Mercurial > repos > devteam > samtool_filter2

comparison samtool_filter2.xml @ 1:94d5786febc4 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 4381f4022eca6f3c58ae1d01096795cd28c15062
author devteam
date Mon, 10 Aug 2015 17:14:37 -0400
parents 2d4ae2f8231e
children 886b73f04847
comparison
equal deleted inserted replaced
0:2d4ae2f8231e 1:94d5786febc4
1 <tool id="samtool_filter2" name="Filter SAM or BAM, output SAM or BAM" version="1.1.1"> 1 <tool id="samtool_filter2" name="Filter SAM or BAM, output SAM or BAM" version="1.1.1">
2 <description>files on FLAG MAPQ RG LN or by region</description> 2 <description>files on FLAG MAPQ RG LN or by region</description>
3 <requirements> 3 <requirements>
4 <requirement type="package" version="0.1.18">samtools</requirement> 4 <requirement type="package" version="0.1.18">samtools</requirement>
5 </requirements> 5 </requirements>
6 <!-- 6 <stdio>
7 samtools view [-bchuHS] [-t in.refList] [-o output] [-f reqFlag] [-F skipFlag] [-q minMapQ] [-l library] [-r readGroup] [-R rgFile] <in.bam>|<in.sam> [region1 [...]] 7 <exit_code range="1:" />
8 Usage: samtools view [options] <in.bam>|<in.sam> [region1 [...]] 8 </stdio>
9
10 Options: -b output BAM
11 -h print header for the SAM output
12 -H print header only (no alignments)
13 -S input is SAM
14 -u uncompressed BAM output (force -b)
15 -1 fast compression (force -b)
16 -x output FLAG in HEX (samtools-C specific)
17 -X output FLAG in string (samtools-C specific)
18 -c print only the count of matching records
19 -L FILE output alignments overlapping the input BED FILE [null]
20 -t FILE list of reference names and lengths (force -S) [null]
21 -T FILE reference sequence file (force -S) [null]
22 -o FILE output file name [stdout]
23 -R FILE list of read groups to be outputted [null]
24 -f INT required flag, 0 for unset [0]
25 -F INT filtering flag, 0 for unset [0]
26 -q INT minimum mapping quality [0]
27 -l STR only output reads in library STR [null]
28 -r STR only output reads in read group STR [null]
29 -? longer help
30 -->
31 <command> 9 <command>
10 <![CDATA[
32 ##set up input files, regions requires input.bam and input.bai 11 ##set up input files, regions requires input.bam and input.bai
33 #if isinstance($input1.datatype, $__app__.datatypes_registry.get_datatype_by_extension('bam').__class__): 12 #if isinstance($input1.datatype, $__app__.datatypes_registry.get_datatype_by_extension('bam').__class__):
34 #set $input = 'input.bam' 13 #set $input = 'input.bam'
35 ln -s $input1 $input &amp;&amp; 14 ln -s "$input1" $input &&
36 ln -s $input1.metadata.bam_index input.bai &amp;&amp; 15 ln -s "$input1.metadata.bam_index" input.bai &&
37 #elif isinstance($input1.datatype, $__app__.datatypes_registry.get_datatype_by_extension('sam').__class__): 16 #elif isinstance($input1.datatype, $__app__.datatypes_registry.get_datatype_by_extension('sam').__class__):
38 #set $input = 'input.sam' 17 #set $input = 'input.sam'
39 ln -s $input1 $input &amp;&amp; 18 ln -s "$input1" $input &&
40 #end if 19 #end if
41 samtools view -o "$output1" $header 20 samtools view -o "$output1" $header
42 21
43 #if $input1.datatype.file_ext == 'sam': 22 #if $input1.datatype.file_ext == 'sam':
44 -S 23 -S
45 #end if 24 #end if
46 25
47 #if $outputtype.__str__ == "bam": 26 #if $outputtype.__str__ == "bam":
48 -b 27 -b
49 #end if 28 #end if
50 29
51
52 #if $mapq.__str__ != '': 30 #if $mapq.__str__ != '':
53 -q $mapq 31 -q $mapq
54 #end if 32 #end if
55 #if $flag.filter.__str__ == 'yes': 33 #if $flag.filter.__str__ == 'yes':
56 #if $flag.reqBits.__str__ != 'None': 34 #if $flag.reqBits.__str__ != 'None':
57 #set $reqs = $flag.reqBits.__str__.split(',') 35 #set $reqs = $flag.reqBits.__str__.split(',')
58 #set $reqFlag = 0 36 #set $reqFlag = 0
59 #for $xn in $reqs: 37 #for $xn in $reqs:
60 #set $reqFlag += int(xn,16) 38 #set $reqFlag += int(xn,16)
61 #end for 39 #end for
62 -f $hex($reqFlag) 40 -f $hex($reqFlag)
63 #end if 41 #end if
64 #if $flag.skipBits.__str__ != 'None': 42 #if $flag.skipBits.__str__ != 'None':
65 #set $skips = $flag.skipBits.__str__.split(',') 43 #set $skips = $flag.skipBits.__str__.split(',')
66 #set $skipFlag = 0 44 #set $skipFlag = 0
67 #for $xn in $skips: 45 #for $xn in $skips:
68 #set $skipFlag += int(xn,16) 46 #set $skipFlag += int(xn,16)
69 #end for 47 #end for
70 -F $hex($skipFlag) 48 -F $hex($skipFlag)
75 #end if 53 #end if
76 #if $library.__str__.strip() != '': 54 #if $library.__str__.strip() != '':
77 -l $library 55 -l $library
78 #end if 56 #end if
79 #if $bed_file.__str__ != "None" and len($bed_file.__str__) > 0: 57 #if $bed_file.__str__ != "None" and len($bed_file.__str__) > 0:
80 -L $bed_file 58 -L "$bed_file"
81 #end if 59 #end if
82 $input 60 $input
83 #if $regions.__str__.strip() != '' and $input1.datatype.file_ext == 'bam': 61 #if $regions.__str__.strip() != '' and $input1.datatype.file_ext == 'bam':
84 $regions.__str__.strip() 62 $regions.__str__.strip()
85 #end if 63 #end if
86 ## need to redirect stderr message so galaxy does not think this failed 64 ## need to redirect stderr message so galaxy does not think this failed
87 2>&amp;1 65 2>&1
66 ]]>
88 </command> 67 </command>
89 <inputs> 68 <inputs>
90 <param name="input1" type="data" format="sam,bam" label="SAM or BAM File to Filter" /> 69 <param name="input1" type="data" format="sam,bam" label="SAM or BAM file to filter" />
91 <param name="header" type="select" label="Header in output"> 70 <param name="header" type="select" label="Header in output">
92 <option value="-h">Include Header</option> 71 <option value="-h">Include Header</option>
93 <option value="">Exclude Header</option> 72 <option value="">Exclude Header</option>
94 <option value="-H">Only the Header</option> 73 <option value="-H">Only the Header</option>
95 </param> 74 </param>
96 <param name="mapq" type="integer" value="" optional="true" label="Minimum MAPQ quality score"> 75 <param name="mapq" type="integer" value="" optional="true" label="Minimum MAPQ quality score" help="(-q)">
97 <validator type="in_range" message="The MAPQ quality score can't be negative" min="0"/> 76 <validator type="in_range" message="The MAPQ quality score can't be negative" min="0"/>
98 </param> 77 </param>
99 <conditional name="flag"> 78 <conditional name="flag">
100 <param name="filter" type="select" label="Filter on bitwise flag"> 79 <param name="filter" type="select" label="Filter on bitwise flag">
101 <option value="no">no</option> 80 <option value="no">no</option>
102 <option value="yes">yes</option> 81 <option value="yes">yes</option>
103 </param> 82 </param>
104 <when value="no"/> 83 <when value="no"/>
105 <when value="yes"> 84 <when value="yes">
106 <param name="reqBits" type="select" multiple="true" display="checkboxes" label="Only output alignments with all of these flag bits set" > 85 <param name="reqBits" type="select" multiple="true" display="checkboxes" label="Only output alignments with all of these flag bits set" help="(-f)">
107 <option value="0x0001">Read is paired</option> 86 <option value="0x0001">Read is paired</option>
108 <option value="0x0002">Read is mapped in a proper pair</option> 87 <option value="0x0002">Read is mapped in a proper pair</option>
109 <option value="0x0004">The read is unmapped</option> 88 <option value="0x0004">The read is unmapped</option>
110 <option value="0x0008">The mate is unmapped</option> 89 <option value="0x0008">The mate is unmapped</option>
111 <option value="0x0010">Read strand</option> 90 <option value="0x0010">Read strand</option>
114 <option value="0x0080">Read is the second in a pair</option> 93 <option value="0x0080">Read is the second in a pair</option>
115 <option value="0x0100">The alignment or this read is not primary</option> 94 <option value="0x0100">The alignment or this read is not primary</option>
116 <option value="0x0200">The read fails platform/vendor quality checks</option> 95 <option value="0x0200">The read fails platform/vendor quality checks</option>
117 <option value="0x0400">The read is a PCR or optical duplicate</option> 96 <option value="0x0400">The read is a PCR or optical duplicate</option>
118 </param> 97 </param>
119 <param name="skipBits" type="select" multiple="true" display="checkboxes" label="Skip alignments with any of these flag bits set" > 98 <param name="skipBits" type="select" multiple="true" display="checkboxes" label="Skip alignments with any of these flag bits set" help="(-F)">
120 <option value="0x0001">Read is paired</option> 99 <option value="0x0001">Read is paired</option>
121 <option value="0x0002">Read is mapped in a proper pair</option> 100 <option value="0x0002">Read is mapped in a proper pair</option>
122 <option value="0x0004">The read is unmapped</option> 101 <option value="0x0004">The read is unmapped</option>
123 <option value="0x0008">The mate is unmapped</option> 102 <option value="0x0008">The mate is unmapped</option>
124 <option value="0x0010">Read strand</option> 103 <option value="0x0010">Read strand</option>
130 <option value="0x0400">The read is a PCR or optical duplicate</option> 109 <option value="0x0400">The read is a PCR or optical duplicate</option>
131 </param> 110 </param>
132 </when> 111 </when>
133 </conditional> 112 </conditional>
134 <param name="library" type="text" value="" size="20" label="Select alignments from Library" 113 <param name="library" type="text" value="" size="20" label="Select alignments from Library"
135 help="Requires headers in the input SAM or BAM, otherwise no alignments will be output."/> 114 help="(-l) Requires headers in the input SAM or BAM, otherwise no alignments will be output"/>
136 <param name="read_group" type="text" value="" size="20" label="Select alignments from Read Group" 115 <param name="read_group" type="text" value="" size="20" label="Select alignments from Read Group"
137 help="Requires headers in the input SAM or BAM, otherwise no alignments will be output."/> 116 help="(-r) Requires headers in the input SAM or BAM, otherwise no alignments will be output"/>
138 <param name="bed_file" type="data" format="bed" optional="true" label="Output alignments overlapping the regions in the BED FILE"/> 117 <param name="bed_file" type="data" format="bed" optional="true" label="Output alignments overlapping the regions in the BED FILE" help="(-L)"/>
139 <param name="regions" type="text" value="" size="180" label="Select regions (only used when the input is in BAM format)" 118 <param name="regions" type="text" value="" size="180" label="Select regions (only used when the input is in BAM format)"
140 help="region should be presented in one of the following formats: `chr1', `chr2:1,000' and `chr3:1000-2,000'"/> 119 help="region should be presented in one of the following formats: `chr1', `chr2:1,000' and `chr3:1000-2,000'"/>
141 <param name="outputtype" type="select" label="Select the output format"> 120 <param name="outputtype" type="select" label="Select the output format">
142 <option value="bam">bam</option> 121 <option value="bam">BAM (-b)</option>
143 <option value="sam">sam</option> 122 <option value="sam">SAM</option>
144 </param> 123 </param>
145 </inputs> 124 </inputs>
146 <outputs> 125 <outputs>
147 <data name="output1" format_source="input1" label="${tool.name} on ${on_string}: ${input1.datatype.file_ext}"> 126 <data name="output1" format="sam" label="${tool.name} on ${on_string}: ${outputtype}">
148 <change_format> 127 <change_format>
149 <when input="outputtype" value="bam" format="bam" /> 128 <when input="outputtype" value="bam" format="bam" />
150 </change_format> 129 </change_format>
151 </data> 130 </data>
152 </outputs> 131 </outputs>
155 <param name="input1" value="bam_to_sam_in2.sam" ftype="sam" /> 134 <param name="input1" value="bam_to_sam_in2.sam" ftype="sam" />
156 <param name="header" value=""/> 135 <param name="header" value=""/>
157 <param name="filter" value="yes"/> 136 <param name="filter" value="yes"/>
158 <param name="reqBits" value="0x0080"/> 137 <param name="reqBits" value="0x0080"/>
159 <param name="outputtype" value="sam"/> 138 <param name="outputtype" value="sam"/>
160 <output name="output1" > 139 <output name="output1">
161 <assert_contents> 140 <assert_contents>
162 <has_text text="141" /> 141 <has_text text="141" />
163 <not_has_text text="77" /> 142 <not_has_text text="77" />
164 </assert_contents> 143 </assert_contents>
165 </output> 144 </output>
166 </test> 145 </test>
167 <test> 146 <test>
168 <param name="input1" value="bam_to_sam_in2.sam" ftype="sam" /> 147 <param name="input1" value="bam_to_sam_in2.sam" ftype="sam" />
169 <param name="header" value=""/> 148 <param name="header" value=""/>
170 <param name="filter" value="no"/> 149 <param name="filter" value="no"/>
171 <param name="read_group" value="rg1"/> 150 <param name="read_group" value="rg1"/>
172 <param name="outputtype" value="sam"/> 151 <param name="outputtype" value="sam"/>
173 <output name="output1" > 152 <output name="output1">
174 <assert_contents> 153 <assert_contents>
175 <has_text text="rg1" /> 154 <has_text text="rg1" />
176 <not_has_text text="rg2" /> 155 <not_has_text text="rg2" />
177 </assert_contents> 156 </assert_contents>
178 </output> 157 </output>
179 </test> 158 </test>
180 <test> 159 <test>
181 <param name="input1" value="bam_to_sam_in1.sam" ftype="sam" /> 160 <param name="input1" value="bam_to_sam_in1.sam" ftype="sam" />
182 <param name="header" value=""/> 161 <param name="header" value=""/>
183 <param name="filter" value="yes"/> 162 <param name="filter" value="yes"/>
184 <param name="skipBits" value="0x0008"/> 163 <param name="skipBits" value="0x0008"/>
185 <param name="mapq" value="250"/> 164 <param name="mapq" value="250"/>
186 <param name="outputtype" value="sam"/> 165 <param name="outputtype" value="sam"/>
187 <output name="output1" > 166 <output name="output1">
188 <assert_contents> 167 <assert_contents>
189 <has_text text="both_reads_align_clip_marked" /> 168 <has_text text="both_reads_align_clip_marked" />
190 <not_has_text text="both_reads_present_only_first_aligns" /> 169 <not_has_text text="both_reads_present_only_first_aligns" />
191 </assert_contents> 170 </assert_contents>
192 </output> 171 </output>
193 </test> 172 </test>
194 </tests> 173 </tests>
195 <help> 174 <help>
196
197
198 **What it does** 175 **What it does**
199 176
200 This tool uses the samtools view command in SAMTools_ toolkit to filter a SAM or BAM file on the MAPQ (mapping quality), FLAG bits, Read Group, Library, or region. 177 This tool uses the samtools view command in SAMtools_ toolkit to filter a SAM or BAM file on the MAPQ (mapping quality), FLAG bits, Read Group, Library, or region.
201 178
202 **Input** 179 **Input**
203 180
204 Input is either a SAM or BAM file. 181 Input is either a SAM or BAM file.
205 182
207 184
208 The output file will be SAM or BAM (depending on the chosen option), filtered by the selected options. 185 The output file will be SAM or BAM (depending on the chosen option), filtered by the selected options.
209 186
210 **Options** 187 **Options**
211 188
212 Filtering by read group or library requires headers in the input SAM or BAM file. 189 Filtering by read group or library requires headers in the input SAM or BAM file.
213 190
214 If regions are specified, only alignments overlapping the specified regions will be output. An alignment may be given multiple times if it is overlapping several regions. 191 If regions are specified, only alignments overlapping the specified regions will be output. An alignment may be given multiple times if it is overlapping several regions.
215 A region can be presented, for example, in the following format:: 192 A region can be presented, for example, in the following format::
216 193
217 chr2 (the whole chr2) 194 chr2 (the whole chr2)
218 chr2:1000000 (region starting from 1,000,000bp) 195 chr2:1000000 (region starting from 1,000,000bp)
219 chr2:1,000,000-2,000,000 (region between 1,000,000 and 2,000,000bp including the end points). 196 chr2:1,000,000-2,000,000 (region between 1,000,000 and 2,000,000bp including the end points).
220 197
221 Note: The coordinate is 1-based. 198 Note: The coordinate is 1-based.
222 199
223 Multiple regions may be specified, separated by a space character:: 200 Multiple regions may be specified, separated by a space character::
224 201
225 chr2:1000000-2000000 chr2:1,000,000-2,000,000 chrX 202 chr2:1000000-2000000 chr2:1,000,000-2,000,000 chrX
226 203
227 204
228 205
229 .. _SAMTools: http://samtools.sourceforge.net/samtools.shtml 206 .. _SAMtools: http://samtools.sourceforge.net/
230 207
231 </help> 208 </help>
232 </tool> 209 </tool>