annotate umi-tools_extract.xml @ 8:3cfd8e1073d7 draft

planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
author iuc
date Mon, 16 Jul 2018 17:35:16 -0400
parents f77bc14eba31
children 828dba98cdb4
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
1 <tool id="umi_tools_extract" name="UMI-tools extract" version="@VERSION@.2">
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
2 <description>Extract UMI from fastq files</description>
1
79436b3019e9 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents: 0
diff changeset
3 <macros>
79436b3019e9 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents: 0
diff changeset
4 <import>macros.xml</import>
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
5 <macro name="out_conditional">
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
6 <actions>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
7 <conditional name="input_type.type">
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
8 <when value="paired_collection" >
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
9 <action type="format">
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
10 <option type="from_param" name="input_type.input_readpair" param_attribute="forward.ext" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
11 </action>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
12 </when>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
13 <when value="paired" >
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
14 <action type="format">
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
15 <option type="from_param" name="input_type.input_read1" param_attribute="ext" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
16 </action>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
17 </when>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
18 </conditional>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
19 </actions>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
20 </macro>
1
79436b3019e9 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents: 0
diff changeset
21 </macros>
79436b3019e9 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents: 0
diff changeset
22 <expand macro="requirements" />
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
23 <command detect_errors="exit_code"><![CDATA[
4
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
24 @COMMAND_LINK@
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
25
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
26 umi_tools extract
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
27 --extract-method='$extract_method.value'
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
28 --bc-pattern='$bc_pattern'
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
29
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
30 #if $input_type.type == 'single':
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
31 #if $gz:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
32 --stdin=input_single.gz
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
33 --stdout out.gz
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
34 #else
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
35 --stdin=input_single.txt
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
36 --stdout '$out'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
37 #end if
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
38 #else:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
39 #if $gz:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
40 --stdin=input_read1.gz
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
41 --read2-in=input_read2.gz
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
42 --stdout out1.gz
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
43 --read2-out=out2.gz
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
44 #else:
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
45 --stdin=input_read1.txt
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
46 --read2-in=input_read2.txt
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
47 --stdout '$out1'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
48 --read2-out='$out2'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
49 #end if
4
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
50 #if $input_type.barcode.barcode_select == "both_reads":
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
51 --split-barcode
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
52 --bc-pattern2='$input_type.barcode.bc_pattern2'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
53 #end if
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
54 #end if
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
55
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
56 #if $barcodes.use_barcodes.value == 'yes':
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
57 --filter-cell-barcode
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
58 --whitelist='$barcodes.filter_barcode_file'
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
59 '$barcodes.filter_correct.value'
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
60 #end if
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
61
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
62 #if not $prime3:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
63 --3prime
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
64 #end if
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
65 #if $quality.quality_selector =='true':
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
66 --quality-filter-threshold '$quality.quality_filter_threshold'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
67 --quality-encoding '$quality.quality_encoding'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
68 #end if
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
69 #if $print_log == "1":
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
70 --log='$out_log'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
71 #else
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
72 --supress-stats
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
73 #end if
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
74 #if $gz:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
75 #if $input_type.type == 'single':
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
76 && mv out.gz '$out'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
77 #else
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
78 && mv out1.gz '$out1'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
79 && mv out2.gz '$out2'
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
80 #end if
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
81 #end if
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
82 ]]></command>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
83 <inputs>
4
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
84 <expand macro="input_types" />
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
85
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
86 <conditional name="barcodes" >
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
87 <param name="use_barcodes" argument="--filter-cell-barcode" type="select" label="Use Known Barcodes?" >
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
88 <option value="yes">Yes</option>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
89 <option value="no" selected="true" >No</option>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
90 </param>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
91 <when value="no" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
92 <when value="yes" >
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
93 <param name="filter_barcode_file" type="data" format="tsv" label="Barcode File" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
94 <param name="filter_correct" argument="--error-correct-cell" type="boolean" truevalue="--error-correct-cell" falsevalue="" checked="false" label="Apply correction to cell barcodes?" help="This only applies if your barcode file has two columns output from the umi_tools whitelist command." />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
95 </when>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
96 </conditional>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
97
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
98 <param name="extract_method" type="select" label="Method to extract barcodes" >
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
99 <option value="regex">Regular Expressions</option>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
100 <option value="string" selected="true">String</option>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
101 </param>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
102
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
103 <param name="bc_pattern" argument="--bc-pattern" type="text" label="Barcode pattern for first read"
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
104 help="Use this option to specify the format of the UMI/barcode. Use Ns to
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
105 represent the random positions and Xs to indicate the bc positions.
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
106 Bases with Ns will be extracted and added to the read name. Remaining
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
107 bases, marked with an X will be reattached to the read.">
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
108 <sanitizer invalid_char="">
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
109 <valid initial="string.letters,string.digits">
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
110 <add value="!="/>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
111 <add value="-"/>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
112 <add value="_"/>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
113 <add value="."/>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
114 <add value="?"/>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
115 <add value="&lt;"/><!-- left triangle bracket -->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
116 <add value="&gt;"/><!-- right triangle bracket -->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
117 <add value="&#91;"/> <!-- left square bracket -->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
118 <add value="&#93;"/> <!-- right square bracket -->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
119 <add value="&#94;"/> <!-- caret -->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
120 <add value="&#123;"/> <!-- left curly -->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
121 <add value="&#125;"/> <!-- right curly -->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
122 <add value="&#40;"/> <!-- left parenthesis -->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
123 <add value="&#41;"/> <!-- right parenthesis -->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
124 </valid>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
125 </sanitizer>
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
126 </param>
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
127
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
128 <param name="prime3" argument="--3prime" type="boolean" label="Is the barcode at the 5' end?"
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
129 truevalue="1" falsevalue="0" checked="true"
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
130 help="By default the barcode is assumed to be on the 5' end of the read, but
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
131 use this option to sepecify that it is on the 3' end instead." />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
132 <param name="print_log" argument="-L" type="boolean" label="Output log?"
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
133 truevalue="1" falsevalue="0" checked="true"
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
134 help="Choose if you want to generate a text file containing logging information." />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
135 <conditional name="quality">
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
136 <param name="quality_selector" type="select" label="Enable quality filter?" >
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
137 <option value="false">No</option>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
138 <option value="true">Yes</option>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
139 </param>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
140 <when value="false">
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
141 </when>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
142 <when value="true">
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
143 <param name="quality_filter_threshold" label="Phred score threshold"
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
144 type="integer" value="20" argument="--quality-filter-threshold"
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
145 help="Remove reads where any UMI base quality score falls below this threshold." />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
146 <param name="quality_encoding" argument="--quality-encoding" type="select" label="Library type"
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
147 help="Quality score encoding. Choose from phred33 [33-77], phred64 [64-106] or solexa [59-106].">
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
148 <option value="phred33">phred33 [33-77]</option>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
149 <option value="phred64">phred64 [64-106]</option>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
150 <option value="solexa">solexa [59-106]</option>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
151 </param>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
152 </when>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
153 </conditional>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
154 </inputs>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
155 <outputs>
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
156 <data name="out" format_source="input_single" label="Reads: ${tool.name} on ${on_string}" >
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
157 <filter>input_type['type'] == "single"</filter>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
158 </data>
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
159 <data name="out1" format_source="input_read1" label="Reads1: ${tool.name} on ${on_string}" >
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
160 <filter>input_type['type'] != "single"</filter>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
161 <expand macro="out_conditional" />
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
162 </data>
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
163 <data name="out2" format_source="input_read2" label="Reads2: ${tool.name} on ${on_string}" >
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
164 <filter>input_type['type'] != "single"</filter>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
165 <expand macro="out_conditional" />
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
166 </data>
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
167
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
168 <data name="out_log" format="txt">
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
169 <filter>print_log == True</filter>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
170 </data>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
171 </outputs>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
172 <tests>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
173 <test>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
174 <param name="type" value="single" />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
175 <param name="input_single" value="t_R1.fastq" ftype="fastq" />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
176 <param name="bc_pattern" value="XXXNNN" />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
177 <param name="prime3" value="0" />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
178 <param name="quality_selector" value="true" />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
179 <param name="quality_filter_threshold" value="10" />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
180 <param name="quality_encoding" value="phred33" />
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
181 <output name="out" file="out_SE.fastq" ftype="fastq" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
182 <output name="out_log" >
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
183 <assert_contents>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
184 <has_text text="Input Reads: 100" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
185 <has_text text="umi quality: 28" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
186 <has_text text="Reads output: 72" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
187 </assert_contents>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
188 </output>
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
189 </test>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
190 <test>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
191 <param name="type" value="paired" />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
192 <param name="input_read1" value="t_R1.fastq.gz" ftype="fastq.gz" />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
193 <param name="input_read2" value="t_R2.fastq.gz" ftype="fastq.gz" />
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
194 <param name="bc_pattern" value="NNNXXX" />
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
195 <output name="out1" file="out_R1.fastq.gz" decompress="true" lines_diff="2" ftype="fastq.gz" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
196 <output name="out2" file="out_R2.fastq.gz" decompress="true" lines_diff="2" ftype="fastq.gz" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
197 <output name="out_log" >
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
198 <assert_contents>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
199 <has_text text="Input Reads: 100" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
200 <has_text text="Reads output: 100" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
201 </assert_contents>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
202 </output>
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
203 </test>
4
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
204 <test>
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
205 <param name="type" value="paired_collection" /> <!-- same as before, but uncompressed -->
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
206 <param name="paired_type" value="no" />
4
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
207 <param name="input_readpair" >
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
208 <collection type="paired" >
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
209 <element name="forward" ftype="fastq" value="t_R1.fastq" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
210 <element name="reverse" ftype="fastq" value="t_R2.fastq" />
4
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
211 </collection>
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
212 </param>
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
213 <param name="bc_pattern" value="NNNXXX" />
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
214 <output name="out1" file="out_R1.fastq" ftype="fastq" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
215 <output name="out2" file="out_R2.fastq" ftype="fastq" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
216 <output name="out_log" >
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
217 <assert_contents>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
218 <has_text text="Input Reads: 100" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
219 <has_text text="Reads output: 100" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
220 </assert_contents>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
221 </output>
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
222 </test>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
223 <test>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
224 <param name="type" value="paired" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
225 <param name="input_read1" value="scrb_seq_fastq.1.gz" ftype="fastq.gz" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
226 <param name="input_read2" value="scrb_seq_fastq.2.gz" ftype="fastq.gz" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
227 <param name="extract_method" value="string" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
228 <param name="bc_pattern" value="CCCCCCNNNNNNNNNN" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
229 <param name="use_barcodes" value="yes" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
230 <param name="filter_barcode_file" value="scrb_seq_barcodes" />
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
231 <output name="out2" file="scrb_extract.fastq.gz" decompress="true" ftype="fastq.gz" />
5
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
232 </test>
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
233 <test><!-- same as above but with regex barcode-->
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
234 <param name="type" value="paired" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
235 <param name="input_read1" value="scrb_seq_fastq.1.gz" ftype="fastq.gz" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
236 <param name="input_read2" value="scrb_seq_fastq.2.gz" ftype="fastq.gz" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
237 <param name="extract_method" value="regex" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
238 <param name="bc_pattern" value="^(?P&lt;cell_1&gt;.{6})(?P&lt;umi_1&gt;.{10})" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
239 <param name="use_barcodes" value="yes" />
f77bc14eba31 planemo upload commit 57e3e460a740aa7aad217c8365527c49e88c9a30
iuc
parents: 4
diff changeset
240 <param name="filter_barcode_file" value="scrb_seq_barcodes" />
8
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
241 <output name="out2" file="scrb_extract.fastq.gz" decompress="true" ftype="fastq.gz" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
242 </test>
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
243 <test><!-- CelSeq2 example -->
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
244 <param name="type" value="paired" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
245 <param name="input_read1" value="read_R1.200.gz" ftype="fastq.gz" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
246 <param name="input_read2" value="read_R2.200.gz" ftype="fastq.gz" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
247 <param name="extract_method" value="string" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
248 <param name="bc_pattern" value="NNNNNNCCCCCC" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
249 <output name="out1" file="read_R1.200_extracted.fastq.gz" ftype="fastq.gz" decompress="true" lines_diff="1" />
3cfd8e1073d7 planemo upload commit f6178c9e071a2158a35b82a3607f6dc8a767675c
iuc
parents: 5
diff changeset
250 <output name="out2" file="read_R2.200_extracted.fastq.gz" ftype="fastq.gz" decompress="true" lines_diff="1" />
4
e73a22ff585c planemo upload commit 76cbd559320d2a639e35ed10cb2d9522a5a77ae0
iuc
parents: 1
diff changeset
251 </test>
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
252 </tests>
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
253 <help><![CDATA[
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
254
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
255
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
256 UMI-tools extract.py - Extract UMI from fastq
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
257 =============================================
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
258
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
259 Purpose
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
260 -------
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
261
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
262 Extract UMI barcode from a read and add it to the read name, leaving
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
263 any sample barcode in place. Can deal with paired end reads and UMIs
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
264 split across the paired ends
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
265
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
266 Options
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
267 -------
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
268
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
269 --split-barcode
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
270 By default the UMI is assumed to be on the first read. Use this
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
271 option if the UMI is contained on both reads and specify the
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
272 pattern of the barcode/UMI on the second read using the option
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
273 ``--bc-pattern2``
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
274
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
275 --bc-pattern
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
276 Use this option to specify the format of the UMI/barcode. Use Ns to
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
277 represent the random positions and Xs to indicate the bc positions.
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
278 Bases with Ns will be extracted and added to the read name. Remaining
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
279 bases, marked with an X will be reattached to the read.
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
280
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
281 E.g. If the pattern is NNXXNN,
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
282 Then the read:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
283
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
284 @HISEQ:87:00000000 read1
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
285 AAGGTTGCTGATTGGATGGGCTAG
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
286 DA1AEBFGGCG01DFH00B1FF0B
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
287 +
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
288
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
289 will become:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
290 @HISEQ:87:00000000_AATT read1
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
291 GGGCTGATTGGATGGGCTAG
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
292 1AFGGCG01DFH00B1FF0B
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
293 +
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
294
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
295 --bc-pattern2
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
296 Use this option to specify the format of the UMI/barcode for
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
297 the second read pair if required. If --bc-pattern2 is not
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
298 supplied, this defaults to the same pattern as --bc-pattern
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
299
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
300 --3prime
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
301 By default the barcode is assumed to be on the 5' end of the read, but
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
302 use this option to sepecify that it is on the 3' end instead
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
303
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
304 -L
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
305 Specify a log file to retain logging information and final statistics
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
306
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
307 --split-barcode
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
308 barcode is split across read pair
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
309
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
310 --quality-filter-threshold=QUALITY_FILTER_THRESHOLD
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
311 Remove reads where any UMI base quality score falls
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
312 below this threshold
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
313 --quality-encoding=QUALITY_ENCODING
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
314 Quality score encoding. Choose from phred33[33-77]
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
315 phred64 [64-106] or solexa [59-106]
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
316
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
317 Usage:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
318 ------
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
319
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
320 For single ended reads:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
321 umi_tools extract --bc-pattern=[PATTERN] -L extract.log [OPTIONS]
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
322
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
323 reads from stdin and outputs to stdout.
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
324
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
325 For paired end reads:
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
326 umi_tools extract --bc-pattern=[PATTERN] --read2-in=[FASTQIN] --read2-out=[FASTQOUT] -L extract.log [OPTIONS]
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
327
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
328 reads end one from stdin and end two from FASTQIN and outputs end one to stdin
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
329 and end two to FASTQOUT.
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
330
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
331 ]]></help>
1
79436b3019e9 planemo upload commit c8e46ecad0b1473097517e582ed6c43eb0635b36
iuc
parents: 0
diff changeset
332 <expand macro="citations" />
0
418b961e0576 planemo upload commit 453bb3b44d9f27908cbe2677378da88b9f77b5cf
iuc
parents:
diff changeset
333 </tool>