Mercurial > repos > avowinkel > picard

comparison picard_FastqToSam.xml @ 0:5166ed57b1c4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded version 1.135
author avowinkel
date Mon, 06 Jul 2015 14:46:32 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:5166ed57b1c4
1 <tool name="FastqToSam" id="picard_FastqToSam" version="1.135">
2 <description>convert Fastq data into unaligned BAM</description>
3 <macros>
4 <import>picard_macros.xml</import>
5 </macros>
6 <expand macro="requirements" />
7 <command>
8 @java_options@
9
10 java -jar \$JAVA_JAR_PATH/picard.jar
11 FastqToSam
12
13 #if str( $input_type.input_type_selector ) == "se":
14 FASTQ="${input_type.fastq}"
15 #elif str( $input_type.input_type_selector ) == "pe":
16 FASTQ="${input_type.fastq}"
17 FASTQ2="${input_type.fastq2}"
18 #else
19 FASTQ="${input_type.fastq.forward}"
20 FASTQ2="${input_type.fastq.reverse}"
21 #end if
22
23 QUALITY_FORMAT="${quality_format}"
24 OUTPUT="${outFile}"
25 READ_GROUP_NAME="${read_group_name}"
26 SAMPLE_NAME="${sample_name}"
27
28 #if str( $library_name ):
29 LIBRARY_NAME="${library_name}"
30 #end if
31
32 #if str( $platform_unit ):
33 PLATFORM_UNIT="${platform_unit}"
34 #end if
35
36 #if str( $platform ):
37 PLATFORM="${platform}"
38 #end if
39
40 #if str( $sequencing_center ):
41 SEQUENCING_CENTER="${sequencing_center}"
42 #end if
43
44 #if str( $predicted_insert_size ):
45 PREDICTED_INSERT_SIZE="${predicted_insert_size}"
46 #end if
47
48 #if str( $comment ):
49 COMMENT="${comment}"
50 #end if
51
52 #if str( $description ):
53 DESCRIPTION="${description}"
54 #end if
55
56 #if str( $run_date ):
57 RUN_DATE="${run_date}"
58 #end if
59
60 MIN_Q="${min_q}"
61 MAX_Q="${max_q}"
62 STRIP_UNPAIRED_MATE_NUMBER="${strip_unpairied_mate_number}"
63 ALLOW_AND_IGNORE_EMPTY_LINES="${allow_and_ignore_empty_lines}"
64
65 SORT_ORDER=coordinate
66 VALIDATION_STRINGENCY="${validation_stringency}"
67 QUIET=true
68 VERBOSITY=ERROR
69
70 </command>
71 <inputs>
72 <conditional name="input_type">
73 <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">
74 <option value="se">Single end (single dataset)</option>
75 <option value="pe">Paired end (two datasets)</option>
76 <option value="pc">Paired collection</option>
77 </param>
78 <when value="se">
79 <param name="fastq" type="data" format="fastq" label="Input fastq file for single end data" help="FASTQ"/>
80 </when>
81 <when value="pe">
82 <param name="fastq" type="data" format="fastq" label="Input fastq file for the first read in paired end data" help="FASTQ"/>
83 <param name="fastq2" type="data" format="fastq" label="Input fastq file for the second read of paired end data" help="FASTQ2"/>
84 </when>
85 <when value="pc">
86 <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"/>
87 </when>
88 </conditional>
89
90 <param name="quality_format" type="select" label="Select quality encoding scheme" help="QUALITY_FORMAT">
91 <option value="Standard" selected="True">Sanger (+33)</option>
92 <option value="Illumina">Illumina (+64)</option>
93 <option value="Solexa">Solexa (+66)</option>
94 </param>
95
96 <param name="read_group_name" type="text" size="20" value="A" label="Read group name" help="READ_GROUP_NAME"/>
97 <param name="sample_name" type="text" size="20" value="sample-a" label="Sample name" help="SAMPLE_NAME"/>
98 <param name="library_name" type="text" size="20" optional="True" label="The library name" help="LIBRARY_NAME; Optional"/>
99 <param name="platform_unit" type="text" size="20" optional="True" label="The platform unit (often run_barcode.lane)" help="PLATFORM_UNIT; Optional"/>
100 <param name="platform" type="text" size="20" optional="True" label="The platform type (e.g. illumina, 454)" help="PLATFORM; Optional"/>
101 <param name="sequencing_center" type="text" size="20" optional="True" label="The sequencing center from which the data originated" help="SEQUENCING_CENTER; Optional"/>
102
103 <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"/>
104 <param name="comment" type="text" size="20" optional="True" label="Comment to include in the output dataset's header" help="COMMENT; Optional"/>
105 <param name="description" type="text" size="20" optional="True" label="Optional description information" help="DESCRIPTION; Optional"/>
106 <param name="run_date" optional="True" type="text" label="Run date" help="RGDT; Optional; Format=YYYY-MM-DD (eg 1997-07-16)"/>
107 <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"/>
108 <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"/>
109 <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"/>
110 <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"/>
111
112 <expand macro="VS" />
113
114 </inputs>
115
116 <outputs>
117 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: reads as unaligned BAM"/>
118 </outputs>
119
120 <tests>
121 <test>
122 <param name="input_type_selector" value="pe" />
123 <param name="quality_format" value="Standard" />
124 <param name="read_group_name" value="A" />
125 <param name="sample_name" value="sample-a" />
126 <param name="library_name" value="A"/>
127 <param name="platform_unit" value="A"/>
128 <param name="platform" value="Illumina"/>
129 <param name="sequencing_center" value="A"/>
130 <param name="predicted_insert_size" value="300"/>
131 <param name="comment" value="A"/>
132 <param name="description" value="A"/>
133 <param name="run_date" value="2014-10-10"/>
134 <param name="min_q" value="0" />
135 <param name="max_q" value="93" />
136 <param name="strip_unpairied_mate_number" value="False" />
137 <param name="allow_and_ignore_empty_lines" value="False" />
138 <param name="validation_stringency" value="LENIENT"/>
139 <param name="fastq" value="picard_FastqToSam_read1.fq" ftype="fastq" />
140 <param name="fastq2" value="picard_FastqToSam_read2.fq" ftype="fastq" />
141 <output name="outFile" file="picard_FastqToSam_test1.bam" ftype="bam" lines_diff="4"/>
142 </test>
143 </tests>
144
145 <stdio>
146 <exit_code range="1:" level="fatal"/>
147 </stdio>
148
149 <help>
150
151 .. class:: infomark
152
153 **Purpose**
154
155 Computes a number of metrics that are useful for evaluating coverage and performance of whole genome sequencing experiments.
156
157 @dataset_collections@
158
159 @RG@
160
161 @description@
162
163 FASTQ=File
164 F1=File Input fastq file for single end data, or first read in paired end
165 data. Required.
166
167 FASTQ2=File
168 F2=File Input fastq file for the second read of paired end data (if used).
169
170 QUALITY_FORMAT=FastqQualityFormat
171 V=FastqQualityFormat A value describing how the quality values are encoded in the fastq. Either Solexa for
172 pre-pipeline 1.3 style scores (solexa scaling + 66), Illumina for pipeline 1.3 and above
173 (phred scaling + 64) or Standard for phred scaled scores with a character shift of 33.
174 If this value is not specified, the quality format will be detected automatically.
175 Default value: null. Possible values: {Solexa, Illumina, Standard}
176
177 READ_GROUP_NAME=String
178 RG=String Read group name Default value: A.
179
180 SAMPLE_NAME=String
181 SM=String Sample name to insert into the read group header Required.
182
183 LIBRARY_NAME=String
184 LB=String The library name to place into the LB attribute in the read group header.
185
186 PLATFORM_UNIT=String
187 PU=String The platform unit (often run_barcode.lane) to insert into the read group header.
188
189 PLATFORM=String
190 PL=String The platform type (e.g. illumina, solid) to insert into the read group header.
191
192 SEQUENCING_CENTER=String
193 CN=String The sequencing center from which the data originated.
194
195 PREDICTED_INSERT_SIZE=Integer
196 PI=Integer Predicted median insert size, to insert into the read group header.
197
198 COMMENT=String
199 CO=String Comment to include in the merged output file's header.
200
201 DESCRIPTION=String
202 DS=String Inserted into the read group header.
203
204 RUN_DATE=Iso8601Date
205 DT=Iso8601Date Date the run was produced, to insert into the read group header.
206
207 MIN_Q=Integer Minimum quality allowed in the input fastq. An exception will be thrown if a quality is
208 less than this value. Default value: 0.
209
210 MAX_Q=Integer Maximum quality allowed in the input fastq. An exception will be thrown if a quality is
211 greater than this value. Default value: 93.
212
213 STRIP_UNPAIRED_MATE_NUMBER=Boolean
214 If true and this is an unpaired fastq any occurance of '/1' will be removed from the end
215 of a read name. Default value: false. Possible values: {true, false}
216
217 ALLOW_AND_IGNORE_EMPTY_LINES=Boolean
218 Allow (and ignore) empty lines Default value: false. Possible values: {true, false}
219
220
221 @more_info@
222
223 </help>
224 </tool>
225
226