample names to genes is correct'
	37	);
	38
	39	ok(
	40	$obj = Bio::Roary::ExtractCoreGenesFromSpreadsheet->new(
	41	spreadsheet => 't/data/core_group_statistics.csv',
	42	allow_paralogs => 1,
	43	),
	44	'initalise obj where paralogs allowed'
	45	);
	46	is_deeply( $obj->ordered_core_genes, [ 'argF', 'hly', 'speH', 'group_5' ], 'Correct ordering where paralogs allowed' );
	47
	48	is_deeply(
	49	$obj->sample_names_to_genes,
	50	{
	51	'query_2' => {
	52	'2_3' => 1,
	53	'2_7' => 1,
	54	'2_1' => 1,
	55	'2_2' => 1
	56	},
	57	'query_1' => {
	58	'1_6' => 1,
	59	'1_3' => 1,
	60	'1_1' => 1,
	61	'1_2' => 1
	62	}
	63	},
	64	'Correct of sample names to genes is correct where paralogs allowed'
	65	);
31	66
32	67	done_testing();