line |
stmt |
bran |
cond |
sub |
pod |
time |
code |
1
|
|
|
|
|
|
|
package BioX::Workflow::Command::run::Rules::Directives::Sample; |
2
|
|
|
|
|
|
|
|
3
|
1
|
|
|
1
|
|
544
|
use MooseX::App::Role; |
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
12
|
|
4
|
1
|
|
|
1
|
|
6581
|
use namespace::autoclean; |
|
1
|
|
|
|
|
2
|
|
|
1
|
|
|
|
|
10
|
|
5
|
|
|
|
|
|
|
|
6
|
1
|
|
|
1
|
|
72
|
use BioSAILs::Utils::Traits qw(ArrayRefOfStrs); |
|
1
|
|
|
|
|
3
|
|
|
1
|
|
|
|
|
11
|
|
7
|
1
|
|
|
1
|
|
861
|
use MooseX::Types::Path::Tiny qw/Path Paths AbsPath AbsPaths AbsFile/; |
|
1
|
|
|
|
|
4
|
|
|
1
|
|
|
|
|
8
|
|
8
|
|
|
|
|
|
|
|
9
|
|
|
|
|
|
|
=head3 sample_rule |
10
|
|
|
|
|
|
|
|
11
|
|
|
|
|
|
|
Rule to find files/samples |
12
|
|
|
|
|
|
|
|
13
|
|
|
|
|
|
|
=cut |
14
|
|
|
|
|
|
|
|
15
|
|
|
|
|
|
|
has 'sample_rule' => ( |
16
|
|
|
|
|
|
|
is => 'rw', |
17
|
|
|
|
|
|
|
isa => 'Str', |
18
|
|
|
|
|
|
|
default => sub { return "(.*)"; }, |
19
|
|
|
|
|
|
|
clearer => 'clear_sample_rule', |
20
|
|
|
|
|
|
|
predicate => 'has_sample_rule', |
21
|
|
|
|
|
|
|
); |
22
|
|
|
|
|
|
|
|
23
|
|
|
|
|
|
|
=head3 maxdepth |
24
|
|
|
|
|
|
|
|
25
|
|
|
|
|
|
|
Like find -max_depth |
26
|
|
|
|
|
|
|
|
27
|
|
|
|
|
|
|
=cut |
28
|
|
|
|
|
|
|
|
29
|
|
|
|
|
|
|
has 'maxdepth' => ( |
30
|
|
|
|
|
|
|
is => 'rw', |
31
|
|
|
|
|
|
|
default => 1 |
32
|
|
|
|
|
|
|
); |
33
|
|
|
|
|
|
|
|
34
|
|
|
|
|
|
|
=head3 sample_glob |
35
|
|
|
|
|
|
|
|
36
|
|
|
|
|
|
|
Alternately, instead of sample_rule use sample_glob to find files. Glob does not |
37
|
|
|
|
|
|
|
differentiate between files and directories. |
38
|
|
|
|
|
|
|
|
39
|
|
|
|
|
|
|
=cut |
40
|
|
|
|
|
|
|
|
41
|
|
|
|
|
|
|
has 'sample_glob' => ( |
42
|
|
|
|
|
|
|
is => 'rw', |
43
|
|
|
|
|
|
|
isa => 'Str', |
44
|
|
|
|
|
|
|
clearer => 'clear_sample_glob', |
45
|
|
|
|
|
|
|
predicate => 'has_sample_glob', |
46
|
|
|
|
|
|
|
); |
47
|
|
|
|
|
|
|
|
48
|
|
|
|
|
|
|
=head2 find_sample_bydir |
49
|
|
|
|
|
|
|
|
50
|
|
|
|
|
|
|
#Previous find_by_dir |
51
|
|
|
|
|
|
|
|
52
|
|
|
|
|
|
|
Use this option when you sample names are by directory |
53
|
|
|
|
|
|
|
The default is to find samples by filename |
54
|
|
|
|
|
|
|
|
55
|
|
|
|
|
|
|
/SAMPLE1 |
56
|
|
|
|
|
|
|
SAMPLE1_r1.fastq.gz |
57
|
|
|
|
|
|
|
SAMPLE1_r2.fastq.gz |
58
|
|
|
|
|
|
|
/SAMPLE2 |
59
|
|
|
|
|
|
|
SAMPLE2_r1.fastq.gz |
60
|
|
|
|
|
|
|
SAMPLE2_r2.fastq.gz |
61
|
|
|
|
|
|
|
|
62
|
|
|
|
|
|
|
=cut |
63
|
|
|
|
|
|
|
|
64
|
|
|
|
|
|
|
has 'find_sample_bydir' => ( |
65
|
|
|
|
|
|
|
is => 'rw', |
66
|
|
|
|
|
|
|
isa => 'Bool', |
67
|
|
|
|
|
|
|
default => 0, |
68
|
|
|
|
|
|
|
documentation => q{Use this option when you sample names are directories}, |
69
|
|
|
|
|
|
|
predicate => 'has_find_sample_bydir', |
70
|
|
|
|
|
|
|
); |
71
|
|
|
|
|
|
|
|
72
|
|
|
|
|
|
|
#Same thing - here for backwards compatibility |
73
|
|
|
|
|
|
|
|
74
|
|
|
|
|
|
|
has 'find_by_dir' => ( |
75
|
|
|
|
|
|
|
is => 'rw', |
76
|
|
|
|
|
|
|
isa => 'Bool', |
77
|
|
|
|
|
|
|
default => 0, |
78
|
|
|
|
|
|
|
documentation => q{Use this option when you sample names are directories}, |
79
|
|
|
|
|
|
|
predicate => 'has_find_by_dir', |
80
|
|
|
|
|
|
|
trigger => sub { |
81
|
|
|
|
|
|
|
my $self = shift; |
82
|
|
|
|
|
|
|
$self->find_sample_bydir( $self->find_by_dir ); |
83
|
|
|
|
|
|
|
} |
84
|
|
|
|
|
|
|
); |
85
|
|
|
|
|
|
|
|
86
|
|
|
|
|
|
|
=head3 by_sample_outdir |
87
|
|
|
|
|
|
|
|
88
|
|
|
|
|
|
|
No change - previously by sample outdir |
89
|
|
|
|
|
|
|
|
90
|
|
|
|
|
|
|
Preface outdir with sample |
91
|
|
|
|
|
|
|
|
92
|
|
|
|
|
|
|
Instead of |
93
|
|
|
|
|
|
|
|
94
|
|
|
|
|
|
|
outdir/ |
95
|
|
|
|
|
|
|
rule1 |
96
|
|
|
|
|
|
|
rule2 |
97
|
|
|
|
|
|
|
|
98
|
|
|
|
|
|
|
outdir/ |
99
|
|
|
|
|
|
|
Sample_01/ |
100
|
|
|
|
|
|
|
rule1 |
101
|
|
|
|
|
|
|
rule2 |
102
|
|
|
|
|
|
|
|
103
|
|
|
|
|
|
|
=cut |
104
|
|
|
|
|
|
|
|
105
|
|
|
|
|
|
|
has 'by_sample_outdir' => ( |
106
|
|
|
|
|
|
|
traits => ['Bool'], |
107
|
|
|
|
|
|
|
is => 'rw', |
108
|
|
|
|
|
|
|
isa => 'Bool', |
109
|
|
|
|
|
|
|
default => 0, |
110
|
|
|
|
|
|
|
documentation => q{Use this option when you sample names are directories}, |
111
|
|
|
|
|
|
|
predicate => 'has_by_sample_outdir', |
112
|
|
|
|
|
|
|
handles => { |
113
|
|
|
|
|
|
|
clear_by_sample_outdir => 'unset', |
114
|
|
|
|
|
|
|
}, |
115
|
|
|
|
|
|
|
); |
116
|
|
|
|
|
|
|
|
117
|
|
|
|
|
|
|
=head3 samples |
118
|
|
|
|
|
|
|
|
119
|
|
|
|
|
|
|
This is our actual list of samples |
120
|
|
|
|
|
|
|
|
121
|
|
|
|
|
|
|
=cut |
122
|
|
|
|
|
|
|
|
123
|
|
|
|
|
|
|
option 'samples' => ( |
124
|
|
|
|
|
|
|
traits => ['Array'], |
125
|
|
|
|
|
|
|
is => 'rw', |
126
|
|
|
|
|
|
|
isa => 'ArrayRef', |
127
|
|
|
|
|
|
|
default => sub { [] }, |
128
|
|
|
|
|
|
|
required => 0, |
129
|
|
|
|
|
|
|
cmd_split => qr/,/, |
130
|
|
|
|
|
|
|
handles => { |
131
|
|
|
|
|
|
|
all_samples => 'elements', |
132
|
|
|
|
|
|
|
has_samples => 'count', |
133
|
|
|
|
|
|
|
has_no_samples => 'is_empty', |
134
|
|
|
|
|
|
|
sorted_samples => 'sort', |
135
|
|
|
|
|
|
|
}, |
136
|
|
|
|
|
|
|
documentation => |
137
|
|
|
|
|
|
|
q{Supply samples on the command line as --samples sample1 --samples sample2, or find through sample_rule.} |
138
|
|
|
|
|
|
|
); |
139
|
|
|
|
|
|
|
|
140
|
|
|
|
|
|
|
option 'exclude_samples' => ( |
141
|
|
|
|
|
|
|
traits => ['Array'], |
142
|
|
|
|
|
|
|
is => 'rw', |
143
|
|
|
|
|
|
|
isa => 'ArrayRef', |
144
|
|
|
|
|
|
|
default => sub { [] }, |
145
|
|
|
|
|
|
|
required => 0, |
146
|
|
|
|
|
|
|
cmd_split => qr/,/, |
147
|
|
|
|
|
|
|
handles => { |
148
|
|
|
|
|
|
|
all_exclude_samples => 'elements', |
149
|
|
|
|
|
|
|
has_exclude_samples => 'count', |
150
|
|
|
|
|
|
|
has_no_exclude_samples => 'is_empty', |
151
|
|
|
|
|
|
|
sorted_exclude_samples => 'sort', |
152
|
|
|
|
|
|
|
}, |
153
|
|
|
|
|
|
|
documentation => |
154
|
|
|
|
|
|
|
q{Exclude samples from analysis --exclude_samples sample1 --exclude_samples sample2} |
155
|
|
|
|
|
|
|
); |
156
|
|
|
|
|
|
|
|
157
|
|
|
|
|
|
|
has 'sample' => ( |
158
|
|
|
|
|
|
|
is => 'rw', |
159
|
|
|
|
|
|
|
isa => 'Str', |
160
|
|
|
|
|
|
|
predicate => 'has_sample', |
161
|
|
|
|
|
|
|
clearer => 'clear_sample', |
162
|
|
|
|
|
|
|
required => 0, |
163
|
|
|
|
|
|
|
); |
164
|
|
|
|
|
|
|
|
165
|
|
|
|
|
|
|
=head3 resample |
166
|
|
|
|
|
|
|
|
167
|
|
|
|
|
|
|
Boolean value get new samples based on indir/sample_rule or no |
168
|
|
|
|
|
|
|
|
169
|
|
|
|
|
|
|
Samples are found at the beginning of the workflow, based on the global indir |
170
|
|
|
|
|
|
|
variable and the file_find. |
171
|
|
|
|
|
|
|
|
172
|
|
|
|
|
|
|
Chances are you don't want to set resample to true. These files probably won't |
173
|
|
|
|
|
|
|
exist outside of the indirectory until the pipeline is run. |
174
|
|
|
|
|
|
|
|
175
|
|
|
|
|
|
|
One example of doing so, shown in the gemini.yml in the examples directory, is |
176
|
|
|
|
|
|
|
looking for uncompressed files, .vcf extension, compressing them, and then |
177
|
|
|
|
|
|
|
resampling based on the .vcf.gz extension. |
178
|
|
|
|
|
|
|
|
179
|
|
|
|
|
|
|
=cut |
180
|
|
|
|
|
|
|
|
181
|
|
|
|
|
|
|
has 'resample' => ( |
182
|
|
|
|
|
|
|
isa => 'Bool', |
183
|
|
|
|
|
|
|
is => 'rw', |
184
|
|
|
|
|
|
|
default => 0, |
185
|
|
|
|
|
|
|
predicate => 'has_resample', |
186
|
|
|
|
|
|
|
clearer => 'clear_resample', |
187
|
|
|
|
|
|
|
); |
188
|
|
|
|
|
|
|
|
189
|
|
|
|
|
|
|
=head3 sample_files |
190
|
|
|
|
|
|
|
|
191
|
|
|
|
|
|
|
Infiles to be processed |
192
|
|
|
|
|
|
|
|
193
|
|
|
|
|
|
|
=cut |
194
|
|
|
|
|
|
|
|
195
|
|
|
|
|
|
|
has 'sample_files' => ( |
196
|
|
|
|
|
|
|
is => 'rw', |
197
|
|
|
|
|
|
|
isa => Paths, |
198
|
|
|
|
|
|
|
coerce => 1, |
199
|
|
|
|
|
|
|
); |
200
|
|
|
|
|
|
|
|
201
|
|
|
|
|
|
|
1; |