Mercurial > repos > devteam > picard

comparison picard_FastqToSam.xml @ 3:52fdfc45590a draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
author devteam
date Thu, 16 Jul 2015 15:32:31 -0400
parents ff4ec13e496e
children 2589e6207cb4
comparison
equal deleted inserted replaced
2:93ace7e49295 3:52fdfc45590a
1 <tool id="picard_FastqToSam" name="FASTQ to BAM" version="1.56.0"> 1 <tool name="FastqToSam" id="picard_FastqToSam" version="@TOOL_VERSION@.0">
2 <description>creates an unaligned BAM file</description> 2 <description>convert Fastq data into unaligned BAM</description>
3 <requirements><requirement type="package" version="1.56.0">picard</requirement></requirements> 3 <macros>
4 <!-- Dan Blankenberg --> 4 <import>picard_macros.xml</import>
5 <command>java -XX:DefaultMaxRAMFraction=1 -XX:+UseParallelGC 5 </macros>
6 -jar "\$JAVA_JAR_PATH/FastqToSam.jar" 6 <expand macro="requirements" />
7 FASTQ="${input_fastq1}" 7 <command>
8 #if str( $input_fastq2) != "None": 8 @java_options@
9 FASTQ2="${input_fastq2}" 9
10 #end if 10 java -jar \$JAVA_JAR_PATH/picard.jar
11 QUALITY_FORMAT="${ dict( fastqsanger='Standard', fastqcssanger='Standard', fastqillumina='Illumina', fastqsolexa='Solexa' )[ $input_fastq1.ext ] }" ##Solexa, Illumina, Standard 11 FastqToSam
12 OUTPUT="${output_bam}" 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="${outFile}"
13 READ_GROUP_NAME="${read_group_name}" 25 READ_GROUP_NAME="${read_group_name}"
14 SAMPLE_NAME="${sample_name}" 26 SAMPLE_NAME="${sample_name}"
15 #if $param_type.param_type_selector == "advanced": 27
16 #if str( $param_type.library_name ) != "": 28 #if str( $library_name ):
17 LIBRARY_NAME="${param_type.library_name}" 29 LIBRARY_NAME="${library_name}"
18 #end if 30 #end if
19 #if str( $param_type.platform_unit ) != "": 31
20 PLATFORM_UNIT="${param_type.platform_unit}" 32 #if str( $platform_unit ):
21 #end if 33 PLATFORM_UNIT="${platform_unit}"
22 #if str( $param_type.platform ) != "": 34 #end if
23 PLATFORM="${param_type.platform}" 35
24 #end if 36 #if str( $platform ):
25 #if str( $param_type.sequencing_center ) != "": 37 PLATFORM="${platform}"
26 SEQUENCING_CENTER="${param_type.sequencing_center}" 38 #end if
27 #end if 39
28 #if str( $param_type.predicted_insert_size ) != "": 40 #if str( $sequencing_center ):
29 PREDICTED_INSERT_SIZE="${param_type.predicted_insert_size}" 41 SEQUENCING_CENTER="${sequencing_center}"
30 #end if 42 #end if
31 #if str( $param_type.description.value ) != "": 43
32 DESCRIPTION="${param_type.description}" 44 #if str( $predicted_insert_size ):
33 #end if 45 PREDICTED_INSERT_SIZE="${predicted_insert_size}"
34 #if str( $param_type.run_date ) != "": 46 #end if
35 RUN_DATE="${param_type.run_date}" 47
36 #end if 48 #if str( $comment ):
37 #if str( $param_type.min_q ) != "": 49 COMMENT="${comment}"
38 MIN_Q="${param_type.min_q}" 50 #end if
39 #end if 51
40 #if str( $param_type.min_q ) != "": 52 #if str( $description ):
41 MAX_Q="${param_type.max_q}" 53 DESCRIPTION="${description}"
42 #end if 54 #end if
43 SORT_ORDER="${param_type.sort_order}" 55
44 #else: 56 #if str( $run_date ):
45 SORT_ORDER=coordinate ##unsorted, queryname, coordinate; always use coordinate 57 RUN_DATE="${run_date}"
46 #end if 58 #end if
47 2&gt;&amp;1 59
48 || echo "Error running Picard FastqToSAM" >&amp;2 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
49 </command> 70 </command>
50 <inputs> 71 <inputs>
51 <param name="input_fastq1" type="data" format="fastqsanger,fastqillumina,fastqsolexa,fastqcssanger" label="FASTQ file" /> <!-- confirm that fastqcssanger also works --> 72 <conditional name="input_type">
52 <param name="input_fastq2" type="data" format="fastqsanger,fastqillumina,fastqsolexa,fastqcssanger" optional="True" label="Second FASTQ of paired end data" help="Only needed when using paired end data." > 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">
53 <options options_filter_attribute="ext" from_parameter="tool.app.datatypes_registry.datatypes_by_extension" transform_lines="obj.keys()"> 74 <option value="se">Single end (single dataset)</option>
54 <column name="name" index="0"/> 75 <option value="pe">Paired end (two datasets)</option>
55 <column name="value" index="0"/> 76 <option value="pc">Paired collection</option>
56 <filter type="param_value" ref="input_fastq1" ref_attribute="ext" column="0"/>
57 </options>
58 </param>
59 <param name="read_group_name" type="text" value="A" label="Read Group Name" />
60 <param name="sample_name" type="text" value="unknown sample" label="Sample Name" />
61 <conditional name="param_type">
62 <param name="param_type_selector" type="select" label="Basic or Advanced options">
63 <option value="basic" selected="True">Basic</option>
64 <option value="advanced">Advanced</option>
65 </param> 77 </param>
66 <when value="basic"> 78 <when value="se">
67 <!-- Do nothing here --> 79 <param name="fastq" type="data" format="fastq" label="Input fastq file for single end data" help="FASTQ"/>
68 </when> 80 </when>
69 <when value="advanced"> 81 <when value="pe">
70 <param name="library_name" type="text" value="" label="Library Name" /> 82 <param name="fastq" type="data" format="fastq" label="Input fastq file for the first read in paired end data" help="FASTQ"/>
71 <param name="platform_unit" type="text" value="" label="Platform Unit" /> 83 <param name="fastq2" type="data" format="fastq" label="Input fastq file for the second read of paired end data" help="FASTQ2"/>
72 <param name="platform" type="text" value="" label="Platform" /> 84 </when>
73 <param name="sequencing_center" type="text" value="" label="Sequencing Center" /> 85 <when value="pc">
74 <param name="predicted_insert_size" type="integer" value="" optional="True" label="Predicted Insert Size" /> 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"/>
75 <param name="description" type="text" value="" label="Description" />
76 <param name="run_date" type="text" value="" label="Run Date" />
77 <param name="min_q" type="integer" optional="True" value="0" label="Min Q" />
78 <param name="max_q" type="integer" optional="True" value="93" label="Max Q" />
79 <param name="sort_order" type="select" label="Sort order">
80 <option value="coordinate" selected="True">coordinate</option>
81 <option value="queryname">queryname</option>
82 <option value="unsorted">unsorted</option>
83 </param>
84 </when> 87 </when>
85 </conditional> 88 </conditional>
86 </inputs> 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
87 <outputs> 116 <outputs>
88 <data format="bam" name="output_bam" /> 117 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: reads as unaligned BAM"/>
89 </outputs> 118 </outputs>
119
90 <tests> 120 <tests>
91 <test> 121 <test>
92 <param name="input_fastq1" value="bwa_wrapper_in2.fastqsanger" ftype="fastqsanger" /> 122 <param name="input_type_selector" value="pe" />
93 <param name="input_fastq2" /> 123 <param name="quality_format" value="Standard" />
94 <param name="read_group_name" value="A" /> 124 <param name="read_group_name" value="A" />
95 <param name="sample_name" value="unknown sample" /> 125 <param name="sample_name" value="sample-a" />
96 <param name="param_type_selector" value="basic" /> 126 <param name="library_name" value="A"/>
97 <output name="output_bam" file="picard_fastq_to_sam_out1.bam" ftype="bam"/> 127 <param name="platform_unit" value="A"/>
98 </test> 128 <param name="platform" value="Illumina"/>
99 <test> 129 <param name="sequencing_center" value="A"/>
100 <param name="input_fastq1" value="bwa_wrapper_in2.fastqsanger" ftype="fastqsanger" /> 130 <param name="predicted_insert_size" value="300"/>
101 <param name="input_fastq2" value="bwa_wrapper_in3.fastqsanger" ftype="fastqsanger" /> 131 <param name="comment" value="A"/>
102 <param name="read_group_name" value="A" /> 132 <param name="description" value="A"/>
103 <param name="sample_name" value="unknown sample" /> 133 <param name="run_date" value="2014-10-10"/>
104 <param name="param_type_selector" value="basic" /> 134 <param name="min_q" value="0" />
105 <output name="output_bam" file="picard_fastq_to_sam_out2.bam" ftype="bam"/> 135 <param name="max_q" value="93" />
106 </test> 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>
107 </tests> 143 </tests>
144
145 <stdio>
146 <exit_code range="1:" level="fatal"/>
147 </stdio>
148
108 <help> 149 <help>
109 **What it does** 150
110 151 .. class:: infomark
111 Picard: FastqToSam converts FASTQ files to unaligned BAM files. 152
112 153 **Purpose**
113 ------ 154
114 155 Computes a number of metrics that are useful for evaluating coverage and performance of whole genome sequencing experiments.
115 Please cite the website "http://picard.sourceforge.net". 156
116 157 @dataset_collections@
117 ------ 158
118 159 @RG@
119 160
120 **Input formats** 161 @description@
121 162
122 FastqToSam accepts FASTQ input files. If using paired-end data, you should select two FASTQ files. 163 FASTQ=File
123 164 F1=File Input fastq file for single end data, or first read in paired end
124 ------ 165 data. Required.
125 166
126 **Outputs** 167 FASTQ2=File
127 168 F2=File Input fastq file for the second read of paired end data (if used).
128 The output is in BAM format, see http://samtools.sourceforge.net for more details. 169
129 170 QUALITY_FORMAT=FastqQualityFormat
130 ------- 171 V=FastqQualityFormat A value describing how the quality values are encoded in the fastq. Either Solexa for
131 172 pre-pipeline 1.3 style scores (solexa scaling + 66), Illumina for pipeline 1.3 and above
132 **FastqToSam settings** 173 (phred scaling + 64) or Standard for phred scaled scores with a character shift of 33.
133 174 If this value is not specified, the quality format will be detected automatically.
134 This is list of FastqToSam options:: 175 Default value: null. Possible values: {Solexa, Illumina, Standard}
135 176
136 READ_GROUP_NAME=String Read group name Default value: A. This option can be set to 'null' to clear the default value. 177 READ_GROUP_NAME=String
137 SAMPLE_NAME=String Sample name to insert into the read group header Required. 178 RG=String Read group name Default value: A.
138 LIBRARY_NAME=String The library name to place into the LB attribute in the read group header Default value: null. 179
139 PLATFORM_UNIT=String The platform unit (often run_barcode.lane) to insert into the read group header Default value: null. 180 SAMPLE_NAME=String
140 PLATFORM=String The platform type (e.g. illumina, solid) to insert into the read group header Default value: null. 181 SM=String Sample name to insert into the read group header Required.
141 SEQUENCING_CENTER=String The sequencing center from which the data originated Default value: null. 182
142 PREDICTED_INSERT_SIZE=Integer Predicted median insert size, to insert into the read group header Default value: null. 183 LIBRARY_NAME=String
143 DESCRIPTION=String Inserted into the read group header Default value: null. 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
144 </help> 223 </help>
145 </tool> 224 </tool>
225
226