Mercurial > repos > devteam > bowtie2
changeset 5:42bb952b4e3c draft
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bowtie2 commit d0e3412c58bd3bdc1a483a1e2f7f9c2aa5c87a1f-dirty
| author | devteam |
|---|---|
| date | Tue, 21 Jul 2015 13:01:59 -0400 |
| parents | 1fc845afa3ac |
| children | e23b0cdeeba6 |
| files | bowtie2_wrapper.xml read_group_macros.xml test-data/bowtie2-test2.bam |
| diffstat | 3 files changed, 339 insertions(+), 21 deletions(-) [+] |
line wrap: on
line diff
--- a/bowtie2_wrapper.xml Tue Jul 21 13:00:51 2015 -0400 +++ b/bowtie2_wrapper.xml Tue Jul 21 13:01:59 2015 -0400 @@ -1,6 +1,9 @@ -<tool id="bowtie2" name="Bowtie2" version="0.5"> +<tool id="bowtie2" name="Bowtie2" version="0.6"> <!-- Wrapper compatible with Bowtie version 2.2.4 --> <description>- map reads against reference genome</description> + <macros> + <import>read_group_macros.xml</import> + </macros> <version_command>bowtie2 --version</version_command> <requirements> <requirement type="package" version="2.2.4">bowtie2</requirement> @@ -70,12 +73,30 @@ #end if #end if - ## Readgroups - #if str( $read_group.read_group_selector ) == "yes": - --rg-id "${read_group.rgid}" - --rg "SM:${read_group.rgsm}" - --rg "LB:${read_group.rglb}" - --rg "PL:${read_group.rgpl}" + ## Read group information. + @define_read_group_helpers@ + #if str( $library.type ) == "single": + #set $rg_auto_name = $read_group_name_default($library.input_1) + #elif str( $library.type ) == "paired": + #set $rg_auto_name = $read_group_name_default($library.input_1, $library.input_2) + #else + #set $rg_auto_name = $read_group_name_default($library.input_1) + #end if + @set_use_rg_var@ + @set_read_group_vars@ + #if $use_rg + $format_read_group("", $rg_id, '"', arg='--rg-id ') + $format_read_group("SM:", $rg_sm, '"', arg='--rg ') + $format_read_group("PL:", $rg_pl, '"', arg='--rg ') + $format_read_group("LB:", $rg_lb, '"', arg='--rg ') + $format_read_group("CN:", $rg_cn, '"', arg='--rg ') + $format_read_group("DS:", $rg_ds, '"', arg='--rg ') + $format_read_group("DT:", $rg_dt, '"', arg='--rg ') + $format_read_group("FO:", $rg_fo, '"', arg='--rg ') + $format_read_group("KS:", $rg_ks, '"', arg='--rg ') + $format_read_group("PG:", $rg_pg, '"', arg='--rg ') + $format_read_group("PI:", $rg_pi, '"', arg='--rg ') + $format_read_group("PU:", $rg_pu, '"', arg='--rg ') #end if ## Analysis type @@ -257,20 +278,7 @@ </conditional> <!-- read group settings --> - <conditional name="read_group"> - <param name="read_group_selector" type="select" label="Specify the read group for this file?" help="Specifying readgroup information can greatly simplify your downstream analyses by allowing combining multiple datasets. See help below for more details"> - <option value="yes">Yes</option> - <option value="no" selected="True">No</option> - </param> - <when value="yes"> - <param name="rgid" type="text" size="25" label="Read group identifier (ID). Each @RG line must have a unique ID. The value of ID is used in the RG tags of alignment records. Must be unique among all read groups in header section." help="--rg-id; Required if RG specified. Read group IDs may be modified when merging SAM files in order to handle collisions." /> - <param name="rglb" type="text" size="25" label="Library name (LB)" help="--rg; Required if RG specified" /> - <param name="rgpl" type="text" size="25" label="Platform/technology used to produce the reads (PL)" help="--rg; Required if RG specified. Valid values : CAPILLARY, LS454, ILLUMINA, SOLID, HELICOS, IONTORRENT and PACBIO" /> - <param name="rgsm" type="text" size="25" label="Sample (SM)" help="--rg; Required if RG specified. Use pool name where a pool is being sequenced" /> - </when> - <when value="no" /> - </conditional> - + <expand macro="read_group_conditional" /> <conditional name="analysis_type"> <param name="analysis_type_selector" type="select" label="Select analysis mode"> <option value="simple">1: Default setting only</option> @@ -479,6 +487,22 @@ <param name="own_file" value="bowtie2-ref.fasta" /> <output name="output" file="bowtie2-test1.bam" ftype="bam" lines_diff="2"/> </test> + <test> + <!-- basic test on single paired default run --> + <param name="type" value="paired"/> + <param name="selection" value="no"/> + <param name="paired_options_selector" value="no"/> + <param name="unaligned_file" value="false"/> + <param name="analysis_type_selector" value="simple"/> + <param name="rg_selector" value="set"/> + <param name="ID" value="rg1"/> + <param name="PL" value="CAPILLARY"/> + <param name="source" value="history" /> + <param name="input_1" value="bowtie2-fq1.fq" ftype="fastqsanger"/> + <param name="input_2" value="bowtie2-fq2.fq" ftype="fastqsanger"/> + <param name="own_file" value="bowtie2-ref.fasta" /> + <output name="output" file="bowtie2-test2.bam" ftype="bam" lines_diff="2"/> + </test> </tests> <help>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/read_group_macros.xml Tue Jul 21 13:01:59 2015 -0400 @@ -0,0 +1,294 @@ +<macros> + <!-- Import this at the top of your command block and then + define rg_auto_name. --> + <token name="@define_read_group_helpers@"> +#import re +#def identifier_or_name($input1) + #if hasattr($input1, 'element_identifier') + #return $input1.element_identifier + #else + #return $input1.name.rstrip('.gz').rstrip('.fastq').rstrip('.fq') + #end if +#end def + +#def clean(name) + #set $name_clean = re.sub('[^\w\-_\.]', '_', $name) + #return $name_clean +#end def + +#def read_group_name_default($input1, $input2=None) + #if $input2 is None + #return $clean($identifier_or_name($input1)) + #else + #import itertools + #set $input_name1 = $clean($identifier_or_name($input1)) + #set $input_name2 = $clean($identifier_or_name($input2)) + #set $common_prefix = ''.join([c[0] for c in itertools.takewhile(lambda x: all(x[0] == y for y in x), itertools.izip(*[$input_name1, $input_name2]))]) + #if len($common_prefix) > 3 + #return $common_prefix + #else + #return $input_name1 + #end if + #end if +#end def + +#def format_read_group(prefix, value, quote='', arg='') + #if $value + #return $arg + $quote + $prefix + $value + $quote + #else + #return '' + #end if +#end def + +#def rg_param(name) + #if $varExists("rg") + #return $rg.get($name, None) + #else + #return $getVar($name, None) + #end if +#end def + +#set $use_rg = True + </token> + <!-- preconditions use_rg and rg_auto_name have been + defined. + --> + <token name="@set_read_group_vars@"> +#if $use_rg + #if $rg_param('read_group_id_conditional') is None + #set $rg_id = $rg_auto_name + #elif $rg_param('read_group_id_conditional').do_auto_name + #set $rg_id = $rg_auto_name + #else + #set $rg_id = str($rg_param('read_group_id_conditional').ID) + #end if + + #if $rg_param('read_group_sm_conditional') is None + #set $rg_sm = '' + #elif $rg_param('read_group_sm_conditional').do_auto_name + #set $rg_sm = $rg_auto_name + #else + #set $rg_sm = str($rg_param('read_group_sm_conditional').SM) + #end if + + #if $rg_param('PL') + #set $rg_pl = str($rg_param('PL')) + #else + #set $rg_pl = '' + #end if + + #if $rg_param('read_group_lb_conditional') is None + #set $rg_lb = '' + #elif $rg_param('read_group_lb_conditional')do_auto_name + #set $rg_lb = $rg_auto_name + #else + #set $rg_lb = str($rg_param('read_group_lb_conditional').LB) + #end if + + #if $rg_param('CN') + #set $rg_cn = str($rg_param('CN')) + #else + #set $rg_cn = '' + #end if + + #if $rg_param("DS") + #set $rg_ds = str($rg_param("DS")) + #else + #set $rg_ds = '' + #end if + + #if $rg_param("DT") + #set $rg_dt = str($rg_param("DT")) + #else + #set $rg_dt = '' + #end if + + #if $rg_param("FO") + #set $rg_fo = str($rg_param("FO")) + #else + #set $rg_fo = '' + #end if + + #if $rg_param("KS") + #set $rg_ks = str($rg_param("KS")) + #else + #set $rg_ks = '' + #end if + + #if $rg_param("PG") + #set $rg_pg = str($rg_param("PG")) + #else + #set $rg_pg = '' + #end if + + #if str($rg_param("PI")) + #set $rg_pi = str($rg_param("PI")) + #else + #set $rg_pi = '' + #end if + + #if $rg_param("PU") + #set $rg_pu = str($rg_param("PU")) + #else + #set $rg_pu = '' + #end if +#end if + </token> + <token name="@set_use_rg_var@"> +#set $use_rg = str($rg.rg_selector) != "do_not_set" + </token> + <xml name="read_group_auto_name_conditional"> + <param name="do_auto_name" type="boolean" label="Auto-assign" help="Use dataset name or collection information to automatically assign this value" checked="no" /> + <when value="true"> + </when> + <when value="false"> + <yield /> + </when> + </xml> + <xml name="read_group_id_param"> + <param name="ID" type="text" value="" size="20" label="Read group identifier (ID)" help="This value must be unique among multiple samples in your experiment" optional="false"> + <validator type="empty_field" /> + </param> + </xml> + <xml name="read_group_id_conditional"> + <conditional name="read_group_id_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_id_param" /> + </expand> + </conditional> + </xml> + <xml name="read_group_sm_param"> + <param name="SM" type="text" value="" size="20" label="Read group sample name (SM)" help="This value should be descriptive. Use pool name where a pool is being sequenced" /> + </xml> + <xml name="read_group_sm_conditional"> + <conditional name="read_group_sm_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_sm_param" /> + </expand> + </conditional> + </xml> + <!-- Above SM param is optional (for SAM/BAM spec, this is required + as per Picard. + --> + <xml name="read_group_sm_param_required"> + <param name="SM" type="text" value="" size="20" label="Read group sample name (SM)" optional="false" help="This value should be descriptive. Use pool name where a pool is being sequenced"> + <validator type="empty_field" /> + </param> + </xml> + <xml name="read_group_sm_required_conditional"> + <conditional name="read_group_sm_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_sm_param" /> + </expand> + </conditional> + </xml> + <xml name="read_group_pl_param"> + <param name="PL" type="select" label="Platform/technology used to produce the reads (PL)"> + <option value="CAPILLARY">CAPILLARY</option> + <option value="LS454">LS454</option> + <option selected="True" value="ILLUMINA">ILLUMINA</option> + <option value="SOLID">SOLID</option> + <option value="HELICOS">HELICOS</option> + <option value="IONTORRENT">IONTORRENT</option> + <option value="PACBIO">PACBIO</option> + </param> + </xml> + <xml name="read_group_lb_param"> + <param name="LB" type="text" size="25" label="Library name (LB)" optional="true" /> + </xml> + <xml name="read_group_lb_conditional"> + <conditional name="read_group_lb_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_lb_param" /> + </expand> + </conditional> + </xml> + <xml name="read_group_lb_required_param"> + <param name="LB" type="text" size="25" label="Library name (LB)" optional="false"> + <validator type="empty_field" /> + </param> + </xml> + <xml name="read_group_lb_required_conditional"> + <conditional name="read_group_lb_conditional"> + <expand macro="read_group_auto_name_conditional"> + <expand macro="read_group_lb_required_param" /> + </expand> + </conditional> + </xml> + <xml name="read_group_cn_param"> + <param name="CN" type="text" size="25" label="Sequencing center that produced the read (CN)" /> + </xml> + <xml name="read_group_ds_param"> + <param name="DS" type="text" size="25" label="Description (DS)" /> + </xml> + <xml name="read_group_dt_param"> + <param name="DT" type="text" size="25" label="Date that run was produced (DT)" help="ISO8601 format date or date/time, like YYYY-MM-DD" /> + </xml> + <xml name="read_group_fo_param"> + <param name="FO" type="text" size="25" optional="true" label="Flow order (FO)" help="The array of nucleotide bases that correspond to the nucleotides used for each flow of each read. Multi-base flows are encoded in IUPAC format, and non-nucleotide flows by various other characters. Format: /\*|[ACMGRSVTWYHKDBN]+/"> + <validator type="regex" message="Invalid flow order">\*|[ACMGRSVTWYHKDBN]+$</validator> + </param> + </xml> + <xml name="read_group_ks_param"> + <param name="KS" type="text" size="25" label="The array of nucleotide bases that correspond to the key sequence of each read (KS)" /> + </xml> + <xml name="read_group_pg_param"> + <param name="PG" type="text" size="25" label="Programs used for processing the read group (PG)" /> + </xml> + <xml name="read_group_pi_param"> + <param name="PI" type="integer" optional="true" label="Predicted median insert size (PI)" /> + </xml> + <xml name="read_group_pu_param"> + <param name="PU" type="text" size="25" label="Platform unit (PU)" help="Unique identifier (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD)" optional="True" /> + </xml> + <xml name="read_group_pu_required_param"> + <param name="PU" type="text" size="25" label="Platform unit (PU)" help="Unique identifier (e.g. flowcell-barcode.lane for Illumina or slide for SOLiD)" optional="False" /> + </xml> + <!-- Only ID is required - all groups available --> + <xml name="read_group_inputs_spec"> + <expand macro="read_group_id_conditional" /> + <expand macro="read_group_sm_conditional" /> + <expand macro="read_group_pl_param" /> + <expand macro="read_group_lb_conditional" /> + <expand macro="read_group_cn_param" /> + <expand macro="read_group_ds_param" /> + <expand macro="read_group_dt_param" /> + <expand macro="read_group_fo_param" /> + <expand macro="read_group_ks_param" /> + <expand macro="read_group_pg_param" /> + <expand macro="read_group_pi_param" /> + <expand macro="read_group_pu_param" /> + </xml> + <!-- ID, SM, LB, PU, PL all required - not ks, pg, or fo params. --> + <xml name="read_group_inputs_picard"> + <expand macro="read_group_id_conditional" /> + <expand macro="read_group_sm_required_conditional" /> + <expand macro="read_group_lb_required_conditional" /> + <expand macro="read_group_pl_param" /> + <expand macro="read_group_pu_required_param" /> + <expand macro="read_group_cn_param" /> + <expand macro="read_group_ds_param" /> + <expand macro="read_group_pi_param" /> + <expand macro="read_group_dt_param" /> + </xml> + <xml name="read_group_conditional"> + <conditional name="rg"> + <param name="rg_selector" type="select" label="Set read groups information?" help="Specifying read group information can greatly simplify your downstream analyses by allowing combining multiple datasets."> + <option value="set">Set read groups (SAM/BAM specification)</option> + <option value="set_picard">Set read groups (Picard style)</option> + <option value="set_id_auto">Automatically assign ID</option> + <option value="do_not_set" selected="True">Do not set</option> + </param> + <when value="set_picard"> + <expand macro="read_group_inputs_picard" /> + </when> + <when value="set"> + <expand macro="read_group_inputs_spec" /> + </when> + <when value="set_id_auto"> + </when> + <when value="do_not_set"> + </when> + </conditional> + </xml> +</macros>