Mercurial > repos > devteam > bamtools_filter
diff bamtools-filter.xml @ 0:9315b97e25a4 draft
Uploaded
| author | devteam |
|---|---|
| date | Fri, 09 Jan 2015 11:48:18 -0500 |
| parents | |
| children | d64c7e752f4d |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bamtools-filter.xml Fri Jan 09 11:48:18 2015 -0500 @@ -0,0 +1,331 @@ +<tool id="bamFilter" name="Filter" version="0.0.1"> + <description>BAM datasets on a variety of attributes</description> + <requirements> + <requirement type="package" version="2.3.0_2d7685d2ae">bamtools</requirement> + </requirements> + <command> + + cat $script_file > $out_file2; + + #for $bam_count, $input_bam in enumerate( $input_bams ): + ln -s "${input_bam.input_bam}" "localbam_${bam_count}.bam" && + ln -s "${input_bam.input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" && + #end for + + bamtools + filter + -script $script_file + + #for $bam_count, $input_bam in enumerate( $input_bams ): + -in "localbam_${bam_count}.bam" + #end for + -out $out_file1 + + </command> + + <inputs> + <repeat name="input_bams" title="BAM dataset(s) to filter" min="1"> + <param name="input_bam" type="data" format="bam" label="BAM dataset" /> + </repeat> + <repeat name="conditions" title="Condition" min="1"> + <repeat name="filters" title="Filter" min="1"> + <conditional name="bam_property"> + <param name="bam_property_selector" type="select" label="Select BAM property to filter on"> + <option value="alignmentFlag"/> + <option value="cigar"/> + <option value="insertSize"/> + <option value="isDuplicate"/> + <option value="isFailedQC"/> + <option value="isFirstMate"/> + <option value="isMapped"/> + <option value="isMateMapped"/> + <option value="isMateReverseStrand"/> + <option value="isPaired"/> + <option value="isPrimaryAlignment"/> + <option value="isProperPair"/> + <option value="isReverseStrand"/> + <option value="isSecondMate"/> + <option selected="True" value="mapQuality"/> + <option value="matePosition"/> + <option value="mateReference"/> + <option value="name"/> + <option value="position"/> + <option value="queryBases"/> + <option value="reference"/> + <option value="tag"/> + </param> + <!-- would be fanstastic to have AND and OR constructs in when statements --> + <when value="alignmentFlag"> + <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"/> + </when> + <when value="cigar"> + <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"/> + </when> + <when value="insertSize"> + <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""> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> + </sanitizer> + </param> + </when> + <when value="isDuplicate"> + <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" /> + </when> + <when value="isFailedQC"> + <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Select reads failing QC" help="Checked = Failed QC, Empty = Passed QC"/> + </when> + <when value="isFirstMate"> + <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"/> + </when> + <when value="isMapped"> + <param name="bam_property_value" type="boolean" truevalue="true" falsevalue="false" label="Selected mapped reads" help="Checked = Mapped, Empty = NOT mapped"/> + </when> + <when value="isMateMapped"> + <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"/> + </when> + <when value="isMateReverseStrand"> + <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"/> + </when> + <when value="isPaired"> + <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"/> + </when> + <when value="isPrimaryAlignment"> + <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"/> + </when> + <when value="isProperPair"> + <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"/> + </when> + <when value="isReverseStrand"> + <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"/> + </when> + <when value="isSecondMate"> + <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"/> + </when> + <when value="mapQuality"> + <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""> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> + </sanitizer> + </param> + </when> + <when value="matePosition"> + <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""> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> + </sanitizer> + </param> + </when> + <when value="mateReference"> + <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""> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> + </sanitizer> + </param> + </when> + <when value="name"> + <param name="bam_property_value" type="text" label="Filter on read name" help="You can use = and ! (not) in your expression."> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> + </sanitizer> + </param> + </when> + <when value="position"> + <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""> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> + </sanitizer> + </param> + </when> + <when value="queryBases"> + <param name="bam_property_value" type="text" value="ttagggttagg" label="Filter on a sequence motif" help="You can use ! (not) in your expression"> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> + </sanitizer> + </param> + </when> + <when value="reference"> + <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"> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value="!="/></valid> + </sanitizer> + </param> + </when> + <when value="tag"> + <param name="bam_property_value" type="text" value="NM:>1" label="Filter on a particular tag" help="You can use >, <, =, and ! (not). + Tag name and its value must be separated by ":". E.g., to obtain reads with at least one mismatch use "NM:>1""> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"><add value=">"/><add value="<"/><add value=":!="/></valid> + </sanitizer> + </param> + </when> + </conditional> + </repeat> + </repeat> + <conditional name="rule_configuration"> + <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." /> + <when value="true"> + <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." > + <sanitizer invalid_char=""> + <valid initial="string.printable"/> + </sanitizer> + </param> + </when> + </conditional> + </inputs> + + <configfiles> + <configfile name="script_file"> + ##Sets up a json configfile for bamtools filter + ##If there is more than one condition prints brackets and "filters:" + #if len( $conditions ) > 1 + { + "filters": + [ + #end if + #for $i, $c in enumerate( $conditions, start=1 ) + { "id": "$i", + #for $j, $s in enumerate( $c.filters, start=1 ) + ##The if below takes care of the comma at the end of last condition within group + #if $j != len( $c.filters) + "${s.bam_property.bam_property_selector}":"${s.bam_property.bam_property_value}", + #else + "${s.bam_property.bam_property_selector}":"${s.bam_property.bam_property_value}" + #end if + #end for + ##The if below takes care of the comma at the end of last condition within group + #if $i != len( $conditions ) + }, + #else + } + #end if + #end for + #if len( $conditions ) > 1 + #if str( $rule_configuration.rules_selector ) == "True": + ], + "rule" : "${rule_configuration.rules}" + #else + ] + #end if + } + #end if + </configfile> + </configfiles> + + <outputs> + <data format="txt" name="out_file2" /> + <data format="bam" name="out_file1" /> + </outputs> + <tests> + <test> + <param name="input_bam" ftype="bam" value="bamtools-input1.bam"/> + <param name="bam_property_selector" value="mapQuality"/> + <param name="bam_property_value" value=">20"/> + <output name="out_file1" file="bamtools-test1.bam" ftype="bam"/> + </test> + </tests> +<help> +**What is does** + +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). + +----- + +**How it works** + +The tool use logic relies on the three concepts: (1) input BAM, (2) groups, and (3) filters. + +*Input BAM(s)* + +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** + +*Conditions and Filters* + +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. + +----- + +**Example 1. Using a single filter** + +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). +For example, for retaining reads with mapping quality of at least 20 one would set the tool interface as shown below: + +.. image:: ${static_path}/images/simple-filter.png + +----- + +**Example 2. Using multiple filters** + +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. +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): + +.. image:: ${static_path}/images/multiple-filters.png + +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. +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. + +----- + +**Example 3. Complex filtering with multiple conditions** + +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*) +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*. +The following screenshot expalins how this can be done: + +.. image:: ${static_path}/images/complex-filters.png + +----- + +**Example 4. Even more complex filtering with Rules** + +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. +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 +filtering will look like this:: + + !(1) & (2 | 3) + +Here, numbers 1, 2, and 3 represent conditions. The following screenshot illustrates how to do this in Galaxy: + +.. image:: ${static_path}/images/rule.png + +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. +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:: + + NOT condition 1 AND (condition 2 OR condition 3) + +----- + +**JSON script file** + +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. +For instance, the example 4 looks like this in the JSON form:: + + { + "filters": + [ + { "id": "1", + "tag":"NM:=0", + "isReverseStrand":"false" + }, + { "id": "2", + "tag":"NM:>0", + "isReverseStrand":"true" + } + ] + } + + + +----- + +**More information** + +.. class:: infomark + +Additional information about BAMtools can be found at https://github.com/pezmaster31/bamtools/wiki + + +</help> + <citations> + <citation type="doi">10.1093/bioinformatics/btr174</citation> + </citations> +</tool>