Mercurial > repos > devteam > picard_122_up

comparison picard_FastqToSam.xml @ 0:b76a4f17bbbb draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Thu, 23 Oct 2014 11:31:30 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:b76a4f17bbbb
1 <tool name="FastqToSam" id="picard_FastqToSam" version="1.122.0">
2 <description>convert Fastq data into unaligned BAM</description>
3 <requirements>
4 <requirement type="package" version="1.122.0">picard</requirement>
5 </requirements>
6
7 <macros>
8 <import>picard_macros.xml</import>
9 </macros>
10
11 <command>
12 @java_options@
13
14 java -jar \$JAVA_JAR_PATH/FastqToSam.jar
15
16 #if str( $input_type.input_type_selector ) == "se":
17 FASTQ="${input_type.fastq}"
18 #elif str( $input_type.input_type_selector ) == "pe":
19 FASTQ="${input_type.fastq}"
20 FASTQ2="${input_type.fastq2}"
21 #else
22 FASTQ="${input_type.fastq.forward}"
23 FASTQ2="${input_type.fastq.reverse}"
24 #end if
25
26 QUALITY_FORMAT="${quality_format}"
27 OUTPUT="${outFile}"
28 READ_GROUP_NAME="${read_group_name}"
29 SAMPLE_NAME="${sample_name}"
30
31 #if str( $library_name ):
32 LIBRARY_NAME="${library_name}"
33 #end if
34
35 #if str( $platform_unit ):
36 PLATFORM_UNIT="${platform_unit}"
37 #end if
38
39 #if str( $platform ):
40 PLATFORM="${platform}"
41 #end if
42
43 #if str( $sequencing_center ):
44 SEQUENCING_CENTER="${sequencing_center}"
45 #end if
46
47 #if str( $predicted_insert_size ):
48 PREDICTED_INSERT_SIZE="${predicted_insert_size}"
49 #end if
50
51 #if str( $comment ):
52 COMMENT="${comment}"
53 #end if
54
55 #if str( $description ):
56 DESCRIPTION="${description}"
57 #end if
58
59 #if str( $run_date ):
60 RUN_DATE="${run_date}"
61 #end if
62
63 MIN_Q="${min_q}"
64 MAX_Q="${max_q}"
65 STRIP_UNPAIRED_MATE_NUMBER="${strip_unpairied_mate_number}"
66 ALLOW_AND_IGNORE_EMPTY_LINES="${allow_and_ignore_empty_lines}"
67
68 SORT_ORDER=coordinate
69 VALIDATION_STRINGENCY="${validation_stringency}"
70 QUIET=true
71 VERBOSITY=ERROR
72
73 </command>
74 <inputs>
75 <conditional name="input_type">
76 <param name="input_type_selector" type="select" label="What is your input data" help="Select between single end, paired end, and collections. See help below for full explanation of dataset types">
77 <option value="se">Single end (single dataset)</option>
78 <option value="pe">Paired end (two datasets)</option>
79 <option value="pc">Paired collection</option>
80 </param>
81 <when value="se">
82 <param name="fastq" type="data" format="fastq" label="Input fastq file for single end data" help="FASTQ"/>
83 </when>
84 <when value="pe">
85 <param name="fastq" type="data" format="fastq" label="Input fastq file for the first read in paired end data" help="FASTQ"/>
86 <param name="fastq2" type="data" format="fastq" label="Input fastq file for the second read of paired end data" help="FASTQ2"/>
87 </when>
88 <when value="pc">
89 <param name="fastq" type="data_collection" collection_type="paired" label="FASTQ paired dataset collection" help="FASTQ and FASTQ2; A collection of two datasets with forward and reverse reads. See help below on explanation of dataset collections"/>
90 </when>
91 </conditional>
92
93 <param name="quality_format" type="select" label="Select quality encoding scheme" help="QUALITY_FORMAT">
94 <option value="Standard" selected="True">Sanger (+33)</option>
95 <option value="Illumina">Illumina (+64)</option>
96 <option value="Solexa">Solexa (+66)</option>
97 </param>
98
99 <param name="read_group_name" type="text" size="20" value="A" label="Read group name" help="READ_GROUP_NAME"/>
100 <param name="sample_name" type="text" size="20" value="sample-a" label="Sample name" help="SAMPLE_NAME"/>
101 <param name="library_name" type="text" size="20" optional="True" label="The library name" help="LIBRARY_NAME; Optional"/>
102 <param name="platform_unit" type="text" size="20" optional="True" label="The platform unit (often run_barcode.lane)" help="PLATFORM_UNIT; Optional"/>
103 <param name="platform" type="text" size="20" optional="True" label="The platform type (e.g. illumina, 454)" help="PLATFORM; Optional"/>
104 <param name="sequencing_center" type="text" size="20" optional="True" label="The sequencing center from which the data originated" help="SEQUENCING_CENTER; Optional"/>
105
106 <param name="predicted_insert_size" type="integer" min="0" max="100000" optional="True" label="Predicted median insert size, to insert into the read group header" help="PREDICTED_INSERT_SIZE; Optional"/>
107 <param name="comment" type="text" size="20" optional="True" label="Comment to include in the output dataset's header" help="COMMENT; Optional"/>
108 <param name="description" type="text" size="20" optional="True" label="Optional description information" help="DESCRIPTION; Optional"/>
109 <param name="run_date" optional="True" type="text" label="Run date" help="RGDT; Optional; Format=YYYY-MM-DD (eg 1997-07-16)"/>
110 <param name="min_q" type="integer" value="0" min="0" max="100" label="Minimum quality allowed in the input fastq" help="MIN_Q; An exception will be thrown if a quality is less than this value; default=0"/>
111 <param name="max_q" type="integer" value="93" min="0" max="100" label="Minimum quality allowed in the input fastq" help="MAX_Q; An exception will be thrown if a quality is greater than this value; default=93"/>
112 <param name="strip_unpairied_mate_number" type="boolean" truevalue="true" falsevalue="false" label="If true and this is an unpaired fastq any occurance of '/1' will be removed from the end of a read name" help="STRIP_UNPAIRED_MATE_NUMBER; default=false"/>
113 <param name="allow_and_ignore_empty_lines" type="boolean" truevalue="true" falsevalue="false" label="Allow (and ignore) empty lines" help="ALLOW_AND_IGNORE_EMPTY_LINES; default=false"/>
114
115 <expand macro="VS" />
116
117 </inputs>
118
119 <outputs>
120 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: reads as unaligned BAM"/>
121 </outputs>
122
123 <tests>
124 <test>
125 <param name="input_type_selector" value="pe" />
126 <param name="quality_format" value="Standard" />
127 <param name="read_group_name" value="A" />
128 <param name="sample_name" value="sample-a" />
129 <param name="library_name" value="A"/>
130 <param name="platform_unit" value="A"/>
131 <param name="platform" value="Illumina"/>
132 <param name="sequencing_center" value="A"/>
133 <param name="predicted_insert_size" value="300"/>
134 <param name="comment" value="A"/>
135 <param name="description" value="A"/>
136 <param name="run_date" value="2014-10-10"/>
137 <param name="min_q" value="0" />
138 <param name="max_q" value="93" />
139 <param name="strip_unpairied_mate_number" value="False" />
140 <param name="allow_and_ignore_empty_lines" value="False" />
141 <param name="validation_stringency" value="LENIENT"/>
142 <param name="fastq" value="picard_FastqToSam_read1.fq" ftype="fastq" />
143 <param name="fastq2" value="picard_FastqToSam_read2.fq" ftype="fastq" />
144 <output name="outFile" file="picard_FastqToSam_test1.bam" ftype="bam" lines_diff="4"/>
145 </test>
146 </tests>
147
148 <stdio>
149 <exit_code range="1:" level="fatal"/>
150 </stdio>
151
152 <help>
153
154 .. class:: infomark
155
156 **Purpose**
157
158 Computes a number of metrics that are useful for evaluating coverage and performance of whole genome sequencing experiments.
159
160 @dataset_collections@
161
162 @RG@
163
164 @description@
165
166 FASTQ=File
167 F1=File Input fastq file for single end data, or first read in paired end
168 data. Required.
169
170 FASTQ2=File
171 F2=File Input fastq file for the second read of paired end data (if used).
172
173 QUALITY_FORMAT=FastqQualityFormat
174 V=FastqQualityFormat A value describing how the quality values are encoded in the fastq. Either Solexa for
175 pre-pipeline 1.3 style scores (solexa scaling + 66), Illumina for pipeline 1.3 and above
176 (phred scaling + 64) or Standard for phred scaled scores with a character shift of 33.
177 If this value is not specified, the quality format will be detected automatically.
178 Default value: null. Possible values: {Solexa, Illumina, Standard}
179
180 READ_GROUP_NAME=String
181 RG=String Read group name Default value: A.
182
183 SAMPLE_NAME=String
184 SM=String Sample name to insert into the read group header Required.
185
186 LIBRARY_NAME=String
187 LB=String The library name to place into the LB attribute in the read group header.
188
189 PLATFORM_UNIT=String
190 PU=String The platform unit (often run_barcode.lane) to insert into the read group header.
191
192 PLATFORM=String
193 PL=String The platform type (e.g. illumina, solid) to insert into the read group header.
194
195 SEQUENCING_CENTER=String
196 CN=String The sequencing center from which the data originated.
197
198 PREDICTED_INSERT_SIZE=Integer
199 PI=Integer Predicted median insert size, to insert into the read group header.
200
201 COMMENT=String
202 CO=String Comment to include in the merged output file's header.
203
204 DESCRIPTION=String
205 DS=String Inserted into the read group header.
206
207 RUN_DATE=Iso8601Date
208 DT=Iso8601Date Date the run was produced, to insert into the read group header.
209
210 MIN_Q=Integer Minimum quality allowed in the input fastq. An exception will be thrown if a quality is
211 less than this value. Default value: 0.
212
213 MAX_Q=Integer Maximum quality allowed in the input fastq. An exception will be thrown if a quality is
214 greater than this value. Default value: 93.
215
216 STRIP_UNPAIRED_MATE_NUMBER=Boolean
217 If true and this is an unpaired fastq any occurance of '/1' will be removed from the end
218 of a read name. Default value: false. Possible values: {true, false}
219
220 ALLOW_AND_IGNORE_EMPTY_LINES=Boolean
221 Allow (and ignore) empty lines Default value: false. Possible values: {true, false}
222
223
224 @more_info@
225
226 </help>
227 </tool>
228
229