Mercurial > repos > jjohnson > bamtools_split
changeset 0:8c17ddca0eee draft
Uploaded
| author | jjohnson |
|---|---|
| date | Mon, 15 May 2017 16:27:18 -0400 |
| parents | |
| children | 59f09c61031c |
| files | ._bamtools-split-ref.xml ._bamtools-split-tag.xml bamtools-split-mapped.xml bamtools-split-paired.xml bamtools-split-ref.xml bamtools-split-tag.xml bamtools-split.xml bamtools-split.xml.save test-data/bamtools-input-paired.bam test-data/bamtools-input-tags.bam test-data/bamtools-input1.bam test-data/bamtools-input2.bam test-data/bamtools-split-test1.bam test-data/bamtools_input2.chr1 test-data/bamtools_input_tags.TAG_XG_N.bam test-data/bamtools_input_tags.TAG_XG_V.bam test-data/split_bam.MAPPED.bam test-data/split_bam.PAIRED_END.bam test-data/split_bam.SINGLE_END.bam test-data/split_bam.UNMAPPED.bam |
| diffstat | 20 files changed, 523 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bamtools-split-mapped.xml Mon May 15 16:27:18 2017 -0400 @@ -0,0 +1,55 @@ +<tool id="bamSplitMapped" name="Split BAM by Mapped" version="2.4.0"> + <description></description> + <requirements> + <requirement type="package" version="2.4.0">bamtools</requirement> + </requirements> + <command> + <![CDATA[ + ln -s '${input_bam}' 'localbam.bam' && + ln -s '${input_bam.metadata.bam_index}' 'localbam.bam.bai' && + bamtools split -mapped + -in localbam.bam + -stub split_bam + ]]> + </command> + <inputs> + <param name="input_bam" type="data" format="bam" label="BAM dataset to split by mapped/unmapped"/> + </inputs> + <outputs> + <data format="bam" name="mapped" label="${input_bam.name} mapped" from_work_dir="split_bam.MAPPED.bam" /> + <data format="bam" name="unmapped" label="${input_bam.name} unmapped" from_work_dir="split_bam.UNMAPPED.bam" /> + </outputs> + <tests> + <test> + <param name="input_bam" ftype="bam" value="bamtools-input1.bam"/> + <output name="mapped" file="split_bam.MAPPED.bam" compare="sim_size" delta="200" /> + <output name="unmapped" file="split_bam.UNMAPPED.bam" compare="sim_size" delta="200" /> + </test> + </tests> + <help> +**What is does** + +BAMTools split is a utility for splitting BAM files. It is based on BAMtools suite of tools by Derek Barnett (https://github.com/pezmaster31/bamtools). + +----- + +.. class:: warningmark + + +**How it works** + +Splits the input BAM file into 2 output files named (MAPPED) and (UNMAPPED) containing mapped and unmapped reads, respectively. + +----- + +.. class:: infomark + +**More information** + +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>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bamtools-split-paired.xml Mon May 15 16:27:18 2017 -0400 @@ -0,0 +1,56 @@ +<tool id="bamSplitPaired" name="Split BAM by Paired/Single End" version="2.4.0"> + <description></description> + <requirements> + <requirement type="package" version="2.4.0">bamtools</requirement> + </requirements> + <command> + <![CDATA[ + ln -s '${input_bam}' 'localbam.bam' && + ln -s '${input_bam.metadata.bam_index}' 'localbam.bam.bai' && + bamtools split -paired + -in localbam.bam + -stub split_bam + ]]> + </command> + <inputs> + <param name="input_bam" type="data" format="bam" label="BAM dataset to split by single_end/paired_end"/> + </inputs> + <outputs> + <data format="bam" name="single" label="${input_bam.name} mapped" from_work_dir="split_bam.SINGLE_END.bam" /> + <data format="bam" name="paired" label="${input_bam.name} unmapped" from_work_dir="split_bam.PAIRED_END.bam" /> + </outputs> + <tests> + <test> + <param name="input_bam" ftype="bam" value="bamtools-input-paired.bam"/> + <output name="single" file="split_bam.SINGLE_END.bam" compare="sim_size" delta="200" /> + <output name="paired" file="split_bam.PAIRED_END.bam" compare="sim_size" delta="200" /> + </test> + </tests> + <help> +**What is does** + +BAMTools split is a utility for splitting BAM files. It is based on BAMtools suite of tools by Derek Barnett (https://github.com/pezmaster31/bamtools). + +----- + +.. class:: warningmark + + +**How it works** + + +Splits the input BAM file into 2 output files named (SINGLE_END) and (PAIRED_END) containing single_end and paired_end reads, respectively. + +----- + +.. class:: infomark + +**More information** + +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>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bamtools-split-ref.xml Mon May 15 16:27:18 2017 -0400 @@ -0,0 +1,88 @@ +<tool id="bamSplitRef" name="Split BAM by Reference" version="2.4.0"> + <description>into dataset list collection</description> + <requirements> + <requirement type="package" version="2.4.0">bamtools</requirement> + </requirements> + <command> + <![CDATA[ + ln -s '${input_bam}' 'localbam.bam' && + ln -s '${input_bam.metadata.bam_index}' 'localbam.bam.bai' && + bamtools split -reference + -in localbam.bam + -stub split_bam + ## Preserve order from metadata in the output collection + #import re + #set $name = $re.sub('\W','_',$re.sub('\.bam$','',$input_bam.name)) + #if str($refs) != 'None': + #set $ref_list = ' '.join(str($refs).split(",")) + #else + #set $ref_list = ' '.join([$re.sub('^.*__sq__(.+)__sq__.*$','\\1',n) if n.find('__sq__') >= 0 else n for n in str($input_bam.metadata.reference_names).split(',')]) + #end if + && mkdir -p outputs + && (export I=0; + for i in $ref_list; + do I=\$((++I)); SN=`printf "split_bam.REF_%s.bam" "\$i"`; + if [ -e \$SN ]; then FN=`printf "outputs/split_bam%05d%s.%s.bam" \$((I)) '$name' "\$i"`; mv \$SN \$FN; fi; + done) + ]]> + </command> + <inputs> + <param name="input_bam" type="data" format="bam" label="BAM dataset to split by reference"/> + <param name="refs" type="select" optional="True" multiple="True" label="Select references (chromosomes and contigs) you would like to restrict bam to" > + <help><![CDATA[Click and type in the box above to see options. You can select multiple entries. + If "No options available" is displayed, you need to re-detect metadata on the input dataset. + ]]></help> + <options> + <filter type="data_meta" ref="input_bam" key="reference_names" /> + </options> + </param> + </inputs> + <outputs> + <collection name="output_bams" type="list" label="${input_bam.name} Split List"> + <discover_datasets pattern="split_bam\d*(?P<designation>.+)\.bam" ext="bam" directory="outputs" visible="false"/> + </collection> + </outputs> + <tests> + <test> + <param name="input_bam" ftype="bam" value="bamtools-input2.bam"/> + <output_collection name="output_bams" type="list"> + <element name="bamtools_input2.chr1" file="bamtools_input2.chr1" compare="sim_size" delta="500" /> + </output_collection> + </test> + </tests> + <help> +**What is does** + +BAMTools split is a utility for splitting BAM files. It is based on BAMtools suite of tools by Derek Barnett (https://github.com/pezmaster31/bamtools). + +----- + +.. class:: warningmark + +**DANGER: Multiple Outputs** + +As described below, splitting a BAM dataset(s) on reference name or a tag value can produce very large numbers of outputs. Read below and know what you are doing. + +----- + +**How it works** + +Split alignments by reference name into a dataset list collection. The collection will be in the same order as the input BAM references. + +In cases of unfinished genomes with very large number of reference sequences (scaffolds) +it can generate thousands (if not millions) of output datasets. + + +----- + +.. class:: infomark + +**More information** + +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>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bamtools-split-tag.xml Mon May 15 16:27:18 2017 -0400 @@ -0,0 +1,70 @@ +<tool id="bamSplitTag" name="Split BAM by Tag" version="2.4.0"> + <description>into dataset list collection</description> + <requirements> + <requirement type="package" version="2.4.0">bamtools</requirement> + </requirements> + <command> + <![CDATA[ + #import re + #set $name = 'split_bam' + $re.sub('\W','_',$re.sub('\.bam$','',$input_bam.name)) + ln -s '${input_bam}' 'localbam.bam' && + ln -s '${input_bam.metadata.bam_index}' 'localbam.bam.bai' && + bamtools split -tag $tag_name + -in 'localbam.bam' + -stub '$name' + ]]> + </command> + <inputs> + <param name="input_bam" type="data" format="bam" label="BAM dataset to split by tag value"/> + <param name="tag_name" type="text" value="NM" label="Enter tag name here" help="For example, to split on NM tag enter "NM""/> + </inputs> + <outputs> + <collection name="output_bams" type="list" label="${input_bam.name} Split List"> + <discover_datasets pattern="split_bam(?P<designation>.+)\.bam" ext="bam" visible="false"/> + </collection> + </outputs> + <tests> + <test> + <param name="input_bam" ftype="bam" value="bamtools-input-tags.bam"/> + <param name="tag_name" value="XG"/> + <output_collection name="output_bams" type="list"> + <element name="bamtools_input_tags.TAG_XG_V.bam" file="bamtools_input_tags.TAG_XG_V.bam" compare="sim_size" delta="500" /> + </output_collection> + </test> + + </tests> + <help> +**What is does** + +BAMTools split is a utility for splitting BAM files. It is based on BAMtools suite of tools by Derek Barnett (https://github.com/pezmaster31/bamtools). + +----- + +.. class:: warningmark + +**DANGER: Multiple Outputs** + +As described below, splitting a BAM dataset(s) on tag value can produce very large numbers of outputs. Read below and know what you are doing. + +----- + +**How it works** + +Split alignments by tag name into a dataset list collection. + +This can generate a huge number of output datasets depending on the number of distinct values of the TAG. + + +----- + +.. class:: infomark + +**More information** + +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>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bamtools-split.xml Mon May 15 16:27:18 2017 -0400 @@ -0,0 +1,108 @@ +<tool id="bamSplit" name="Split" version="2.4.0"> + <description>BAM datasets on variety of attributes</description> + <requirements> + <requirement type="package" version="2.4.0">bamtools</requirement> + </requirements> + <command> + <![CDATA[ + echo "BAM" > $report && + #for $bam_count, $input_bam in enumerate( $input_bams ): + ln -s "${input_bam}" "localbam_${bam_count}.bam" && + ln -s "${input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" && + #end for + bamtools + split + #if str ( $analysis_type.analysis_type_selector ) == "-tag" : + ${analysis_type.analysis_type_selector} "${analysis_type.tag_name}" + #else + ${analysis_type.analysis_type_selector} + #end if + -stub split_bam + #for $bam_count, $input_bam in enumerate( $input_bams ): + -in "localbam_${bam_count}.bam" + #end for + ]]> + </command> + <inputs> + <param name="input_bams" type="data" format="bam" label="BAM dataset(s) to filter" min="1" multiple="True"/> + <conditional name="analysis_type"> + <param name="analysis_type_selector" type="select" label="Split BAM dataset(s) by" help="See help below for explanation of each option"> + <option value="-mapped">Mapping status (-mapped)</option> + <option value="-paired">Pairing status (-paired)</option> + <option value="-reference">Reference name (-reference)</option> + <option value="-tag">Specific tag (-tag)</option> + </param> + <when value="-mapped" /> + <when value="-paired" /> + <when value="-reference" /> + <when value="-tag"> + <param name="tag_name" type="text" value="NM" label="Enter tag name here" help="For example, to split on NM tag enter "NM""/> + </when> + </conditional> + </inputs> + <outputs> + <data format="txt" name="report" label="BAMSplitter Run" hidden="true"> + <discover_datasets pattern="split_bam\.(?P<designation>.+)\.bam" ext="bam" visible="true"/> + </data> + </outputs> + <tests> + <test> + <param name="input_bams" ftype="bam" value="bamtools-input1.bam"/> + <param name="analysis_type_selector" value="-mapped"/> + <output name="report"> + <assert_contents> + <has_line line="BAM" /> + </assert_contents> + <discovered_dataset designation="MAPPED" file="bamtools-split-test1.bam" ftype="bam"/> + </output> + </test> + </tests> + <help> +**What is does** + +BAMTools split is a utility for splitting BAM files. It is based on BAMtools suite of tools by Derek Barnett (https://github.com/pezmaster31/bamtools). + +----- + +.. class:: warningmark + +**DANGER: Multiple Outputs** + +As described below, splitting a BAM dataset(s) on reference name or a tag value can produce very large numbers of outputs. Read below and know what you are doing. + +----- + +**How it works** + +The following options can be specified via "**Split BAM dataset(s) by**" dropdown:: + + Mapping status (-mapped) split mapped/unmapped and generate two output files + named (MAPPED) and (UNMAPPED) containing mapped and unmapped + reads, respectively. + + Pairing status (-paired) split single-end/paired-end alignments and generate two output files + named (SINGLE_END) and (PAIRED_END) containing paired and unpaired + reads, respectively. + + Reference name (-reference) split alignments by reference name. In cases of unfinished genomes with + very large number of reference sequences (scaffolds) it can generate + thousands (if not millions) of output datasets. + + Specific tag (-tag) split alignments based on all values of TAG encountered. Choosing this + option from the menu will allow you to enter the tag name. As was the + case with the reference splitting above, this option can produce very + large number of outputs if a tag has a large number of unique values. + +----- + +.. class:: infomark + +**More information** + +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>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/bamtools-split.xml.save Mon May 15 16:27:18 2017 -0400 @@ -0,0 +1,146 @@ +<tool id="bamSplit" name="Split" version="2.4.1"> + <description>BAM datasets on variety of attributes</description> + <macros> + <xml name="macro_output_type"> + <param name="output_type" type="select" label="output as"> + <option value="history_items">history items</option> + <option value="dataset_collection">dataset_collection</option> + </param> + </xml> + </macros> + <requirements> + <requirement type="package" version="2.4.0">bamtools</requirement> + </requirements> + <command> + <![CDATA[ + echo "BAM" > $report && + #for $bam_count, $input_bam in enumerate( $input_bams ): + ln -s "${input_bam}" "localbam_${bam_count}.bam" && + ln -s "${input_bam.metadata.bam_index}" "localbam_${bam_count}.bam.bai" && + #end for + bamtools + split + #if str ( $analysis_type.analysis_type_selector ) == "-tag" : + ${analysis_type.analysis_type_selector} "${analysis_type.tag_name}" + #else + ${analysis_type.analysis_type_selector} + #end if + -stub split_bam + #for $bam_count, $input_bam in enumerate( $input_bams ): + -in "localbam_${bam_count}.bam" + #end for + #if str ( $analysis_type.analysis_type_selector ) == "-reference" and $analysis_type.output_type == "dataset_collection": + #import re + #set $name = $re.sub('\W','_',$re.sub('\.bam$','',$input_bams[0].name)) + #set $ref_list = ' '.join([$re.sub('^.*__sq__(.+)__sq__.*$','\\1',n) if n.find('__sq__') >= 0 else n for n in str($input_bam.metadata.reference_names).split(',')]) + && (export I=0; + for i in $ref_list; + do I=\$((++I)); SN=`printf "split_bam.REF_%s.bam" "\$i"`; + if [ -e \$SN ]; + then FN=`printf "split_bam%05d%s.%s.bam" \$((I)) "$name" "\$i"`; + mv \$SN \$FN; + fi; + done) + #end if + ]]> + </command> + <inputs> + <param name="input_bams" type="data" format="bam" label="BAM dataset(s) to filter" min="1" multiple="True"/> + <conditional name="analysis_type"> + <param name="analysis_type_selector" type="select" label="Split BAM dataset(s) by" help="See help below for explanation of each option"> + <option value="-mapped">Mapping status (-mapped)</option> + <option value="-paired">Pairing status (-paired)</option> + <option value="-reference">Reference name (-reference)</option> + <option value="-tag">Specific tag (-tag)</option> + </param> + <when value="-mapped" /> + <when value="-paired" /> + <when value="-reference" > + <expand macro="macro_output_type" /> + </when> + <when value="-tag"> + <param name="tag_name" type="text" value="NM" label="Enter tag name here" help="For example, to split on NM tag enter "NM""/> + <expand macro="macro_output_type" /> + </when> + </conditional> + </inputs> + <outputs> + <data format="txt" name="report" label="BAMSplitter Run" hidden="true"> + <discover_datasets pattern="split_bam\.(?P<designation>.+)\.bam" ext="bam" visible="true"/> + <filter>analysis_type['analysis_type_selector'] in ('-mapped','-paired') or analysis_type['output_type'] != 'dataset_collection'</filter> + </data> + <collection name="output_bams" type="list" label="${input_bams[0].name} by ${analysis_type.analysis_type_selector.replace('-','')}"> + <discover_datasets pattern="split_bam\d*(?P<designation>.+)\.bam" ext="bam" visible="false"/> + <filter>analysis_type['analysis_type_selector'] in ('-reference','-tag') and analysis_type['output_type'] == 'dataset_collection'</filter> + </collection> + </outputs> + <tests> + <test> + <param name="input_bams" ftype="bam" value="bamtools-input1.bam"/> + <param name="analysis_type_selector" value="-mapped"/> + <output name="report"> + <assert_contents> + <has_line line="BAM" /> + </assert_contents> + <discovered_dataset designation="MAPPED" file="bamtools-split-test1.bam" ftype="bam"/> + </output> + </test> + <test> + <param name="input_bams" ftype="bam" value="bamtools-input2.bam"/> + <param name="analysis_type_selector" value="-reference"/> + <param name="output_type" value="dataset_collection"/> + <output_collection name="output_bams" type="list"> + <element name="bamtools_input2.chr1" file="bamtools_input2.chr1" compare="sim_size" delta="500" /> + </output_collection> + </test> + + </tests> + <help> +**What is does** + +BAMTools split is a utility for splitting BAM files. It is based on BAMtools suite of tools by Derek Barnett (https://github.com/pezmaster31/bamtools). + +----- + +.. class:: warningmark + +**DANGER: Multiple Outputs** + +As described below, splitting a BAM dataset(s) on reference name or a tag value can produce very large numbers of outputs. Read below and know what you are doing. + +----- + +**How it works** + +The following options can be specified via "**Split BAM dataset(s) by**" dropdown:: + + Mapping status (-mapped) split mapped/unmapped and generate two output files + named (MAPPED) and (UNMAPPED) containing mapped and unmapped + reads, respectively. + + Pairing status (-paired) split single-end/paired-end alignments and generate two output files + named (SINGLE_END) and (PAIRED_END) containing paired and unpaired + reads, respectively. + + Reference name (-reference) split alignments by reference name. In cases of unfinished genomes with + very large number of reference sequences (scaffolds) it can generate + thousands (if not millions) of output datasets. + + Specific tag (-tag) split alignments based on all values of TAG encountered. Choosing this + option from the menu will allow you to enter the tag name. As was the + case with the reference splitting above, this option can produce very + large number of outputs if a tag has a large number of unique values. + +----- + +.. class:: infomark + +**More information** + +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>