Mercurial > repos > devteam > picard

comparison picard_SamToFastq.xml @ 5:3d4f1fa26f0e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Tue, 16 Dec 2014 19:03:21 -0500
parents 9227b8c3093b
children 3a3234d7a2e8
comparison
equal deleted inserted replaced
4:ab1f60c26526 5:3d4f1fa26f0e
1 <tool id="picard_SamToFastq" name="SAM to FASTQ" version="1.56.1" force_history_refresh="True"> 1 <tool name="SamToFastq" id="picard_SamToFastq" version="1.126.0">
2 <description>creates a FASTQ file</description> 2 <description>extract reads and qualities from SAM/BAM dataset and convert to fastq</description>
3 <requirements><requirement type="package" version="1.56.0">picard</requirement></requirements> 3 <requirements>
4 <!-- Dan Blankenberg --> 4 <requirement type="package" version="1.126.0">picard</requirement>
5 <command interpreter="python">picard_SamToFastq_wrapper.py 5 </requirements>
6 -p ' 6
7 java -XX:DefaultMaxRAMFraction=1 -XX:+UseParallelGC 7 <macros>
8 -jar "\$JAVA_JAR_PATH/SamToFastq.jar" 8 <import>picard_macros.xml</import>
9 INPUT="${input_sam}" 9 </macros>
10 VALIDATION_STRINGENCY="LENIENT" 10
11 <command>
12
13 echo "BAM" > $report &amp;&amp; ## This is necessary for output dataset detection (see output tags below)
14
15 @java_options@
16
17 java -jar \$JAVA_JAR_PATH/picard.jar
18 SamToFastq
19
20 INPUT="${inputFile}"
21
22 #if str( $output_per_rg ) == "true":
23 OUTPUT_PER_RG=true
24 OUTPUT_DIR=.
25 #elif str( $output_per_rg ) == "false" and str( $interleave ) == "false":
26 FASTQ=READ1.fastq
27 SECOND_END_FASTQ=READ2.fastq
28 UNPAIRED_FASTQ=UNPAIRED_READS.fastq
29 #elif str( $output_per_rg ) == "false" and str( $interleave ) == "true":
30 FASTQ=INTERLEAVED.fastq
31 #end if
32
11 RE_REVERSE="${re_reverse}" 33 RE_REVERSE="${re_reverse}"
34 INTERLEAVE="${interleave}"
12 INCLUDE_NON_PF_READS="${include_non_pf_reads}" 35 INCLUDE_NON_PF_READS="${include_non_pf_reads}"
13 #if str( $clipping_attribute ): 36 CLIPPING_ATTRIBUTE="${clipping_attribute}"
14 CLIPPING_ATTRIBUTE="${clipping_attribute}" 37 CLIPPING_ACTION="${clipping_action}"
38 READ1_TRIM="${read1_trim}"
39
40 #if int($read1_max_bases_to_write) > -1:
41 READ1_MAX_BASES_TO_WRITE="${read1_max_bases_to_write}"
15 #end if 42 #end if
16 #if str( $clipping_action ): 43
17 CLIPPING_ACTION="${clipping_action}" 44 READ2_TRIM="${read2_trim}"
45
46 #if int($read2_max_bases_to_write) > -1:
47 READ2_MAX_BASES_TO_WRITE="${read2_max_bases_to_write}"
18 #end if 48 #end if
19 #if str( $read1_trim ): 49
20 READ1_TRIM="${read1_trim}"
21 #end if
22 #if str( $read1_max_bases_to_write ):
23 READ1_MAX_BASES_TO_WRITE="${read1_max_bases_to_write}"
24 #end if
25 INCLUDE_NON_PRIMARY_ALIGNMENTS="${include_non_primary_alignments}" 50 INCLUDE_NON_PRIMARY_ALIGNMENTS="${include_non_primary_alignments}"
26 51
27 #if str( $output_per_read_group_selector ) == 'per_sam_file': 52
28 ##OUTPUT_PER_RG=false 53 VALIDATION_STRINGENCY="${validation_stringency}"
29 FASTQ="${output_fastq1}" 54 QUIET=true
30 55 VERBOSITY=ERROR
31 #if str( $single_paired_end_type.single_paired_end_type_selector ) == 'paired': 56
32 SECOND_END_FASTQ="${output_fastq2}"
33 #if str( $single_paired_end_type.read2_trim ):
34 READ2_TRIM="${single_paired_end_type.read2_trim}"
35 #end if
36 #if str( $single_paired_end_type.read2_max_bases_to_write ):
37 READ2_MAX_BASES_TO_WRITE="${single_paired_end_type.read2_max_bases_to_write}"
38 #end if
39 #end if
40 '
41 #else:
42 OUTPUT_PER_RG=true
43 #if str( $single_paired_end_type.single_paired_end_type_selector ) == 'paired':
44 '
45 --read_group_file_2 "${output_fastq2}"
46 --file_id_2 "${output_fastq2.id}"
47 -p '
48 #if str( $single_paired_end_type.read2_trim ):
49 READ2_TRIM="${single_paired_end_type.read2_trim}"
50 #end if
51 #if str( $single_paired_end_type.read2_max_bases_to_write ):
52 READ2_MAX_BASES_TO_WRITE="${single_paired_end_type.read2_max_bases_to_write}"
53 #end if
54 #end if
55 '
56 --read_group_file_1 "${output_fastq1}"
57 --new_files_path "${__new_file_path__}"
58 --file_id_1 "${output_fastq1.id}"
59 #end if
60 </command> 57 </command>
61 <inputs> 58 <inputs>
62 <param name="input_sam" type="data" format="sam,bam" label="BAM/SAM file" /> 59
63 <param name="read1_trim" type="integer" value="" optional="True" label="The number of bases to trim from the beginning of read 1." /> 60 <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/>
64 <param name="read1_max_bases_to_write" type="integer" optional="True" value="" label="The maximum number of bases to write from read 1 after trimming." /> 61 <param name="output_per_rg" type="boolean" checked="False" label="Do you want to output a fastq file per read group (two fastq files per read group if the group is paired)" help="OUTPUT_PER_RG; default=False"/>
65 <param name="output_per_read_group_selector" type="select" label="Output per read group"> 62 <param name="re_reverse" type="boolean" checked="True" label="Re-reverse bases and qualities of reads with negative strand flag set before writing them to fastq" help="RE_REVERSE; default=True"/>
66 <option value="per_sam_file" selected="True">Per BAM/SAM file</option> 63 <param name="interleave" type="boolean" label="Will generate an interleaved fastq if paired, each line will have /1 or /2 to describe which end it came from" help="INTERLEAVE; default=False"/>
67 <option value="per_read_group">Per Read Group</option> 64 <param name="include_non_pf_reads" type="boolean" label="Include non-PF reads from the SAM/BAM dataset into the output FASTQ" help="INCLUDE_NON_PF_READS; PF means 'passes filtering'. Reads whose 'not passing quality controls' flag is set are non-PF reads; default=False"/>
68 </param> 65 <param name="clipping_attribute" type="text" size="4" value="null" label="The attribute that stores the position at which the SAM/BAM record should be clipped" help="CLIPPING_ATTRIBUTE; default=null"/>
69 <conditional name="single_paired_end_type"> 66 <param name="clipping_action" type="text" size="10" value="null" label="The action that should be taken with clipped reads: 'X' means the reads and qualities should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in the clipped region; and any integer means that the base qualities should be set to that value in the clipped region" help="CLIPPING_ACTION; default=null"/>
70 <param name="single_paired_end_type_selector" type="select" label="Single or Paired end"> 67 <param name="read1_trim" type="integer" value="0" min="0" label="The number of bases to trim from the beginning of read 1" help="READ1_TRIM; default=0"/>
71 <option value="single" selected="True">Single</option> 68 <param name="read1_max_bases_to_write" type="integer" value="-1" label="The maximum number of bases to write from read 1 after trimming" help="READ1_MAX_BASES_TO_WRITE; If there are fewer than this many bases left after trimming, all will be written. If this value is null then all bases left after trimming will be written; default=null (-1)"/>
72 <option value="paired">Paired end</option> 69 <param name="read2_trim" type="integer" value="0" min="0" label="The number of bases to trim from the beginning of read 2" help="READ2_TRIM; default=0"/>
73 </param> 70 <param name="read2_max_bases_to_write" type="integer" value="-1" label="The maximum number of bases to write from read 2 after trimming" help="READ2_MAX_BASES_TO_WRITE; If there are fewer than this many bases left after trimming, all will be written. If this value is null then all bases left after trimming will be written; default=null (-1)"/>
74 <when value="single"> 71 <param name="include_non_primary_alignments" type="boolean" label="If true, include non-primary alignments in the output" help="INCLUDE_NON_PRIMARY_ALIGNMENTS; Support of non-primary alignments in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and there are paired reads with non-primary alignments; default=False"/>
75 <!-- nothing yet --> 72
76 </when> 73 <expand macro="VS" />
77 <when value="paired"> 74
78 <param name="read2_trim" type="integer" value="" optional="True" label="The number of bases to trim from the beginning of read 2." /> 75 </inputs>
79 <param name="read2_max_bases_to_write" type="integer" optional="True" value="" label="The maximum number of bases to write from read 2 after trimming." /> 76
80 </when>
81 </conditional>
82 <param name="re_reverse" type="boolean" truevalue="true" falsevalue="false" checked="True" label="Re-reverse bases and qualities of reads on negative strand"/>
83 <param name="include_non_pf_reads" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Include non-PF reads from the SAM file into the output FASTQ files."/>
84 <param name="clipping_attribute" type="text" value="" label="The attribute that stores the position at which the SAM record should be clipped" help="Leave blank for null" />
85 <param name="clipping_action" type="text" value="" label="The action that should be taken with clipped reads" help="'X' means the reads and qualities should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in the clipped region; and any integer means that the base qualities should be set to that value in the clipped region. Leave blank for null" />
86 <param name="include_non_primary_alignments" type="boolean" truevalue="true" falsevalue="false" checked="False" label="If true, include non-primary alignments in the output." help="Support of non-primary alignments in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and there are paired reads with non-primary alignments."/>
87
88 </inputs>
89 <outputs> 77 <outputs>
90 <data format="fastqsanger" name="output_fastq1" label="${tool.name} on ${on_string}: FASTQ 1" /> 78 <!-- here dataset discovery is based on fact that if OUTPUT_PER_RG=true this tool automatically adds .fastq extension to emitted files -->
91 <data format="fastqsanger" name="output_fastq2" label="${tool.name} on ${on_string}: FASTQ 2" > 79 <data format="txt" name="report" label="SamToFastq run" hidden="true">
92 <filter>single_paired_end_type['single_paired_end_type_selector'] == 'paired'</filter> 80 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.fastq" ext="fastqsanger" visible="true"/>
93 </data> 81 </data>
94 </outputs> 82 </outputs>
83
95 <tests> 84 <tests>
96 <test> 85 <test>
97 <param name="input_sam" value="bfast_out1.sam" ftype="sam" /> 86 <param name="inputFile" value="picard_SamToFastq.bam" ftype="bam"/>
98 <param name="output_per_read_group_selector" value="per_sam_file" /> 87 <param name="output_per_rg" value="false"/>
99 <param name="single_paired_end_type_selector" value="single" /> 88 <param name="re_reverse" value="true"/>
100 <param name="read1_trim" value="" /> 89 <param name="interleave" value="true"/>
101 <param name="read1_max_bases_to_write" value="" /> 90 <param name="include_non_pf_reads" value="false"/>
102 <param name="re_reverse" value="True" /> 91 <param name="clipping_attribute" value="null" />
103 <param name="include_non_pf_reads" value="False" /> 92 <param name="clipping_action" value="null" />
104 <param name="clipping_action" value="" /> 93 <param name="read1_trim" value="0" />
105 <param name="clipping_attribute" value="" /> 94 <param name="read1_max_bases_to_write" value="-1"/>
106 <param name="include_non_primary_alignments" value="False" /> 95 <param name="read2_trim" value="0" />
107 <output name="output_fastq1" file="random_phiX_1.fastqsanger"/> 96 <param name="read2_max_bases_to_write" value="-1"/>
108 </test> 97 <param name="include_non_primary_alignments" value="false"/>
109 <test> 98 <output name="report">
110 <param name="input_sam" value="bwa_wrapper_out3.sam" ftype="sam" /> 99 <assert_contents>
111 <param name="output_per_read_group_selector" value="per_sam_file" /> 100 <has_line line="BAM" />
112 <param name="single_paired_end_type_selector" value="paired" /> 101 </assert_contents>
113 <param name="read1_trim" value="" /> 102 <discovered_dataset designation="INTERLEAVED" file="picard_SamToFastq_test1.fq" ftype="fastqsanger"/>
114 <param name="read1_max_bases_to_write" value="" /> 103 </output>
115 <param name="read2_trim" value="" /> 104 </test>
116 <param name="read2_max_bases_to_write" value="" />
117 <param name="re_reverse" value="True" />
118 <param name="include_non_pf_reads" value="False" />
119 <param name="clipping_action" value="" />
120 <param name="clipping_attribute" value="" />
121 <param name="include_non_primary_alignments" value="False" />
122 <output name="output_fastq1" file="bwa_wrapper_in2.fastqsanger" lines_diff="64"/> <!-- 16 unaligned fastq blocks not present in original sam file -->
123 <output name="output_fastq2" file="bwa_wrapper_in3.fastqsanger" lines_diff="64"/> <!-- 16 unaligned fastq blocks not present in original sam file -->
124 </test>
125 <test>
126 <param name="input_sam" value="bwa_wrapper_out3.sam" ftype="sam" />
127 <param name="output_per_read_group_selector" value="per_read_group" />
128 <param name="single_paired_end_type_selector" value="paired" />
129 <param name="read1_trim" value="" />
130 <param name="read1_max_bases_to_write" value="" />
131 <param name="read2_trim" value="" />
132 <param name="read2_max_bases_to_write" value="" />
133 <param name="re_reverse" value="True" />
134 <param name="include_non_pf_reads" value="False" />
135 <param name="clipping_action" value="" />
136 <param name="clipping_attribute" value="" />
137 <param name="include_non_primary_alignments" value="False" />
138 <output name="output_fastq1" file="bwa_wrapper_in2.fastqsanger" lines_diff="64"/> <!-- 16 unaligned fastq blocks not present in original sam file -->
139 <output name="output_fastq2" file="bwa_wrapper_in3.fastqsanger" lines_diff="64"/> <!-- 16 unaligned fastq blocks not present in original sam file -->
140 </test>
141 </tests> 105 </tests>
106
107 <stdio>
108 <exit_code range="1:" level="fatal"/>
109 </stdio>
110
142 <help> 111 <help>
143 **What it does** 112
144 113 **Purpose**
145 Picard: SamToFastq converts SAM files to FASTQ files. 114
146 115 Extracts read sequences and qualities from the input SAM/BAM dataset and outputs them in Sanger fastq format. In the RE_REVERSE=True mode (default behavior), if the read is aligned and the alignment is to the reverse strand on the genome, the read's sequence from input SAM.BAM dataset will be reverse-complemented prior to writing it to fastq in order restore correctly the original read sequence as it was generated by the sequencer.
147 Extracts read sequences and qualities from the input SAM/BAM file and writes them into the output file in Sanger fastq format. In the RC mode (default is True), if the read is aligned and the alignment is to the reverse strand on the genome, the read's sequence from input SAM file will be reverse-complemented prior to writing it to fastq in order restore correctly the original read sequence as it was generated by the sequencer. 116
148 117 -----
149 ------ 118
150 119 .. class:: warningmark
151 Please cite the website "http://picard.sourceforge.net". 120
152 121 **DANGER: Multiple Outputs**
153 ------ 122
154 123 Generating per readgroup fastq (setting **OUTPUT_PER_RG** to True) may produce very large numbers of outputs. Know what you are doing!
155 124
156 **Input formats** 125 @dataset_collections@
157 126
158 FastqToSam accepts SAM input files, see http://samtools.sourceforge.net for more details. 127 @description@
159 128
160 ------ 129 FASTQ=File
161 130 F=File Output fastq file (single-end fastq or, if paired, first end of the pair fastq).
162 **Outputs** 131 Required. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG)
163 132
164 The output is in FASTQ format. If using Paired end data, 2 fastq files are created. 133 SECOND_END_FASTQ=File
165 134 F2=File Output fastq file (if paired, second end of the pair fastq). Default value: null.
166 ------- 135 Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG)
167 136
168 **FastqToSam settings** 137 UNPAIRED_FASTQ=File
169 138 FU=File Output fastq file for unpaired reads; may only be provided in paired-fastq mode Default
170 This is list of SamToFastq options:: 139 value: null. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG)
171 140
172 INPUT=File Input SAM/BAM file to extract reads from Required. 141 OUTPUT_PER_RG=Boolean
173 FASTQ=File Output fastq file (single-end fastq or, if paired, first end of the pair fastq). Required. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) 142 OPRG=Boolean Output a fastq file per read group (two fastq files per read group if the group is
174 SECOND_END_FASTQ=File Output fastq file (if paired, second end of the pair fastq). Default value: null. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) 143 paired). Default value: false. Possible values: {true, false} Cannot be used in
175 OUTPUT_PER_RG=Boolean Output a fastq file per read group (two fastq files per read group if the group is paired). Default value: false. This option can be set to 'null' to clear the default value. Possible values: {true, false} Cannot be used in conjuction with option(s) SECOND_END_FASTQ (F2) FASTQ (F) 144 conjuction with option(s) SECOND_END_FASTQ (F2) UNPAIRED_FASTQ (FU) FASTQ (F)
176 OUTPUT_DIR=File Directory in which to output the fastq file(s). Used only when OUTPUT_PER_RG is true. Default value: null. 145
177 RE_REVERSE=Boolean Re-reverse bases and qualities of reads with negative strand flag set before writing them to fastq Default value: true. This option can be set to 'null' to clear the default value. Possible values: {true, false} 146 OUTPUT_DIR=File
178 INCLUDE_NON_PF_READS=Boolean Include non-PF reads from the SAM file into the output FASTQ files. Default value: false. This option can be set to 'null' to clear the default value. Possible values: {true, false} 147 ODIR=File Directory in which to output the fastq file(s). Used only when OUTPUT_PER_RG is true.
179 CLIPPING_ATTRIBUTE=String The attribute that stores the position at which the SAM record should be clipped Default value: null. 148 Default value: null.
180 CLIPPING_ACTION=String The action that should be taken with clipped reads: 'X' means the reads and qualities should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in the clipped region; and any integer means that the base qualities should be set to that value in the clipped region. Default value: null. 149
181 READ1_TRIM=Integer The number of bases to trim from the beginning of read 1. Default value: 0. This option can be set to 'null' to clear the default value. 150 RE_REVERSE=Boolean
182 READ1_MAX_BASES_TO_WRITE=Integer The maximum number of bases to write from read 1 after trimming. If there are fewer than this many bases left after trimming, all will be written. If this value is null then all bases left after trimming will be written. Default value: null. 151 RC=Boolean Re-reverse bases and qualities of reads with negative strand flag set before writing them
183 READ2_TRIM=Integer The number of bases to trim from the beginning of read 2. Default value: 0. This option can be set to 'null' to clear the default value. 152 to fastq Default value: true. Possible values: {true, false}
184 READ2_MAX_BASES_TO_WRITE=Integer The maximum number of bases to write from read 2 after trimming. If there are fewer than this many bases left after trimming, all will be written. If this value is null then all bases left after trimming will be written. Default value: null. 153
185 INCLUDE_NON_PRIMARY_ALIGNMENTS=Boolean If true, include non-primary alignments in the output. Support of non-primary alignments in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and there are paired reads with non-primary alignments. Default value: false. This option can be set to 'null' to clear the default value. Possible values: {true, false} 154 INTERLEAVE=Boolean
186 155 INTER=Boolean Will generate an interleaved fastq if paired, each line will have /1 or /2 to describe
156 which end it came from Default value: false. Possible values: {true, false}
157
158 INCLUDE_NON_PF_READS=Boolean
159 NON_PF=Boolean Include non-PF reads from the SAM file into the output FASTQ files. PF means 'passes
160 filtering'. Reads whose 'not passing quality controls' flag is set are non-PF reads.
161 Default value: false. Possible values: {true, false}
162
163 CLIPPING_ATTRIBUTE=String
164 CLIP_ATTR=String The attribute that stores the position at which the SAM record should be clipped Default
165 value: null.
166
167 CLIPPING_ACTION=String
168 CLIP_ACT=String The action that should be taken with clipped reads: 'X' means the reads and qualities
169 should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in
170 the clipped region; and any integer means that the base qualities should be set to that
171 value in the clipped region. Default value: null.
172
173 READ1_TRIM=Integer
174 R1_TRIM=Integer The number of bases to trim from the beginning of read 1. Default value: 0.
175
176 READ1_MAX_BASES_TO_WRITE=Integer
177 R1_MAX_BASES=Integer The maximum number of bases to write from read 1 after trimming. If there are fewer than
178 this many bases left after trimming, all will be written. If this value is null then all
179 bases left after trimming will be written. Default value: null.
180
181 READ2_TRIM=Integer
182 R2_TRIM=Integer The number of bases to trim from the beginning of read 2. Default value: 0.
183
184 READ2_MAX_BASES_TO_WRITE=Integer
185 R2_MAX_BASES=Integer The maximum number of bases to write from read 2 after trimming. If there are fewer than
186 this many bases left after trimming, all will be written. If this value is null then all
187 bases left after trimming will be written. Default value: null.
188
189 INCLUDE_NON_PRIMARY_ALIGNMENTS=Boolean
190 If true, include non-primary alignments in the output. Support of non-primary alignments
191 in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and
192 there are paired reads with non-primary alignments. Default value: false.
193 Possible values: {true, false}
194
195 @more_info@
187 196
188 </help> 197 </help>
189 </tool> 198 </tool>
199
200