Mercurial > repos > avowinkel > picard

comparison picard_SamToFastq.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="SamToFastq" id="picard_SamToFastq" version="1.135">
2 <description>extract reads and qualities from SAM/BAM dataset and convert to fastq</description>
3 <macros>
4 <import>picard_macros.xml</import>
5 </macros>
6 <expand macro="requirements" />
7 <command>
8
9 echo "BAM" > $report &amp;&amp; ## This is necessary for output dataset detection (see output tags below)
10
11 @java_options@
12
13 java -jar \$JAVA_JAR_PATH/picard.jar
14 SamToFastq
15
16 INPUT="${inputFile}"
17
18 #if str( $output_per_rg ) == "true":
19 OUTPUT_PER_RG=true
20 OUTPUT_DIR=.
21 #elif str( $output_per_rg ) == "false" and str( $interleave ) == "false":
22 FASTQ=READ1.fastq
23 SECOND_END_FASTQ=READ2.fastq
24 UNPAIRED_FASTQ=UNPAIRED_READS.fastq
25 #elif str( $output_per_rg ) == "false" and str( $interleave ) == "true":
26 FASTQ=INTERLEAVED.fastq
27 #end if
28
29 RE_REVERSE="${re_reverse}"
30 INTERLEAVE="${interleave}"
31 INCLUDE_NON_PF_READS="${include_non_pf_reads}"
32 CLIPPING_ATTRIBUTE="${clipping_attribute}"
33 CLIPPING_ACTION="${clipping_action}"
34 READ1_TRIM="${read1_trim}"
35
36 #if int($read1_max_bases_to_write) > -1:
37 READ1_MAX_BASES_TO_WRITE="${read1_max_bases_to_write}"
38 #end if
39
40 READ2_TRIM="${read2_trim}"
41
42 #if int($read2_max_bases_to_write) > -1:
43 READ2_MAX_BASES_TO_WRITE="${read2_max_bases_to_write}"
44 #end if
45
46 INCLUDE_NON_PRIMARY_ALIGNMENTS="${include_non_primary_alignments}"
47
48
49 VALIDATION_STRINGENCY="${validation_stringency}"
50 QUIET=true
51 VERBOSITY=ERROR
52
53 </command>
54 <inputs>
55
56 <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"/>
57 <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"/>
58 <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"/>
59 <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"/>
60 <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"/>
61 <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"/>
62 <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"/>
63 <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"/>
64 <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)"/>
65 <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"/>
66 <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)"/>
67 <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"/>
68
69 <expand macro="VS" />
70
71 </inputs>
72
73 <outputs>
74 <!-- here dataset discovery is based on fact that if OUTPUT_PER_RG=true this tool automatically adds .fastq extension to emitted files -->
75 <data format="txt" name="report" label="SamToFastq run" hidden="true">
76 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.fastq" ext="fastqsanger" visible="true"/>
77 </data>
78 </outputs>
79
80 <tests>
81 <test>
82 <param name="inputFile" value="picard_SamToFastq.bam" ftype="bam"/>
83 <param name="output_per_rg" value="false"/>
84 <param name="re_reverse" value="true"/>
85 <param name="interleave" value="true"/>
86 <param name="include_non_pf_reads" value="false"/>
87 <param name="clipping_attribute" value="null" />
88 <param name="clipping_action" value="null" />
89 <param name="read1_trim" value="0" />
90 <param name="read1_max_bases_to_write" value="-1"/>
91 <param name="read2_trim" value="0" />
92 <param name="read2_max_bases_to_write" value="-1"/>
93 <param name="include_non_primary_alignments" value="false"/>
94 <output name="report">
95 <assert_contents>
96 <has_line line="BAM" />
97 </assert_contents>
98 <discovered_dataset designation="INTERLEAVED" file="picard_SamToFastq_test1.fq" ftype="fastqsanger"/>
99 </output>
100 </test>
101 </tests>
102
103 <stdio>
104 <exit_code range="1:" level="fatal"/>
105 </stdio>
106
107 <help>
108
109 **Purpose**
110
111 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.
112
113 -----
114
115 .. class:: warningmark
116
117 **DANGER: Multiple Outputs**
118
119 Generating per readgroup fastq (setting **OUTPUT_PER_RG** to True) may produce very large numbers of outputs. Know what you are doing!
120
121 @dataset_collections@
122
123 @description@
124
125 FASTQ=File
126 F=File Output fastq file (single-end fastq or, if paired, first end of the pair fastq).
127 Required. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG)
128
129 SECOND_END_FASTQ=File
130 F2=File Output fastq file (if paired, second end of the pair fastq). Default value: null.
131 Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG)
132
133 UNPAIRED_FASTQ=File
134 FU=File Output fastq file for unpaired reads; may only be provided in paired-fastq mode Default
135 value: null. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG)
136
137 OUTPUT_PER_RG=Boolean
138 OPRG=Boolean Output a fastq file per read group (two fastq files per read group if the group is
139 paired). Default value: false. Possible values: {true, false} Cannot be used in
140 conjuction with option(s) SECOND_END_FASTQ (F2) UNPAIRED_FASTQ (FU) FASTQ (F)
141
142 OUTPUT_DIR=File
143 ODIR=File Directory in which to output the fastq file(s). Used only when OUTPUT_PER_RG is true.
144 Default value: null.
145
146 RE_REVERSE=Boolean
147 RC=Boolean Re-reverse bases and qualities of reads with negative strand flag set before writing them
148 to fastq Default value: true. Possible values: {true, false}
149
150 INTERLEAVE=Boolean
151 INTER=Boolean Will generate an interleaved fastq if paired, each line will have /1 or /2 to describe
152 which end it came from Default value: false. Possible values: {true, false}
153
154 INCLUDE_NON_PF_READS=Boolean
155 NON_PF=Boolean Include non-PF reads from the SAM file into the output FASTQ files. PF means 'passes
156 filtering'. Reads whose 'not passing quality controls' flag is set are non-PF reads.
157 Default value: false. Possible values: {true, false}
158
159 CLIPPING_ATTRIBUTE=String
160 CLIP_ATTR=String The attribute that stores the position at which the SAM record should be clipped Default
161 value: null.
162
163 CLIPPING_ACTION=String
164 CLIP_ACT=String The action that should be taken with clipped reads: 'X' means the reads and qualities
165 should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in
166 the clipped region; and any integer means that the base qualities should be set to that
167 value in the clipped region. Default value: null.
168
169 READ1_TRIM=Integer
170 R1_TRIM=Integer The number of bases to trim from the beginning of read 1. Default value: 0.
171
172 READ1_MAX_BASES_TO_WRITE=Integer
173 R1_MAX_BASES=Integer The maximum number of bases to write from read 1 after trimming. If there are fewer than
174 this many bases left after trimming, all will be written. If this value is null then all
175 bases left after trimming will be written. Default value: null.
176
177 READ2_TRIM=Integer
178 R2_TRIM=Integer The number of bases to trim from the beginning of read 2. Default value: 0.
179
180 READ2_MAX_BASES_TO_WRITE=Integer
181 R2_MAX_BASES=Integer The maximum number of bases to write from read 2 after trimming. If there are fewer than
182 this many bases left after trimming, all will be written. If this value is null then all
183 bases left after trimming will be written. Default value: null.
184
185 INCLUDE_NON_PRIMARY_ALIGNMENTS=Boolean
186 If true, include non-primary alignments in the output. Support of non-primary alignments
187 in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and
188 there are paired reads with non-primary alignments. Default value: false.
189 Possible values: {true, false}
190
191 @more_info@
192
193 </help>
194 </tool>
195
196