File: filenames.yaml

package info (click to toggle)
qcumber 2.3.0-2
  • links: PTS, VCS
  • area: main
  • in suites: bullseye, sid
  • size: 2,276 kB
  • sloc: python: 3,097; sh: 153; makefile: 18
file content (219 lines) | stat: -rw-r--r-- 6,042 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
# Filename conventions for FastQ files

ion_torrent_bam:
    main_exts:
        - '.bam'
    formats:
        - some_ion_torrent_format:
            main_sep: '_'
            format:
                sample_name:
                    regex: '.+'


illumina_fastq:
    main_exts: ['.fasta', '.fastq', '.fas', '.fna', '.fnq', '.fa']
    secondary_exts: ['.gz', '.xz', '.bz2', '.lzma', '.lzo', '.lz', '.rz']
    formats:
        - illumina_basel_fastq:
            main_sep: '_'
            id_fields: ['openBIS_id', 'sample_name']
            format:
                openBIS_id:
                    subf_num: 3
                flowcell: {}
                lane_short:
                    regex: '\d+'
                sample_name:
                    subf_num: 2
                index:
                    subf_num: 2
                sample_num:
                    regex: 'S\d+'
                lane:
                    regex: 'L\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'
                mismatches_index:
                    regex: 'MM_\d+'
                    optional: True
        
        - illumina_legacy1_fastq:
            main_sep: '_'
            id_fields: ['sample_name', 'unknown1', 'date', 'unknown2']
            id_sep: '_'
            format:
                sample_name:
                    subf_num: 4
                unknown1: {}
                date:
                    subf_num: 3
                unknown2:
                    subf_num: 3
                barcode: {}
                lane:
                    regex: 'L\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'

        - illumina_legacy2_fastq:
            main_sep: '_'
            id_fields: ['sample_name', 'unknown1', 'date', 'unknown2']
            id_sep: '_'
            format:
                sample_name:
                    subf_num: 4
                unknown1:
                    subf_num: 2
                date:
                    subf_num: 3
                unknown2:
                    subf_num: 3
                barcode: {}
                lane:
                    regex: 'L\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'

        - illumina_someinstitution1_fastq:
            main_sep: '_'
            format:
                sample_name:
                    subf_num: 3
                sample_num:
                    regex: 'S\d+'
                lane:
                    regex: 'L\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'

        - illumina_someinstitution1.2_fastq:
            main_sep: '_'
            format:
                sample_name:
                    subf_num: 5
                    subf_sep: '-'
                sample_num:
                    regex: 'S\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'
        
        - illumina_someinstitution2_fastq:
            main_sep: '_'
            format:
                sample_name:
                    subf_num: 3
                    subf_sep: '-'
                sample_num:
                    regex: 'S\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'
        
        - illumina_someinstitution2.1_fastq:
            main_sep: '_'
            format:
                sample_name:
                    subf_num: 2
                    subf_sep: '-'
                sample_num:
                    regex: 'S\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'

        - illumina_standard_fastq:
            main_sep: '_'
            format:
                sample_name: {}
                sample_num:
                    regex: 'S\d+'
                lane:
                    regex: 'L\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'

        - illumina_fallback1_fastq:
            main_sep: '_'
            format:
                sample_name: 
                    regex: '.+'
                sample_num:
                    regex: 'S\d+'
                lane:
                    regex: 'L\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'

        - illumina_fallback2_fastq:
            main_sep: '_'
            format:
                sample_name: 
                    regex: '.+'
                lane:
                    regex: 'L\d+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'
        
        - illumina_fallback3_fastq:
            main_sep: '_'
            format:
                sample_name: 
                    regex: '.+'
                read:
                    regex: 'R\d+'
                running_num:
                    regex: '\d+'

        - sra_standard_paired_fastq:
            main_sep: '_'
            format:
                sample_name:
                    regex: 'SRR.+'
                read:
                    regex: '\d'

        - sra_standard_single_fastq:
            main_sep: '_'
            format:
               sample_name:
                   regex: 'SRR.+'

        - dwgsim2_paired_bwa_fastq:
            main_sep: '\.'
            format:
                sample_name:
                    regex: '.+'
                bwa_flag:
                    regex: 'bwa'
                read:
                    regex: 'read\d'
pacbio:
    main_exts: ['.bax', '.h5', '.xml']
    secondary_exts: ['.h5']
    formats:
        - standard_pacbio:
            main_sep: '\.'
            format:
                sample_name:
                    regex: '.+'
                file_selector: {}