# HG changeset patch # User devteam # Date 1420822098 18000 # Node ID 9315b97e25a43643349158ce57795c629f9724ab Uploaded diff -r 000000000000 -r 9315b97e25a4 bamtools-filter.xml --- /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 @@ + + BAM datasets on a variety of attributes + + bamtools + + + + 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 + + + + + + + + + + + + + + + + + + + + + + + + + + + + + ##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 + + + + + + + + + + + + + + + + +**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 + + + + + 10.1093/bioinformatics/btr174 + + diff -r 000000000000 -r 9315b97e25a4 images/complex-filters.png Binary file images/complex-filters.png has changed diff -r 000000000000 -r 9315b97e25a4 images/multiple-filters.png Binary file images/multiple-filters.png has changed diff -r 000000000000 -r 9315b97e25a4 images/rule.png Binary file images/rule.png has changed diff -r 000000000000 -r 9315b97e25a4 images/single-filter.png Binary file images/single-filter.png has changed diff -r 000000000000 -r 9315b97e25a4 shed_upload.tar.gz Binary file shed_upload.tar.gz has changed diff -r 000000000000 -r 9315b97e25a4 test-data/bamtools-input1.bam Binary file test-data/bamtools-input1.bam has changed diff -r 000000000000 -r 9315b97e25a4 test-data/bamtools-test1.bam Binary file test-data/bamtools-test1.bam has changed diff -r 000000000000 -r 9315b97e25a4 tool_dependencies.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_dependencies.xml Fri Jan 09 11:48:18 2015 -0500 @@ -0,0 +1,6 @@ + + + + + +