Mercurial > repos > devteam > bamtools_filter
annotate bamtools-filter.xml @ 5:23a1c1f66b47 draft
planemo upload commit 5ad726dc73203a704666033cd3bf70b82575978f-dirty
author | devteam |
---|---|
date | Wed, 26 Aug 2015 15:12:16 -0400 |
parents | baca6d3e27af |
children | 709d8669e8d6 |
rev | line source |
---|---|
0 | 1 <tool id="bamFilter" name="Filter" version="0.0.1"> |
2 <description>BAM datasets on a variety of attributes</description> | |
3 <requirements> | |
4 <requirement type="package" version="2.3.0_2d7685d2ae">bamtools</requirement> | |
5 </requirements> | |
6 <command> | |
1
5e2fe70292a7
planemo upload commit 5ad726dc73203a704666033cd3bf70b82575978f-dirty
devteam
parents:
0
diff
changeset
|
7 cat $script_file > $out_file2; |
0 | 8 |
9 #for $bam_count, $input_bam in enumerate( $input_bams ): | |
10 ln -s "${input_bam.input_bam}" "localbam_${bam_count}.bam" && | |
11 ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" && | |
12 #end for | |
13 | |
14 bamtools | |
15 filter | |
16 -script $script_file | |
17 | |
18 #for $bam_count, $input_bam in enumerate( $input_bams ): | |
19 -in "localbam_${bam_count}.bam" | |
20 #end for | |
21 -out $out_file1 | |
22 </command> | |
23 <inputs> | |
24 <repeat name="input_bams" title="BAM dataset(s) to filter" min="1"> | |
25 <param name="input_bam" type="data" format="bam" label="BAM dataset" /> | |
26 </repeat> | |
27 <repeat name="conditions" title="Condition" min="1"> | |
28 <repeat name="filters" title="Filter" min="1"> | |
29 <conditional name="bam_property"> | |
30 <param name="bam_property_selector" type="select" label="Select BAM property to filter on"> | |
31 <option value="alignmentFlag"/> | |
32 <option value="cigar"/> | |
33 <option value="insertSize"/> | |
34 <option value="isDuplicate"/> | |
35 <option value="isFailedQC"/> | |
36 <option value="isFirstMate"/> | |
37 <option value="isMapped"/> | |
38 <option value="isMateMapped"/> | |
39 <option value="isMateReverseStrand"/> | |
40 <option value="isPaired"/> | |
41 <option value="isPrimaryAlignment"/> | |
42 <option value="isProperPair"/> | |
43 <option value="isReverseStrand"/> | |
44 <option value="isSecondMate"/> | |
45 <option selected="True" value="mapQuality"/> | |
46 <option value="matePosition"/> | |
47 <option value="mateReference"/> | |
48 <option value="name"/> | |
49 <option value="position"/> | |
50 <option value="queryBases"/> | |
51 <option value="reference"/> | |
52 <option value="tag"/> | |
53 </param> | |
54 <!-- would be fanstastic to have AND and OR constructs in when statements --> | |
55 <when value="alignmentFlag"> | |
56 <param name="bam_property_value" type="integer" value="3" label="Filter on this alignment flag" help="Default (3) is for a paired read mapped in a proper pair"/> | |
57 </when> | |
58 <when value="cigar"> | |
59 <param name="bam_property_value" type="text" size="10" value="101M" label="Filter on this CIGAR string" help="Default (101M) is for 101 continuously matched bases"/> | |
60 </when> | |
61 <when value="insertSize"> | |
62 <param name="bam_property_value" type="text" size="10" value=">=250" label="Filter on inster size" help="You can use >, <, =, and ! (not) in your expression. E.g., to select pairs with inster size above 250 nt use ">=250""> | |
63 <sanitizer invalid_char=""> | |
64 <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> | |
65 </sanitizer> | |
66 </param> | |
67 </when> | |
68 <when value="isDuplicate"> | |
69 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select reads makwed as duplicates" help="Checked = Read IS Duplicate, Empty = Read is NOT Duplicate" /> | |
70 </when> | |
71 <when value="isFailedQC"> | |
72 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select reads failing QC" help="Checked = Failed QC, Empty = Passed QC"/> | |
73 </when> | |
74 <when value="isFirstMate"> | |
75 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select first mate in a read pair" help="Checked = is first mate, Empty = is NOT first mate"/> | |
76 </when> | |
77 <when value="isMapped"> | |
78 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Selected mapped reads" help="Checked = Mapped, Empty = NOT mapped"/> | |
79 </when> | |
80 <when value="isMateMapped"> | |
81 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select reads with mapped mate" help="Checked = Mate IS mapped Empty = Mate is NOT mapped"/> | |
82 </when> | |
83 <when value="isMateReverseStrand"> | |
84 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select reads with mate on the reverse strand" help="Checked = Mate IS on reverse strand, Empty = Mate is NOT on the reverse strand"/> | |
85 </when> | |
86 <when value="isPaired"> | |
87 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select paired reads" help="Checked = Read IS paired, Empty = Read is NOT paired"/> | |
88 </when> | |
89 <when value="isPrimaryAlignment"> | |
90 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select BAM records for primary alignments" help="Checked = Alignment IS primary, Empty = Alignment is NOT primary"/> | |
91 </when> | |
92 <when value="isProperPair"> | |
93 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select properly paired reads" help="Checked = Read IS in proper pair, Empty = Read is NOT in the proper pair"/> | |
94 </when> | |
95 <when value="isReverseStrand"> | |
96 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select reads in the reverse strand only" help="Checked = Read IS on the reverse strand, Empty = Read is NOT on the reverse strand"/> | |
97 </when> | |
98 <when value="isSecondMate"> | |
99 <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select second mate in a read pair" help="Checked = Read IS second mate, Empty = Read is NOT second mate"/> | |
100 </when> | |
101 <when value="mapQuality"> | |
102 <param name="bam_property_value" type="text" value="20" label="Filter on read mapping quality (phred scale)" help="You can use >, <, =, and ! (not) in your expression. E.g., to select reads with mapping quality of at least 30 use ">=30""> | |
103 <sanitizer invalid_char=""> | |
104 <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> | |
105 </sanitizer> | |
106 </param> | |
107 </when> | |
108 <when value="matePosition"> | |
109 <param name="bam_property_value" type="text" value="1000000" label="Filter on the position of the mate" help="You can use >, <, =, and ! (not) in your expression. E.g., to select reads with mate (second end) mapping after position 1,000,000 use ">1000000""> | |
110 <sanitizer invalid_char=""> | |
111 <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> | |
112 </sanitizer> | |
113 </param> | |
114 </when> | |
115 <when value="mateReference"> | |
116 <param name="bam_property_value" type="text" value="chr22" label="Filter on reference name for the mate" help="You can use = and ! (not) in your expression. E.g., to select reads with mates mapping to chrM use "chr22""> | |
117 <sanitizer invalid_char=""> | |
118 <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> | |
119 </sanitizer> | |
120 </param> | |
121 </when> | |
122 <when value="name"> | |
123 <param name="bam_property_value" type="text" label="Filter on read name" help="You can use = and ! (not) in your expression."> | |
124 <sanitizer invalid_char=""> | |
125 <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> | |
126 </sanitizer> | |
127 </param> | |
128 </when> | |
129 <when value="position"> | |
130 <param name="bam_property_value" type="text" value="500000" label="Filter on the position of the read" help="You can use >, <, =, and ! (not) in your expression. E.g., to select reads mapping after position 5,000 use ">5000""> | |
131 <sanitizer invalid_char=""> | |
132 <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> | |
133 </sanitizer> | |
134 </param> | |
135 </when> | |
136 <when value="queryBases"> | |
137 <param name="bam_property_value" type="text" value="ttagggttagg" label="Filter on a sequence motif" help="You can use ! (not) in your expression"> | |
138 <sanitizer invalid_char=""> | |
139 <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> | |
140 </sanitizer> | |
141 </param> | |
142 </when> | |
143 <when value="reference"> | |
144 <param name="bam_property_value" type="text" value="chr22" label="Filter on the reference name for the read" help="You can use ! (not) in your expression"> | |
145 <sanitizer invalid_char=""> | |
146 <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> | |
147 </sanitizer> | |
148 </param> | |
149 </when> | |
150 <when value="tag"> | |
151 <param name="bam_property_value" type="text" value="NM:>1" label="Filter on a particular tag" help="You can use >, <, =, and ! (not). | |
152 Tag name and its value must be separated by ":". E.g., to obtain reads with at least one mismatch use "NM:>1""> | |
153 <sanitizer invalid_char=""> | |
154 <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value=":!="/></valid> | |
155 </sanitizer> | |
156 </param> | |
157 </when> | |
158 </conditional> | |
159 </repeat> | |
160 </repeat> | |
161 <conditional name="rule_configuration"> | |
162 <param name="rules_selector" type="boolean" truevalue="true" falsevalue="false" label="Would you like to set rules?" help="Allows complex logical constructs. See Example 4 below." /> | |
163 <when value="true"> | |
164 <param name="rules" type="text" size="20" label="Enter rules here" help="This option can only be used with at least two conditions. Read help below (Example 4) to understand how it works." > | |
165 <sanitizer invalid_char=""> | |
166 <valid initial="string.printable"/> | |
167 </sanitizer> | |
168 </param> | |
169 </when> | |
170 </conditional> | |
171 </inputs> | |
172 | |
173 <configfiles> | |
174 <configfile name="script_file"> | |
175 ##Sets up a json configfile for bamtools filter | |
176 ##If there is more than one condition prints brackets and "filters:" | |
177 #if len( $conditions ) > 1 | |
178 { | |
179 "filters": | |
180 [ | |
181 #end if | |
182 #for $i, $c in enumerate( $conditions, start=1 ) | |
183 { "id": "$i", | |
184 #for $j, $s in enumerate( $c.filters, start=1 ) | |
185 ##The if below takes care of the comma at the end of last condition within group | |
186 #if $j != len( $c.filters) | |
187 "${s.bam_property.bam_property_selector}":"${s.bam_property.bam_property_value}", | |
188 #else | |
189 "${s.bam_property.bam_property_selector}":"${s.bam_property.bam_property_value}" | |
190 #end if | |
191 #end for | |
192 ##The if below takes care of the comma at the end of last condition within group | |
193 #if $i != len( $conditions ) | |
194 }, | |
195 #else | |
196 } | |
1
5e2fe70292a7
planemo upload commit 5ad726dc73203a704666033cd3bf70b82575978f-dirty
devteam
parents:
0
diff
changeset
|
197 #end if |
5e2fe70292a7
planemo upload commit 5ad726dc73203a704666033cd3bf70b82575978f-dirty
devteam
parents:
0
diff
changeset
|
198 #end for |
0 | 199 #if len( $conditions ) > 1 |
200 #if str( $rule_configuration.rules_selector ) == "True": | |
201 ], | |
202 "rule" : "${rule_configuration.rules}" | |
203 #else | |
204 ] | |
205 #end if | |
206 } | |
207 #end if | |
208 </configfile> | |
209 </configfiles> | |
210 | |
211 <outputs> | |
212 <data format="txt" name="out_file2" /> | |
213 <data format="bam" name="out_file1" /> | |
214 </outputs> | |
215 <tests> | |
216 <test> | |
217 <param name="input_bam" ftype="bam" value="bamtools-input1.bam"/> | |
218 <param name="bam_property_selector" value="mapQuality"/> | |
219 <param name="bam_property_value" value=">20"/> | |
220 <output name="out_file1" file="bamtools-test1.bam" ftype="bam"/> | |
221 </test> | |
222 </tests> | |
223 <help> | |
224 **What is does** | |
225 | |
226 BAMTools filter is a very powerful utility to perform complex filtering of BAM files. It is based on BAMtools suite of tools by Derek Barnett (https://github.com/pezmaster31/bamtools). | |
227 | |
228 ----- | |
229 | |
230 **How it works** | |
231 | |
232 The tool use logic relies on the three concepts: (1) input BAM, (2) groups, and (3) filters. | |
233 | |
234 *Input BAM(s)* | |
235 | |
236 The input BAM is self-explanatory. This is the dataset you will be filtering. The tool can accept just one or multiple BAM files. To filter on multiple BAMs just add them by clicking **Add new BAM dataset(s) to filter** | |
237 | |
238 *Conditions and Filters* | |
239 | |
240 Conditions for filtering BAM files can be arranged in **Groups and Filters**. While it can be confusing at first this is what gives ultimate power to this tools. So try to look at the examples we are supplying below. | |
241 | |
242 ----- | |
243 | |
244 **Example 1. Using a single filter** | |
245 | |
246 When filtering on a single condition there is no need to worry about filters and conditions. Just choose a filter from the **Select BAM property to filter on:** dropdown and enter a value (or click a checkbox for binary filters). | |
247 For example, for retaining reads with mapping quality of at least 20 one would set the tool interface as shown below: | |
248 | |
5
23a1c1f66b47
planemo upload commit 5ad726dc73203a704666033cd3bf70b82575978f-dirty
devteam
parents:
4
diff
changeset
|
249 .. image:: single-filter.png |
0 | 250 |
251 ----- | |
252 | |
253 **Example 2. Using multiple filters** | |
254 | |
255 Now suppose one needs to extract reads that (1) have mapping quality of at least 20, (2) contain at least 1 mismatch, and (3) are mapping onto forward strand only. | |
256 To do so we will use three filters as shown below (multiple filters are added to the interface by clicking on the **Add new Filter** button): | |
257 | |
5
23a1c1f66b47
planemo upload commit 5ad726dc73203a704666033cd3bf70b82575978f-dirty
devteam
parents:
4
diff
changeset
|
258 .. image:: multiple-filters.png |
0 | 259 |
260 In this case (you can see that the three filters are grouped within a single Condition - **Condition 1**) the filter too use logical **AND** to perform filtering. | |
261 In other words only reads that (1) have mapping quality of at least 20 **AND** (2) contain at least 1 mismatch **AND** are mapping onto forward strand will be returned in this example. | |
262 | |
263 ----- | |
264 | |
265 **Example 3. Complex filtering with multiple conditions** | |
266 | |
267 Suppose now you would like to select **either** reads that (**1**) have (*1.1*) no mismatches and (*1.2*) are on the forward strand **OR** (**2**) reads that have (*2.1*) | |
268 at least one mismatch and (*2.2*) are on the reverse strand. In this scenario we have to set up two conditions: (**1**) and (**2**) each with two filters: *1.1* and *1.2* as well as *2.1* and *2.2*. | |
269 The following screenshot expalins how this can be done: | |
270 | |
5
23a1c1f66b47
planemo upload commit 5ad726dc73203a704666033cd3bf70b82575978f-dirty
devteam
parents:
4
diff
changeset
|
271 .. image:: complex-filters.png |
0 | 272 |
273 ----- | |
274 | |
275 **Example 4. Even more complex filtering with Rules** | |
276 | |
277 In the above example we have used two conditions (Condition 1 and Condition 2). Using multiple conditions allows to combine them and a variety of ways to enable even more powerful filtering. | |
278 For example, suppose get all reads that (**1**) do NOT map to mitochondria and either (**2**) have mapping quality over 20, or (**3**) are in properly mapped pairs. The logical rule to enable such | |
279 filtering will look like this:: | |
280 | |
281 !(1) & (2 | 3) | |
282 | |
283 Here, numbers 1, 2, and 3 represent conditions. The following screenshot illustrates how to do this in Galaxy: | |
284 | |
5
23a1c1f66b47
planemo upload commit 5ad726dc73203a704666033cd3bf70b82575978f-dirty
devteam
parents:
4
diff
changeset
|
285 .. image:: rule.png |
0 | 286 |
287 There are three conditions here, each with a single filter. A text entry area that can be opened by clicking on the **Would you like to set rules?** checkbox enables you to enter a rule. | |
288 Here numbers correspond to numbers of conditions as they are shown in the interface. E.g., 1 corresponds to condition 1, 2 to condition 2 and so on... In human language this means:: | |
289 | |
290 NOT condition 1 AND (condition 2 OR condition 3) | |
291 | |
292 ----- | |
293 | |
294 **JSON script file** | |
295 | |
296 This tool produces two outputs. One of the them is a BAM file containing filtered reads. The other is a JSONified script. It can help you to see how your instructions are sent to BAMTools. | |
297 For instance, the example 4 looks like this in the JSON form:: | |
298 | |
299 { | |
300 "filters": | |
301 [ | |
302 { "id": "1", | |
303 "tag":"NM:=0", | |
304 "isReverseStrand":"false" | |
305 }, | |
306 { "id": "2", | |
307 "tag":"NM:>0", | |
308 "isReverseStrand":"true" | |
309 } | |
310 ] | |
311 } | |
1
5e2fe70292a7
planemo upload commit 5ad726dc73203a704666033cd3bf70b82575978f-dirty
devteam
parents:
0
diff
changeset
|
312 |
0 | 313 |
314 ----- | |
315 | |
316 **More information** | |
317 | |
318 .. class:: infomark | |
319 | |
320 Additional information about BAMtools can be found at https://github.com/pezmaster31/bamtools/wiki | |
321 | |
322 | |
323 </help> | |
324 <citations> | |
325 <citation type="doi">10.1093/bioinformatics/btr174</citation> | |
326 </citations> | |
327 </tool> |