Mercurial > repos > gbcs-embl-heidelberg > je_demultiplex
annotate je-demultiplex.xml @ 7:8f16495dc5f2 draft
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
| author | gbcs-embl-heidelberg |
|---|---|
| date | Mon, 05 Mar 2018 07:12:52 -0500 |
| parents | 222819c87d90 |
| children |
| rev | line source |
|---|---|
|
3
8930b411a9d7
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit dd9e62bdb01d1252a90ce778103ce9b6b4a8cd52-dirty
gbcs-embl-heidelberg
parents:
0
diff
changeset
|
1 <tool id="je_demultiplex" name="Je-Demultiplex" version="@VERSION_STRING@"> |
| 0 | 2 <description>demultiplexes fastq files</description> |
| 3 <macros> | |
| 4 <import>macros.xml</import> | |
| 5 </macros> | |
|
5
222819c87d90
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents:
3
diff
changeset
|
6 <expand macro="requirements" /> |
| 0 | 7 <stdio> |
| 8 <exit_code range="1:" level="fatal" description="Tool exception" /> | |
| 9 </stdio> | |
|
5
222819c87d90
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents:
3
diff
changeset
|
10 <expand macro="version_command" /> |
|
222819c87d90
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents:
3
diff
changeset
|
11 <command> |
| 0 | 12 <![CDATA[ |
| 13 je demultiplex | |
| 14 | |
| 15 ## Fastq inputs | |
| 16 @single_or_paired_cmd@ | |
| 17 #if str( $library.type ) != "single": | |
| 18 @demultiplex_paired_end_cmd_options@ | |
| 19 #end if | |
| 20 | |
| 21 @barcode_option_cmd@ | |
| 22 @barcode_len_cmd@ | |
| 23 C=$CLIP_BARCODE | |
| 24 | |
| 25 @demultiplexer_common_options_cmd@ | |
| 26 @common_options_cmd@ | |
| 27 | |
| 28 @demultiplexer_common_output_options_cmd@ | |
| 29 @demultiplexer_common_outputs_cmd@ | |
| 30 | |
| 31 ]]> | |
| 32 </command> | |
| 33 <configfiles> | |
| 34 <expand macro="barcode_config_file"></expand> | |
| 35 </configfiles> | |
| 36 <inputs> | |
| 37 <!-- single/paired - similar to macro 'single_or_paired_general' --> | |
| 38 <expand macro="single_or_paired_general"> | |
| 39 <expand macro="demultiplex_paired_end_options"/> | |
| 40 </expand> | |
| 41 | |
| 42 <expand macro="barcode_option"/> | |
| 43 <expand macro="barcode_len_option"/> | |
| 44 <expand macro="clip_barcode"/> | |
| 45 | |
| 46 <expand macro="demultiplexer_common_options"/> | |
| 47 | |
| 48 <expand macro="common_options"/> | |
| 49 | |
| 50 <expand macro="demultiplexer_common_output_options"/> | |
| 51 | |
| 52 </inputs> | |
| 53 <outputs> | |
| 54 <expand macro="demultiplexer_common_outputs"/> | |
| 55 </outputs> | |
| 56 | |
| 57 <tests> | |
| 58 <test> | |
| 59 <!-- simple test on single end data --> | |
| 60 <param name="type" value="single"/> | |
| 61 <param name="input_1" value="file_1_sequence.txt" ftype="fastqsanger"/> | |
| 62 <param name="BARCODE_FILE" value="barcodes_SE.txt" ftype="tabular"/> | |
|
7
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
63 <output name="METRICS_FILE_NAME" file="summary_SE.txt" ftype="tabular" lines_diff="4"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
64 <output name="DEMULTIPLEX_RESULTS" ftype="tabular"> |
| 0 | 65 <discovered_dataset designation="unassigned_1" file="unassigned_1_SE.txt" /> |
| 66 </output> | |
| 67 </test> | |
| 68 <test> | |
| 69 <!-- more complex test on paired end data with different barcode for fwd/rev --> | |
| 70 <param name="type" value="paired"/> | |
| 71 <param name="input_1" value="file_1_sequence.txt" ftype="fastqsanger"/> | |
| 72 <param name="input_2" value="file_2_sequence.txt" ftype="fastqsanger"/> | |
| 73 | |
| 74 <param name="BPOS" value="BOTH"/> | |
| 75 <param name="BM" value="BOTH"/> | |
| 76 <param name="BRED" value="false"/> | |
| 77 | |
|
7
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
78 <param name="COLLECT_OUTPUTS" value="false" /> |
| 0 | 79 <param name="barcode_list_type_con" value="text"/> |
| 80 <param name="barcode_text" | |
| 81 value="sample1 CACTGT:GTATAG sample2 ATTCCG:TCCGTC sample3 GCTACC:TGGTCA sample4 CGAAAC:CACTGT"/> | |
|
7
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
82 <output name="METRICS_FILE_NAME" file="summary_PE.txt" ftype="tabular" lines_diff="4"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
83 <output name="DEMULTIPLEX_RESULTS" ftype="tabular"> |
| 0 | 84 <discovered_dataset designation="unassigned_1" file="unassigned_1_PE.txt" /> |
| 85 <discovered_dataset designation="unassigned_2" file="unassigned_2_PE.txt" /> | |
| 86 <discovered_dataset designation="sample4_CGAAACCACTGT_2" file="sample4_CGAAACCACTGT_2.txt"/> | |
| 87 <discovered_dataset designation="sample4_CGAAACCACTGT_1" file="sample4_CGAAACCACTGT_1.txt"/> | |
| 88 <discovered_dataset designation="sample3_GCTACCTGGTCA_2" file="sample3_GCTACCTGGTCA_2.txt"/> | |
| 89 <discovered_dataset designation="sample3_GCTACCTGGTCA_1" file="sample3_GCTACCTGGTCA_1.txt"/> | |
| 90 <discovered_dataset designation="sample2_ATTCCGTCCGTC_2" file="sample2_ATTCCGTCCGTC_2.txt"/> | |
| 91 <discovered_dataset designation="sample2_ATTCCGTCCGTC_1" file="sample2_ATTCCGTCCGTC_1.txt"/> | |
| 92 <discovered_dataset designation="sample1_CACTGTGTATAG_2" file="sample1_CACTGTGTATAG_2.txt"/> | |
| 93 <discovered_dataset designation="sample1_CACTGTGTATAG_1" file="sample1_CACTGTGTATAG_1.txt"/> | |
| 94 </output> | |
| 95 </test> | |
|
7
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
96 <test> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
97 <!-- Repeat of previous but with collection outputs --> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
98 <param name="type" value="paired"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
99 <param name="input_1" value="file_1_sequence.txt" ftype="fastqsanger"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
100 <param name="input_2" value="file_2_sequence.txt" ftype="fastqsanger"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
101 |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
102 <param name="BPOS" value="BOTH"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
103 <param name="BM" value="BOTH"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
104 <param name="BRED" value="false"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
105 <param name="barcode_list_type_con" value="text"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
106 <param name="barcode_text" |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
107 value="sample1 CACTGT:GTATAG sample2 ATTCCG:TCCGTC sample3 GCTACC:TGGTCA sample4 CGAAAC:CACTGT"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
108 <param name="COLLECT_OUTPUTS" value="true" /> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
109 |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
110 <output_collection name="COLLECTION_1" type="list"> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
111 <element name="sample1_CACTGTGTATAG_1.txt" value="sample4_CGAAACCACTGT_1.txt"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
112 <element name="sample3_GCTACCTGGTCA_1.txt" value="sample3_GCTACCTGGTCA_1.txt"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
113 <element name="sample2_ATTCCGTCCGTC_1.txt" value="sample2_ATTCCGTCCGTC_1.txt"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
114 <element name="sample1_CACTGTGTATAG_1.txt" value="sample1_CACTGTGTATAG_1.txt"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
115 </output_collection> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
116 <output_collection name="COLLECTION_2" type="list"> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
117 <element name="sample4_CGAAACCACTGT_2.txt" value="sample4_CGAAACCACTGT_2.txt"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
118 <element name="sample3_GCTACCTGGTCA_2.txt" value="sample3_GCTACCTGGTCA_2.txt"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
119 <element name="sample2_ATTCCGTCCGTC_2.txt" value="sample2_ATTCCGTCCGTC_2.txt"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
120 <element name="sample1_CACTGTGTATAG_2.txt" value="sample1_CACTGTGTATAG_2.txt"/> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
121 </output_collection> |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
122 </test> |
| 0 | 123 </tests> |
| 124 | |
|
5
222819c87d90
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents:
3
diff
changeset
|
125 <help> |
| 0 | 126 <![CDATA[ |
| 127 **What it does** | |
| 128 | |
| 129 Je demultiplex: A fastq file demultiplexer with optional handling of Unique Molecular Identifiers for further use | |
| 130 in 'markdupes' module. | |
| 131 Input files are fastq files, and can be in gzip compressed format. | |
| 132 | |
| 133 Author: Charles Girardot (charles.girardot@embl.de). | |
| 134 | |
| 135 Wrapper by: Jelle Scholtalbers (jelle.scholtalbers@embl.de). | |
| 136 | |
|
7
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
137 With contributions by: Mehmet Tekman (@mtekman) |
|
8f16495dc5f2
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit e217faa15f73427979bb212036cb130a14c59750
gbcs-embl-heidelberg
parents:
5
diff
changeset
|
138 |
| 0 | 139 ------ |
| 140 | |
| 141 **Know what you are doing** | |
| 142 | |
| 143 .. class:: warningmark | |
| 144 | |
| 145 You will want to read the `documentation`__. | |
| 146 | |
| 147 .. __: http://gbcs.embl.de/portal/Je | |
| 148 | |
| 149 ------ | |
| 150 | |
| 151 **Parameter list** | |
| 152 | |
| 153 This is an exhaustive list of options:: | |
| 154 | |
| 155 FASTQ_FILE1=File | |
| 156 F1=File | |
| 157 | |
| 158 Input fastq file (optionally gzipped) for single end data, or first read in paired end | |
| 159 data. | |
| 160 | |
| 161 Required. | |
| 162 | |
| 163 FASTQ_FILE2=File | |
| 164 F2=File | |
| 165 | |
| 166 Input fastq file (optionally gzipped) for the second read of paired end data. | |
| 167 | |
| 168 Default value: null. | |
| 169 | |
| 170 BARCODE_FILE=File | |
| 171 BF=File | |
| 172 | |
| 173 Barcode file describing sequence list and sample names. Tab-delimited file with 2 | |
| 174 columns, with the sample in col1 and the corresponding barcode in col2. | |
| 175 Simple barcode file format : 2 tab-delimited colums | |
| 176 If multiple barcode map to the same sample, either line can be duplicated e.g. | |
| 177 sample1 ATAT | |
| 178 sample1 GAGG | |
| 179 sample2 CCAA | |
| 180 sample2 TGTG | |
| 181 Or barcodes can be combined using the OR operator '|' i.e. the file above can be | |
| 182 re-written like | |
| 183 sample1 ATAT|GAGG | |
| 184 sample2 CCAA|TGTG | |
| 185 Finally, for the special situation of paired-end data in which barcodes differ at both | |
| 186 ends (ie BPOS=BOTH BRED=false BM=BOTH , see BRED option description), barcodes for read_1 | |
| 187 and read_2 can be distinguished using a ':' separator i.e. | |
| 188 sample1 ATAT:GAGG | |
| 189 sample2 CCAA:TGTG | |
| 190 This above syntax means that sample 1 is encoded with ATAT barcode at read_1 AND GAGG | |
| 191 barcode at read_2. Note that you can still combine barcodes using | e.g. | |
| 192 sample1 ATAT|GAGG:CCAA|TGTG | |
| 193 would mean that sample 1 is mapped by the combination of barcode: ATAT OR GAGG at read_1 | |
| 194 AND CCAA OR TGTG at read_2. | |
| 195 Extended barcode file format : 3 (single-end) or 4 (paired-end) tab-delimited colums | |
| 196 same as the simple barcode file format but the extra columns contains the file name(s) | |
| 197 to use to name output files. A unique extra column is expected for single-end while 2 | |
| 198 extra columns are expected for paired-end. In case, lines are duplicated (multiple | |
| 199 barcodesmapping the same sample), the same file name should be indicated in the third | |
| 200 (and fourth) column(s). | |
| 201 sample1 ATAT spl1_1.txt.gz spl1_2.txt.gz | |
| 202 sample1 GAGG spl1_1.txt.gz spl1_2.txt.gz | |
| 203 sample2 CCAA spl2_1.txt.gz spl2_2.txt.gz | |
| 204 Or | |
| 205 sample1 ATAT|GAGG:CCAA|TGTG spl1_1.txt.gz spl1_2.txt.gz | |
| 206 Ns in barcode sequence are allowed and are used to flag positions that should be ignored | |
| 207 in sample matching | |
| 208 i.e. they will be clipped off the read sequence (like in iCLIP protocol). | |
| 209 | |
| 210 Required. | |
| 211 | |
| 212 BARCODE_READ_POS=BarcodePosition | |
| 213 BPOS=BarcodePosition | |
| 214 | |
| 215 For paired-end data, where to expect the barcode(s) : | |
| 216 READ_1 (beginning of read from FASTQ_FILE_1), | |
| 217 READ_2 (beginning of read from FASTQ_FILE_2), | |
| 218 BOTH (beginning of both reads). | |
| 219 Automatically set to READ_1 in single end mode. | |
| 220 | |
| 221 Default value: BOTH. This option can be set to 'null' to clear the default value. | |
| 222 Possible values: {READ_1, READ_2, BOTH, NONE} | |
| 223 | |
| 224 BCLEN=String | |
| 225 LEN=String | |
| 226 | |
| 227 Length of the barcode sequences, optional. Taken from barcode file when not given. | |
| 228 In situations where BARCODE_READ_POS == BOTH AND REDUNDANT_BARCODES=false, two distinct | |
| 229 length can be provided using the syntax LEN=X:Z where X and Z are 2 integers representing | |
| 230 the barcode length for read_1 and read_2 respectively. | |
| 231 | |
| 232 Default value: null. | |
| 233 | |
| 234 BARCODE_FOR_SAMPLE_MATCHING=BarcodePosition | |
| 235 BM=BarcodePosition | |
| 236 | |
| 237 Indicates which barcode(s) should be used for sample lookup | |
| 238 Automatically set to READ_1 in single end mode. | |
| 239 For paired-end data and when BARCODE_READ_POS == BOTH, which barcode should be used to | |
| 240 resolve sample: | |
| 241 use BM=READ_1 (beginning of read from FASTQ_FILE_1) if only this read should be used | |
| 242 for sample matching: | |
| 243 use BM=READ_2 (beginning of read from FASTQ_FILE_2) if only this read should be used | |
| 244 for sample matching: | |
| 245 use BM=BOTH (beginning of both reads) if both should be used. | |
| 246 | |
| 247 When BM=BOTH, the behaviour is different based on the value of REDUNDANT_BARCODES : | |
| 248 If REDUNDANT_BARCODES=true, the two barcodes are considered to map to the same sample | |
| 249 and 'Je demultiplex' uses the two barcodes according to the STRICT value. | |
| 250 If REDUNDANT_BARCODES=false, the barcode file should map a couple of barcode to each | |
| 251 sample (e.g. sample1 => AGAGTG:TTGATA) and 'Je demultiplex' needs both barcodes to find | |
| 252 the relevant sample. Note that this is the only situation in which all barcode matching | |
| 253 options (MM, MMD, Q) accept different values for both barcodes in the form X:Z where X | |
| 254 and Z are 2 integers. | |
| 255 | |
| 256 Default value: BOTH. This option can be set to 'null' to clear the default value. | |
| 257 Possible values: {READ_1, READ_2, BOTH, NONE} | |
| 258 | |
| 259 | |
| 260 REDUNDANT_BARCODES=Boolean | |
| 261 BRED=Boolean | |
| 262 | |
| 263 This option only applies for paired-end data with BARCODE_READ_POS set to 'BOTH' | |
| 264 Indicates if both read's barcodes encode redundant information or if barcodes are | |
| 265 supposed to be identical at both ends (or to resolve to the same sample when a pool of | |
| 266 barcodes is used per sample). | |
| 267 When REDUNDANT_BARCODES=false, the 2 barcodes potentially encode | |
| 268 different information. For example, only one of the barcodes encodes the sample identity | |
| 269 while | |
| 270 the second barcode might be a random barcode (UMI) to tell apart PCR artefacts from real | |
| 271 duplicates. | |
| 272 Another example is when both barcodes should be used in a combined fashion to resolve the | |
| 273 sample. | |
| 274 In the first example, you should use BPOS=BOTH BRED=false BM=READ_1. | |
| 275 In the second example, you should have BPOS=BOTH BRED=false BM=BOTH. | |
| 276 Note that with BPOS=BOTH BRED=true BM=BOTH, the behavior would be different as | |
| 277 'demultiplex' would then check the STRICT option to perform sample resolution. | |
| 278 Importantly, when BARCODE_READ_POS (BPOS) == BOTH AND REDUNDANT_BARCODES=false, BLEN, | |
| 279 barcode matching options (MM, MMD, Q) and read trimming/clipping options (XT, ZT) accept | |
| 280 different values for both barcodes in the form X:Z where X and Z are 2 integers. | |
| 281 | |
| 282 Default value: true. This option can be set to 'null' to clear the default value. | |
| 283 Possible values: {true, false} | |
| 284 | |
| 285 STRICT=Boolean | |
| 286 S=Boolean | |
| 287 | |
| 288 For paired-end data and when two distinct barcodes/indices are used to encode samples, | |
| 289 this option tells if both barcodes should resolve to the same sample. | |
| 290 When true and if only one of the two reads has a barcode match, the read pair is | |
| 291 'unassigned'. | |
| 292 When false and if only one of the two reads has a barcode match, the read pair is | |
| 293 assigned to the | |
| 294 corresponding sample | |
| 295 When reads resolve to different samples, the read pair is always 'unassigned'. | |
| 296 | |
| 297 Default value: false. This option can be set to 'null' to clear the default value. | |
| 298 Possible values: {true, false} | |
| 299 | |
| 300 MAX_MISMATCHES=String | |
| 301 MM=String | |
| 302 | |
| 303 Maximum mismatches for a barcode to be considered a match. In situations where both | |
| 304 barcodes are used for sample matching i.e. BPOS=BOTH BM=BOTH (or 2 INDEX_FILE given), two | |
| 305 distinct | |
| 306 values can be given here using the syntax MM=X:Z where X and Z are 2 integers to use for | |
| 307 read_1 and read_2 respectively. | |
| 308 MM=null is like MM=0 | |
| 309 | |
| 310 Default value: 1. This option can be set to 'null' to clear the default value. | |
| 311 | |
| 312 MIN_MISMATCH_DELTA=String | |
| 313 MMD=String | |
| 314 | |
| 315 Minimum difference between the number of mismatches against the best and the second best | |
| 316 barcode. When MMD is not respected, the read remains unassigned. | |
| 317 When two distinct barcodes are used for sample matching (dual encoding), two distinct | |
| 318 values can be given using the syntax MMD=X:Z where X and Z are 2 integers to use for | |
| 319 first (e.g. from read_1 or index_1) | |
| 320 MMD=null is like MMD=0 | |
| 321 | |
| 322 Default value: 1. This option can be set to 'null' to clear the default value. | |
| 323 | |
| 324 MIN_BASE_QUALITY=String | |
| 325 Q=String | |
| 326 | |
| 327 Minimum base quality during barcode matching: bases which quality is less than this | |
| 328 cutoff are always considered as a mismatch.When two distinct barcodes are used for sample | |
| 329 matching (dual encoding), two distinct values can be given using the syntax Q=X:Z where X | |
| 330 and Z are 2 integers to use for first (e.g. from read_1 or index_1) and second barcode | |
| 331 (e.g. from read_2 or index_2) respectively. | |
| 332 Q=null is like Q=0. | |
| 333 | |
| 334 Default value: 10. This option can be set to 'null' to clear the default value. | |
| 335 | |
| 336 XTRIMLEN=String | |
| 337 XT=String | |
| 338 | |
| 339 Optional extra number of base to be trimmed right after the barcode (only used if | |
| 340 CLIP_BARCODE=true). | |
| 341 When running paired-end, two distinct values can be given using the syntax XT=X:Z where X | |
| 342 and Z are 2 integers to use for read_1 and read_2 respectively. Note that even when | |
| 343 BPOS=READ_1 or BPOS=READ_2, a X:Y synthax can be given to trim the read w/o barcode as to | |
| 344 end up with reads of the same length (note that this can also be operated using ZT). If a | |
| 345 unique value is given, e.g. XT=1, while running paired-end the following rule applies: | |
| 346 (1) BPOS=READ_1 or BPOS=READ_2, no trim is applied at the read w/o barcode | |
| 347 (2) BPOS=BOTH, the value is used for both reads. | |
| 348 | |
| 349 Note that XT=null is like XT=0. | |
| 350 Default value: 0. This option can be set to 'null' to clear the default value. | |
| 351 | |
| 352 ZTRIMLEN=String | |
| 353 ZT=String | |
| 354 | |
| 355 Optional extra number of bases to be trimmed from the read end i.e. 3' end. | |
| 356 When running paired-end, two distinct values can be given here using the syntax ZT=X:Z | |
| 357 where X and Z are 2 integers to use for read_1 and read_2 respectively. Note that even | |
| 358 when BPOS=READ_1 or BPOS=READ_2, a X:Y synthax can be given to trim the read w/o barcode | |
| 359 as to end up with reads of the same length (note that this can also be operated using | |
| 360 XT). Note that if a single value is passed, the value always applies to both reads in | |
| 361 paired-end mode without further consideration. | |
| 362 ZT=null is like ZT=0. | |
| 363 | |
| 364 Default value: 0. This option can be set to 'null' to clear the default value. | |
| 365 | |
| 366 CLIP_BARCODE=Boolean | |
| 367 C=Boolean | |
| 368 | |
| 369 Clip barcode sequence from read sequence, as well as XTRIMLEN (and ZTRIMLEN) bases if | |
| 370 applicable, before writing to output file. | |
| 371 If false, reads are written without modification to output file. | |
| 372 Apply to both barcodes when BPOS=BOTH. | |
| 373 | |
| 374 Default value: true. This option can be set to 'null' to clear the default value. | |
| 375 Possible values: {true, false} | |
| 376 | |
| 377 ADD_BARCODE_TO_HEADER=Boolean | |
| 378 ADD=Boolean | |
| 379 | |
| 380 Add barcode at the end of the read header. Apply to both barcodes when BPOS=BOTH. | |
| 381 If true, the string ':barcode' is added at the end of the read header with a ':' added | |
| 382 only if current read header does not end with ':'. | |
| 383 If both reads of the pair have a barcode (i.e. BARCODE_READ_POS == BOTH), thenthe second | |
| 384 read also has its own matched barcode written. Else, the read without a barcode receives | |
| 385 the barcode from the barcoded read. | |
| 386 For example: | |
| 387 @D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965 2:N:0: | |
| 388 becomes: | |
| 389 @D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965 2:N:0:BARCODE | |
| 390 | |
| 391 When barcodes containing random positions, i.e. 'N', (for example like in the iCLIP | |
| 392 protocol) or are UMIs, the added sequence is the sequence clipped from the read and NOT | |
| 393 the matched barcode. | |
| 394 | |
| 395 Default value: true. This option can be set to 'null' to clear the default value. | |
| 396 Possible values: {true, false} | |
| 397 | |
| 398 | |
| 399 ENSURE_IDENTICAL_HEADER_NAMES=Boolean | |
| 400 SAME_HEADERS=Boolean | |
| 401 | |
| 402 Makes sure that headers of both reads of a pair are identical, using the following read | |
| 403 header pattern (for both reads of a pair): | |
| 404 @D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965 SAMPLEBARCODE_READ1:SAMPLEBARCODE_READ2(:CLIPPED_SEQ_FROMREAD1:CLIPPED_SEQ_FROMREAD2) | |
| 405 This option only makes sense in | |
| 406 paired end mode and ADD=true. Some (if not all) mappers will indeed complain when the | |
| 407 read headers are not identical. When molecular barcodes are present in reads (either as | |
| 408 additional barcodes or as degenerate barcodes ie with 'N') and the RCHAR is used, you | |
| 409 will end with (problematic) read headers like this: | |
| 410 HISEQ:44:C6KC0ANXX:5:1101:1491:1994:1:N:0:TAGAACAC:TGGAGTAG | |
| 411 HISEQ:44:C6KC0ANXX:5:1101:1491:1994:3:N:0:TAGAACAC:CGTTGTAT | |
| 412 SAME_HEADERS=true will instead generates the following identical header for both reads: | |
| 413 HISEQ:44:C6KC0ANXX:5:1101:1491:1994:TAGAACAC:TGGAGTAG:CGTTGTAT | |
| 414 Note that we also clipped the useless '1:N:0' and '3:N:0' has they will also result in | |
| 415 generating different headers. | |
| 416 Important: this option will force RCHAR=: UNLESS you specify RCHAR=null ; in which | |
| 417 case a space will be preserved ie: | |
| 418 HISEQ:44:C6KC0ANXX:5:1101:1491:1994 TAGAACAC:TGGAGTAG:CGTTGTAT | |
| 419 | |
| 420 Default value: true. This option can be set to 'null' to clear the default value. | |
| 421 Possible values: {true, false} | |
| 422 | |
| 423 | |
| 424 READ_NAME_REPLACE_CHAR=String | |
| 425 RCHAR=String | |
| 426 | |
| 427 Replace spaces in read name/header using provided character. This is particularly handy | |
| 428 when you need to retain ADDed barcode in read name/header during mapping (everything | |
| 429 after space in read name is usually clipped in BAM files). For example, with RCHAR=':': | |
| 430 @D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965 2:N:0: | |
| 431 becomes | |
| 432 @D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965:2:N:0:BARCODE | |
| 433 Default value: null. | |
| 434 | |
| 435 QUALITY_FORMAT=FastqQualityFormat | |
| 436 V=FastqQualityFormat | |
| 437 | |
| 438 A value describing how the quality values are encoded in the fastq. Either 'Solexa' for | |
| 439 pre-pipeline 1.3 style scores (solexa scaling + 66), 'Illumina' for pipeline 1.3 and | |
| 440 above (phred scaling + 64) or 'Standard' for phred scaled scores with a character shift | |
| 441 of 33. If this value is not specified (or 'null' is given), the quality format will be | |
| 442 detected. | |
| 443 | |
| 444 Default value: Standard. This option can be set to 'null' to clear the default value. | |
| 445 Possible values: {Solexa, Illumina, Standard} | |
| 446 | |
| 447 KEEP_UNASSIGNED_READ=Boolean | |
| 448 UN=Boolean | |
| 449 | |
| 450 Should un-assigned reads be saved in files or simply ignored. File names are | |
| 451 automatically created or can be given using UF1 & UF2 options. | |
| 452 | |
| 453 Default value: true. This option can be set to 'null' to clear the default value. | |
| 454 Possible values: {true, false} | |
| 455 | |
| 456 BARCODE_DIAG_FILE=String | |
| 457 DIAG=String | |
| 458 | |
| 459 Name for a barcode match reporting file (not generated by default).Either a name (in | |
| 460 which case the file will be created in the output dir) or full path. This file will | |
| 461 contain a line per read pair with the barcode best matching the read subsequence or | |
| 462 'null' when no match is found according to matching parameters ; and the final selected | |
| 463 sample. This file is useful for debugging or further processing in case both ends are | |
| 464 barcoded. | |
| 465 N.B: this file will have a size of about one of the fastq input files. | |
| 466 | |
| 467 Default value: null. | |
| 468 ]]> | |
|
5
222819c87d90
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents:
3
diff
changeset
|
469 </help> |
|
222819c87d90
planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents:
3
diff
changeset
|
470 <expand macro="citations"/> |
| 0 | 471 </tool> |