Mercurial > repos > jjohnson > fgbio_trim_fastq

comparison macros.xml @ 0:604d9b0ad9a4 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit 77a5370a0978b5332bb3a9f063588a52a468ea08"
author jjohnson
date Thu, 19 Aug 2021 15:13:17 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:604d9b0ad9a4
1 <macros>
2 <token name="@TOOL_VERSION@">1.3.0</token>
3 <token name="@VERSION_SUFFIX@">1</token>
4 <xml name="requirements">
5 <requirements>
6 <requirement type="package" version="@TOOL_VERSION@">fgbio</requirement>
7 <yield/>
8 </requirements>
9 </xml>
10 <xml name="citations">
11 <citations>
12 <citation type="bibtex">@online{fgbio,
13 author = {Tim Fennell, Nils Homer},
14 title = {fgbio},
15 year = 2015,
16 url = {https://github.com/fulcrumgenomics/fgbio},
17 urldate = {2021-03-01}
18 }</citation>
19 </citations>
20 </xml>
21 <token name="@READ_STRUCTURE_PATTERN@">(([1-9][0-9]*[TBMS])*([+]|[1-9][0-9]*)[TBMS])</token>
22 <token name="@READ_STRUCTURES_PATTERN@">@READ_STRUCTURE_PATTERN@(\s@READ_STRUCTURE_PATTERN@)*</token>
23 <xml name="read_structures_validator" token_pattern="@READ_STRUCTURES_PATTERN@">
24 <validator type="regex" message="">^@READ_STRUCTURES_PATTERN@$</validator>
25 </xml>
26 <xml name="read_structures" token_pattern="@READ_STRUCTURES_PATTERN@">
27 <param argument="--read-structures" type="text" value="" optional="true" label="Read structures, one for each of the FASTQ">
28 <expand macro="read_structures_validator" pattern="@READ_STRUCTURE_PATTERN@" />
29 </param>
30 </xml>
31
32 <xml name="fastq_input" token_fastqtype="reads" token_defaultpaired="True" token_defaultnone="False">
33 <conditional name="@FASTQTYPE@">
34 <param name="type" type="select" label="Library type of FASTQ @FASTQTYPE@">
35 <option value="none" selected="@DEFAULTNONE@">NO fastq @FASTQTYPE@</option>
36 <option value="single">Single-end</option>
37 <option value="paired" selected="@DEFAULTPAIRED@">Paired-end</option>
38 <option value="paired_collection">Paired-end Dataset Collection</option>
39 </param>
40 <when value="none"/>
41 <when value="single">
42 <param name="input_single" type="data" format="fastq,fastq.gz" label="Reads in FASTQ format" />
43 <expand macro="read_structures" pattern="@READ_STRUCTURE_PATTERN@" />
44 </when>
45 <when value="paired">
46 <param name="input_read1" type="data" format="fastq,fastq.gz" label="Reads #1 in FASTQ format" />
47 <param name="input_read2" type="data" format="fastq,fastq.gz" label="Reads #2 in FASTQ format" />
48 <expand macro="read_structures" pattern="@READ_STRUCTURES_PATTERN@" />
49 </when>
50 <when value="paired_collection">
51 <param name="input_readpair" type="data_collection" collection_type="paired" format="fastq,fastq.gz" label="Paired Reads in FASTQ format" />
52 <expand macro="read_structures" pattern="@READ_STRUCTURES_PATTERN@" />
53 </when>
54 </conditional>
55 </xml>
56 <xml name="fastq_reads">
57 <expand macro="fastq_input" fastqtype="reads" defaultpaired="True" defaultnone="False"/>
58 </xml>
59 <xml name="fastq_inputs">
60 <expand macro="fastq_input" fastqtype="reads" defaultpaired="True" defaultnone="False"/>
61 <expand macro="fastq_input" fastqtype="indices" defaultpaired="False" defaultnone="True"/>
62 </xml>
63 <token name="@FASTQ_READS@"><![CDATA[
64 #set $fastqs = []
65 #set $read_structs = []
66 #if $reads.type == 'single':
67 $fastqs.append($reads.input_single)
68 #elif $reads.type == 'paired':
69 $fastqs.append($reads.input_read1)
70 $fastqs.append($reads.input_read2)
71 #elif $reads.type == 'paired_collection':
72 $fastqs.append($reads.input_readpair.forward)
73 $fastqs.append($reads.input_readpair.reverse)
74 #end if
75 #if $reads.type !='none' and $reads.read_structures:
76 $read_structs.append(str($reads.read_structures))
77 #end if
78 #set $read_structures = "%s" % (' '.join($read_structs))
79 #if $read_structs:
80 --read-structures $read_structures
81 #end if
82 ]]></token>
83 <token name="@LINK_FASTQ_INPUTS@"><![CDATA[
84 #import re
85 #def identifier_or_name($input1)
86 #if hasattr($input1, 'element_identifier')
87 #return $input1.element_identifier
88 #else
89 #return $input1.name
90 #end if
91 #end def
92 #def clean($name1)
93 #set $name_clean = $re.sub('[^\w\-_]', '_', $re.sub('(?i)[.](fq|fastq)$','', $re.sub('.*/','', $name1.rstrip('.gz'))))
94 #return $name_clean
95 #end def
96 #def ln_name($ds)
97 #set $ext = ''
98 #if $ds.is_of_type('mzml') or $ds.is_of_type('fastq.gz')
99 #set $ext = ".fastq.gz"
100 #else if $ds.is_of_type('fastq')
101 #set $ext = ".fastq"
102 #end if
103 #set $name = "%s%s" % ($clean($identifier_or_name($ds)),$ext)
104 #return $name
105 #end def
106 #set $fastqs = []
107 #set $read_structs = []
108 #if $reads.type == 'single':
109 #set $i_name = $ln_name($reads.input_single)
110 #silent $fastqs.append($i_name)
111 ln -s '$reads.input_single' '$i_name' &&
112 #elif $reads.type == 'paired':
113 #set $f_name = $ln_name($reads.input_read1)
114 #silent $fastqs.append($f_name)
115 ln -s '$reads.input_read1' '$f_name' &&
116 #set $r_name = $ln_name($reads.input_read2)
117 #silent $fastqs.append($r_name)
118 ln -s '$reads.input_read2' '$r_name' &&
119 #elif $reads.type == 'paired_collection':
120 #set $f_name = $ln_name($reads.input_readpair.forward)
121 #silent $fastqs.append($f_name)
122 ln -s '$reads.input_readpair.forward' '$f_name' &&
123 #set $r_name = $ln_name($reads.input_readpair.reverse)
124 #silent $fastqs.append($r_name)
125 ln -s '$reads.input_readpair.reverse' '$r_name' &&
126 #end if
127 #if $reads.type !='none' and $reads.read_structures:
128 $read_structs.append(str($reads.read_structures))
129 #end if
130 #if $indices.type == 'single':
131 #set $i_name = $ln_name($indices.input_single)
132 #silent $fastqs.append($i_name)
133 ln -s '$indices.input_single' '$i_name' &&
134 #elif $indices.type == 'paired':
135 #set $f_name = $ln_name($indices.input_read1)
136 #silent $fastqs.append($f_name)
137 ln -s '$indices.input_read1' '$f_name' &&
138 #set $r_name = $ln_name($indices.input_read2)
139 #silent $fastqs.append($r_name)
140 ln -s '$indices.input_read2' '$r_name' &&
141 #elif $indices.type == 'paired_collection':
142 #set $f_name = $ln_name($indices.input_readpair.forward)
143 #silent $fastqs.append($f_name)
144 ln -s '$indices.input_readpair.forward' '$f_name' &&
145 #set $r_name = $ln_name($indices.input_readpair.reverse)
146 #silent $fastqs.append($r_name)
147 ln -s '$indices.input_readpair.reverse' '$r_name' &&
148 #end if
149 #if $indices.type != 'none' and $indices.read_structures:
150 $read_structs.append(str($indices.read_structures))
151 #end if
152 ]]></token>
153 <token name="@FASTQ_INPUTS@"><![CDATA[
154 --input
155 #for $input in $fastqs
156 '$input'
157 #end for
158 #set $read_structures = "%s" % (' '.join($read_structs))
159 #if $read_structs:
160 --read-structures $read_structures
161 #end if
162 ]]></token>
163 <xml name="inherit_format_1">
164 <actions>
165 <conditional name="library.type">
166 <when value="single">
167 <action type="format">
168 <option type="from_param" name="library.input_1" param_attribute="ext" />
169 </action>
170 </when>
171 <when value="paired">
172 <action type="format">
173 <option type="from_param" name="library.input_1" param_attribute="ext" />
174 </action>
175 </when>
176 <when value="paired_collection">
177 <action type="format">
178 <option type="from_param" name="library.input_1" param_attribute="forward.ext" />
179 </action>
180 </when>
181 </conditional>
182 </actions>
183 </xml>
184
185 <xml name="inherit_format_2">
186 <actions>
187 <conditional name="library.type">
188 <when value="paired">
189 <action type="format">
190 <option type="from_param" name="library.input_2" param_attribute="ext" />
191 </action>
192 </when>
193 <when value="paired_collection">
194 <action type="format">
195 <option type="from_param" name="library.input_1" param_attribute="reverse.ext" />
196 </action>
197 </when>
198 </conditional>
199 </actions>
200 </xml>
201 <xml name="sam_tag_validator">
202
203 <validator type="regex" message="">^[A-Za-z][A-Za-z]$</validator>
204 </xml>
205 <xml name="sam_sort_order">
206 <param argument="--sort-order" type="select" optional="true" label="Sort BAM by">
207 <option value="TemplateCoordinate">TemplateCoordinate</option>
208 <option value="Coordinate">Coordinate</option>
209 <option value="Queryname">Queryname</option>
210 <option value="Random">Random</option>
211 <option value="RandomQuery">RandomQuery</option>
212 </param>
213 </xml>
214
215 <xml name="sort_order_change_format">
216 <change_format>
217 <when input="sort_order" value="Coordinate" format="bam" />
218 <when input="sort_order" value="TemplateCoordinate" format="bam" />
219 <when input="sort_order" value="QueryName" format="unsorted.bam" />
220 <when input="sort_order" value="Random" format="unsorted.bam" />
221 <when input="sort_order" value="RandomQuery" format="unsorted.bam" />
222 </change_format>
223 </xml>
224
225 <token name="@READ_STRUCTURES_HELP@"><![CDATA[
226 **Read Structures**
227
228 Read structures are made up of <number><operator> pairs much like the CIGAR string in BAM files. Four kinds of operators are recognized:
229
230 - T identifies a template read
231 - B identifies a sample barcode read
232 - M identifies a unique molecular index read
233 - S identifies a set of bases that should be skipped or ignored
234
235 The last <number><operator> pair may be specified using a + sign instead of number to denote “all remaining bases”. This is useful if, e.g., fastqs have been trimmed and contain reads of varying length. For example to convert a paired-end run with an index read and where the first 5 bases of R1 are a UMI and the second five bases are monotemplate you might specify:
236
237 ::
238
239 --input r1.fq r2.fq i1.fq --read-structures 5M5S+T +T +B
240
241 Alternative if you know your reads are of fixed length you could specify:
242
243 ::
244
245 --input r1.fq r2.fq i1.fq --read-structures 5M5S65T 75T 8B
246
247
248 ]]></token>
249 <xml name="citations">
250 <citations>
251 <yield />
252 </citations>
253 </xml>
254 </macros>