annotate je-demultiplex-illu.xml @ 5:69c77f9fc064 draft

planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
author gbcs-embl-heidelberg
date Wed, 02 Aug 2017 10:59:09 -0400
parents 01fdc6d10660
children 370d9764f670
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
3
01fdc6d10660 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_illu" name="Je-Demultiplex-Illu" version="@VERSION_STRING@">
0
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
2 <description>demultiplexes fastq files using Illumina Index file</description>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
3 <macros>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
4 <import>macros.xml</import>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
5 </macros>
5
69c77f9fc064 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
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
7 <stdio>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
8 <exit_code range="1:" level="fatal" description="Tool exception" />
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
9 </stdio>
5
69c77f9fc064 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" />
69c77f9fc064 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
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
12 <![CDATA[
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
13 je demultiplex-illu
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
14
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
15 ## Fastq inputs
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
16 @single_or_paired_illu_cmd@
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
17
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
18 @barcode_option_cmd@
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
19
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
20 #if str($INTERNAL_BARCODES_CON.INTERNAL_BARCODES) == 'true':
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
21 BPOS=${INTERNAL_BARCODES_CON.BPOS}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
22 C=${INTERNAL_BARCODES_CON.CLIP_BARCODE}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
23 #if str( $INTERNAL_BARCODES_CON.LEN ) != "":
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
24 BCLEN=$INTERNAL_BARCODES_CON.LEN
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
25 #end if
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
26 #else:
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
27 BPOS=NONE
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
28 C=false
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
29 #end if
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
30
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
31 @common_options_cmd@
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
32
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
33 @demultiplexer_common_output_options_cmd@
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
34 @demultiplexer_common_outputs_cmd@
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
35 ]]>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
36 </command>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
37 <configfiles>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
38 <expand macro="barcode_config_file"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
39 </configfiles>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
40 <inputs>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
41 <!-- single/paired - similar to macro 'single_or_paired_general' -->
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
42 <expand macro="single_or_paired_illu">
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
43 <expand macro="demultiplex_illu_paired_end_options"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
44 </expand>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
45 <expand macro="barcode_option"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
46 <conditional name="INTERNAL_BARCODES_CON">
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
47 <param name="INTERNAL_BARCODES" type="select"
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
48 label="Do your reads contain Unique Molecular Identifiers(UMIs)">
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
49 <option value="true">Yes</option>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
50 <option value="false" selected="true">No</option>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
51 </param>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
52 <when value="true">
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
53 <param name="BPOS" type="select" label="Barcode read position (BPOS)" help="where are the barcodes.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
54 If not using paired-end it does not matter what you specify here.">
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
55 <option value="READ_1" selected="true">READ_1 (beginning of read from the first fastq file)</option>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
56 <option value="READ_2">READ_2 (beginning of read from the second fastq file)</option>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
57 <option value="BOTH">BOTH (beginning of both reads)</option>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
58 </param>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
59 <expand macro="barcode_len_option"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
60 <expand macro="clip_barcode"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
61 </when>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
62 <when value="false"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
63 </conditional>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
64
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
65 <expand macro="demultiplexer_common_options"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
66
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
67 <expand macro="common_options"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
68
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
69 <expand macro="demultiplexer_common_output_options"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
70
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
71 </inputs>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
72 <outputs>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
73 <expand macro="demultiplexer_common_outputs"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
74 </outputs>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
75
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
76 <tests>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
77 <test>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
78 <!-- barcode at both ends, non-redundant -->
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
79 <param name="type" value="paired"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
80 <param name="input_1" value="illu_file_1_sequence.txt" ftype="fastqsanger"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
81 <param name="input_2" value="illu_file_2_sequence.txt" ftype="fastqsanger"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
82 <param name="I1" value="illu_file_1_index.txt" ftype="fastqsanger"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
83 <param name="I2_AVAILABLE" value="true"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
84 <param name="I2" value="illu_file_2_index.txt" ftype="fastqsanger"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
85
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
86 <param name="INTERNAL_BARCODES" value="true"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
87 <param name="barcode_list_type_con" value="file"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
88 <param name="BARCODE_FILE" value="illu_dualindexing.txt" ftype="tabular"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
89 <param name="LEN" value="8:8"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
90 <param name="ZT" value="5:6"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
91 <param name="BPOS" value="BOTH"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
92 <param name="BM" value="BOTH"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
93 <param name="BRED" value="false"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
94 <param name="MM" value="3"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
95 <param name="MMD" value="2"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
96 <param name="Q" value="20"/>
5
69c77f9fc064 planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents: 3
diff changeset
97 <param name="DIAG" value="false"/>
0
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
98 <output name="METRICS_FILE_NAME" file="illu_summary_PE.txt" ftype="tabular" lines_diff="4">
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
99 <discovered_dataset designation="unassigned_1" file="illu_unassigned_1_PE.txt" />
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
100 <discovered_dataset designation="unassigned_2" file="illu_unassigned_2_PE.txt" />
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
101 <discovered_dataset designation="emb681m5_GGACTCCTCTCTCTAT_2" file="emb681m5_GGACTCCTCTCTCTAT_2.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
102 <discovered_dataset designation="emb681m5_GGACTCCTCTCTCTAT_1" file="emb681m5_GGACTCCTCTCTCTAT_1.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
103 <discovered_dataset designation="emb681m4_TCCTGAGCCTCTCTAT_2" file="emb681m4_TCCTGAGCCTCTCTAT_2.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
104 <discovered_dataset designation="emb681m4_TCCTGAGCCTCTCTAT_1" file="emb681m4_TCCTGAGCCTCTCTAT_1.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
105 <discovered_dataset designation="emb681m1_TAAGGCGACTCTCTAT_2" file="emb681m1_TAAGGCGACTCTCTAT_2.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
106 <discovered_dataset designation="emb681m1_TAAGGCGACTCTCTAT_1" file="emb681m1_TAAGGCGACTCTCTAT_1.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
107 <discovered_dataset designation="emb6801m2_AGGCAGAATAGATCGC_2" file="emb6801m2_AGGCAGAATAGATCGC_2.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
108 <discovered_dataset designation="emb6801m2_AGGCAGAATAGATCGC_1" file="emb6801m2_AGGCAGAATAGATCGC_1.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
109 <discovered_dataset designation="emb6801m1_CGTACTAGTAGATCGC_2" file="emb6801m1_CGTACTAGTAGATCGC_2.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
110 <discovered_dataset designation="emb6801m1_CGTACTAGTAGATCGC_1" file="emb6801m1_CGTACTAGTAGATCGC_1.txt"/>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
111 </output>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
112 </test>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
113 </tests>
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
114
5
69c77f9fc064 planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents: 3
diff changeset
115 <help>
0
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
116 <![CDATA[
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
117 **What it does**
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
118
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
119 Je demultiplex-illu: demultiplex fastq files using Illumina Index files,
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
120 with optional handling of Unique Molecular Identifiers for further use in 'markdupes' module
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
121 Input files are fastq files, and can be in gzip compressed format.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
122
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
123 Author: Charles Girardot (charles.girardot@embl.de).
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
124
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
125 Wrapper by: Jelle Scholtalbers (jelle.scholtalbers@embl.de).
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
126
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
127 ------
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
128
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
129 **Know what you are doing**
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
130
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
131 .. class:: warningmark
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
132
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
133 You will want to read the `documentation`__.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
134
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
135 .. __: http://gbcs.embl.de/portal/Je
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
136
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
137 ------
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
138
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
139 **Parameter list**
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
140
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
141 This is an exhaustive list of options::
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
142
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
143 FASTQ_FILE1=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
144 F1=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
145
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
146 Input fastq file (optionally gzipped) for single end data, or first read in paired end
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
147 data.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
148
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
149 Required.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
150
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
151 FASTQ_FILE2=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
152 F2=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
153
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
154 Input fastq file (optionally gzipped) for the second read of paired end data.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
155
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
156 Default value: null.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
157
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
158 INDEX_FILE1=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
159 I1=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
160
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
161 Fastq file for index 1 (barcode) reads, optionally gzipped
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
162
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
163 Required.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
164
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
165 INDEX_FILE2=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
166 I2=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
167
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
168 Fastq file for index 2 (barcode) reads, optionally gzipped.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
169 A INDEX_FILE1 MUST be provided when INDEX_FILE2 is given. This situation corresponds to
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
170 Illumina dual indexing.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
171
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
172 Default value: null.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
173
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
174 BARCODE_FILE=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
175 BF=File
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
176
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
177 Barcode file describing sequence list and sample names. Tab-delimited file with 2
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
178 columns, with the sample in col1 and the corresponding barcode in col2.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
179 Simple barcode file format : 2 tab-delimited colums
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
180 If multiple barcode map to the same sample, either line can be duplicated e.g.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
181 sample1 ATAT
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
182 sample1 GAGG
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
183 sample2 CCAA
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
184 sample2 TGTG
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
185 Or barcodes can be combined using the OR operator '|' i.e. the file above can be
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
186 re-written like
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
187 sample1 ATAT|GAGG
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
188 sample2 CCAA|TGTG
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
189 Finally, for the special situation of paired-end data in which barcodes differ at both
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
190 ends (ie BPOS=BOTH BRED=false BM=BOTH , see BRED option description), barcodes for read_1
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
191 and read_2 can be distinguished using a ':' separator i.e.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
192 sample1 ATAT:GAGG
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
193 sample2 CCAA:TGTG
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
194 This above syntax means that sample 1 is encoded with ATAT barcode at read_1 AND GAGG
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
195 barcode at read_2. Note that you can still combine barcodes using | e.g.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
196 sample1 ATAT|GAGG:CCAA|TGTG
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
197 would mean that sample 1 is mapped by the combination of barcode: ATAT OR GAGG at read_1
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
198 AND CCAA OR TGTG at read_2.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
199 Extended barcode file format : 3 (single-end) or 4 (paired-end) tab-delimited colums
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
200 same as the simple barcode file format but the extra columns contains the file name(s)
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
201 to use to name output files. A unique extra column is expected for single-end while 2
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
202 extra columns are expected for paired-end. In case, lines are duplicated (multiple
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
203 barcodesmapping the same sample), the same file name should be indicated in the third
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
204 (and fourth) column(s).
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
205 sample1 ATAT spl1_1.txt.gz spl1_2.txt.gz
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
206 sample1 GAGG spl1_1.txt.gz spl1_2.txt.gz
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
207 sample2 CCAA spl2_1.txt.gz spl2_2.txt.gz
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
208 Or
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
209 sample1 ATAT|GAGG:CCAA|TGTG spl1_1.txt.gz spl1_2.txt.gz
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
210 Ns in barcode sequence are allowed and are used to flag positions that should be ignored
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
211 in sample matching
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
212 i.e. they will be clipped off the read sequence (like in iCLIP protocol).
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
213
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
214 Required.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
215
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
216 BARCODE_READ_POS=BarcodePosition
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
217 BPOS=BarcodePosition
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
218
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
219 Indicates the location of additional barcodes present in the read(s). Setting this option
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
220 implies setting the LEN option.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
221 Importantly, these additional barcodes must not encode sample identity information but
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
222 used for e.g. molecular barcoding (UMIs) or for any purpose other than sample identity encoding.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
223
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
224 Default value: BOTH. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
225 Possible values: {READ_1, READ_2, BOTH, NONE}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
226
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
227 BCLEN=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
228 LEN=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
229
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
230 Length of the barcode sequences, optional. Taken from barcode file when not given.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
231 In situations where BARCODE_READ_POS == BOTH AND REDUNDANT_BARCODES=false, two distinct
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
232 length can be provided using the syntax LEN=X:Z where X and Z are 2 integers representing
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
233 the barcode length for read_1 and read_2 respectively.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
234
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
235 Default value: null
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
236
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
237 REDUNDANT_BARCODES=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
238 BRED=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
239
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
240 This option only applies for paired-end data with *both* INDEX_FILE1 and INDEX_FILE2
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
241 provided.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
242 Indicates if both index barcodes encode redundant information i.e. if both barcodes are
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
243 supposed to be identical (or resolve to the same sample when a pool of barcodes is used
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
244 per sample).
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
245 When BRED=true, the STRICT option guides the sample lookup behavior When BRED=false,
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
246 barcodes are combined prior to sample lookup.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
247
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
248 Default value: true. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
249 Possible values: {true, false}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
250
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
251 STRICT=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
252 S=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
253
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
254 For paired-end data and when two distinct barcodes/indices are used to encode samples,
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
255 this option tells if both barcodes should resolve to the same sample.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
256 When true and if only one of the two reads has a barcode match, the read pair is
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
257 'unassigned'.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
258 When false and if only one of the two reads has a barcode match, the read pair is
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
259 assigned to the
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
260 corresponding sample
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
261 When reads resolve to different samples, the read pair is always 'unassigned'.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
262
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
263 Default value: false. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
264 Possible values: {true, false}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
265
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
266 MAX_MISMATCHES=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
267 MM=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
268
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
269 Maximum mismatches for a barcode to be considered a match. In situations where both
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
270 barcodes are used for sample matching i.e. BPOS=BOTH BM=BOTH (or 2 INDEX_FILE given), two
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
271 distinct
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
272 values can be given here using the syntax MM=X:Z where X and Z are 2 integers to use for
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
273 read_1 and read_2 respectively.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
274 MM=null is like MM=0
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
275
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
276 Default value: 1. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
277
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
278 MIN_MISMATCH_DELTA=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
279 MMD=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
280
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
281 Minimum difference between the number of mismatches against the best and the second best
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
282 barcode. When MMD is not respected, the read remains unassigned.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
283 When two distinct barcodes are used for sample matching (dual encoding), two distinct
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
284 values can be given using the syntax MMD=X:Z where X and Z are 2 integers to use for
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
285 first (e.g. from read_1 or index_1)
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
286 MMD=null is like MMD=0
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
287
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
288 Default value: 1. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
289
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
290 MIN_BASE_QUALITY=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
291 Q=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
292
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
293 Minimum base quality during barcode matching: bases which quality is less than this
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
294 cutoff are always considered as a mismatch.When two distinct barcodes are used for sample
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
295 matching (dual encoding), two distinct values can be given using the syntax Q=X:Z where X
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
296 and Z are 2 integers to use for first (e.g. from read_1 or index_1) and second barcode
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
297 (e.g. from read_2 or index_2) respectively.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
298 Q=null is like Q=0.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
299
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
300 Default value: 10. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
301
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
302 XTRIMLEN=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
303 XT=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
304
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
305 Optional extra number of base to be trimmed right after the barcode (only used if
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
306 CLIP_BARCODE=true).
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
307 When running paired-end, two distinct values can be given using the syntax XT=X:Z where X
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
308 and Z are 2 integers to use for read_1 and read_2 respectively. Note that even when
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
309 BPOS=READ_1 or BPOS=READ_2, a X:Y synthax can be given to trim the read w/o barcode as to
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
310 end up with reads of the same length (note that this can also be operated using ZT). If a
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
311 unique value is given, e.g. XT=1, while running paired-end the following rule applies:
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
312 (1) BPOS=READ_1 or BPOS=READ_2, no trim is applied at the read w/o barcode
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
313 (2) BPOS=BOTH, the value is used for both reads.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
314
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
315 Note that XT=null is like XT=0.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
316 Default value: 0. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
317
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
318 ZTRIMLEN=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
319 ZT=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
320
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
321 Optional extra number of bases to be trimmed from the read end i.e. 3' end.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
322 When running paired-end, two distinct values can be given here using the syntax ZT=X:Z
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
323 where X and Z are 2 integers to use for read_1 and read_2 respectively. Note that even
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
324 when BPOS=READ_1 or BPOS=READ_2, a X:Y synthax can be given to trim the read w/o barcode
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
325 as to end up with reads of the same length (note that this can also be operated using
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
326 XT). Note that if a single value is passed, the value always applies to both reads in
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
327 paired-end mode without further consideration.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
328 ZT=null is like ZT=0.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
329
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
330 Default value: 0. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
331
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
332 CLIP_BARCODE=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
333 C=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
334
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
335 Clip barcode sequence from read sequence, as well as XTRIMLEN (and ZTRIMLEN) bases if
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
336 applicable, before writing to output file.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
337 If false, reads are written without modification to output file.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
338 Apply to both barcodes when BPOS=BOTH.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
339
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
340 Default value: true. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
341 Possible values: {true, false}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
342
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
343 ADD_BARCODE_TO_HEADER=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
344 ADD=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
345
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
346 Add matched barcode at the end of the read header. Applies to both index when INDEX_FILE2
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
347 is also provided.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
348 First the sample encoding barcodes from I1 (and I2 when relevant) are added to the read
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
349 headers like
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
350 @D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965 2:N:0:I1_BARCODE:I2_BARCODE
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
351 Then, if BPOS!=NONE, the additional barcodes (UMIs) clipped from the read(s) are added
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
352 to their own header, like
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
353 @D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965 2:N:0:I1_BARCODE:I2_BARCODE:CLIPPED_SEQ_FROMREAD
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
354
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
355 Default value: true. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
356 Possible values: {true, false}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
357
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
358 ENSURE_IDENTICAL_HEADER_NAMES=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
359 SAME_HEADERS=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
360
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
361 Makes sure that headers of both reads of a pair are identical, using the following read
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
362 header pattern (for both reads of a pair):
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
363 @D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965 I1_BARCODE:I2_BARCODE(:CLIPPED_SEQ_FROMREAD1:CLIPPED_SEQ_FROMREAD2)
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
364 This option only makes sense in paired end mode and ADD=true. Some (if not all) mappers
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
365 will indeed complain when the read headers are not identical. When molecular barcodes are
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
366 present in reads and the RCHAR is used, you will end with (problematic) read headers like
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
367 this:
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
368 HISEQ:44:C6KC0ANXX:5:1101:1491:1994:1:N:0:TAGAACAC:TGGAGTAG
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
369 HISEQ:44:C6KC0ANXX:5:1101:1491:1994:3:N:0:TAGAACAC:CGTTGTAT
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
370 SAME_HEADERS=true will instead genetates the following identical header for both reads:
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
371 HISEQ:44:C6KC0ANXX:5:1101:1491:1994:TAGAACAC:TGGAGTAG:CGTTGTAT
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
372 Note that we also clipped the useless '1:N:0' and '3:N:0' has they will also result in
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
373 generating different headers
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
374 Important: this option will force RCHAR=: UNLESS you specify RCHAR=null ; in which
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
375 case a space will be preserved ie:
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
376 HISEQ:44:C6KC0ANXX:5:1101:1491:1994 TAGAACAC:TGGAGTAG:CGTTGTAT
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
377
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
378 Default value: true. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
379 Possible values: {true, false}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
380
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
381 READ_NAME_REPLACE_CHAR=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
382 RCHAR=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
383
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
384 Replace spaces in read name/header using provided character. This is particularly handy
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
385 when you need to retain ADDed barcode in read name/header during mapping (everything
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
386 after space in read name is usually clipped in BAM files). For example, with RCHAR=':':
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
387 '@D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965 2:N:0:'
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
388 becomes
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
389 '@D3FCO8P1:178:C1WLBACXX:7:1101:1836:1965:2:N:0:BARCODE'
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
390 Default value: null.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
391
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
392 QUALITY_FORMAT=FastqQualityFormat
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
393 V=FastqQualityFormat
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
394
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
395 A value describing how the quality values are encoded in the fastq. Either 'Solexa' for
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
396 pre-pipeline 1.3 style scores (solexa scaling + 66), 'Illumina' for pipeline 1.3 and
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
397 above (phred scaling + 64) or 'Standard' for phred scaled scores with a character shift
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
398 of 33. If this value is not specified (or 'null' is given), the quality format will be
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
399 detected.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
400
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
401 Default value: Standard. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
402 Possible values: {Solexa, Illumina, Standard}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
403
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
404 KEEP_UNASSIGNED_READ=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
405 UN=Boolean
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
406
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
407 Should un-assigned reads be saved in files or simply ignored. File names are
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
408 automatically created or can be given using UF1 & UF2 options.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
409
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
410 Default value: true. This option can be set to 'null' to clear the default value.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
411 Possible values: {true, false}
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
412
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
413 BARCODE_DIAG_FILE=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
414 DIAG=String
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
415
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
416 Name for a barcode match reporting file (not generated by default).Either a name (in
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
417 which case the file will be created in the output dir) or full path. This file will
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
418 contain a line per read pair with the barcode best matching the read subsequence or
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
419 'null' when no match is found according to matching parameters ; and the final selected
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
420 sample. This file is useful for debugging or further processing in case both ends are
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
421 barcoded.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
422 N.B: this file will have a size of about one of the fastq input files.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
423
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
424 Default value: null.
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
425 ]]>
5
69c77f9fc064 planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents: 3
diff changeset
426 </help>
69c77f9fc064 planemo upload for repository https://git.embl.de/grp-gbcs/Je/tree/master/src/galaxy commit 0eefd837333dae6fbecaf4f55b053268d844eff6
gbcs-embl-heidelberg
parents: 3
diff changeset
427 <expand macro="citations"/>
0
111ba1180318 Initial upload
gbcs-embl-heidelberg
parents:
diff changeset
428 </tool>