Mercurial > repos > yhoogstrate > featurecounts
changeset 2:b5c93611d2c5 draft
planemo upload for repository https://github.com/ErasmusMC-Bioinformatics/featurecounts_galaxy_wrapper commit b05640a41e2106782ac7f88f858b0a256918fa6f
| author | yhoogstrate |
|---|---|
| date | Thu, 10 Sep 2015 05:11:49 -0400 |
| parents | 63bd455ed299 |
| children | e04fbcc4e91a |
| files | README.rst featurecounts.xml featurecounts2bed.sh tool_dependencies.xml |
| diffstat | 4 files changed, 243 insertions(+), 250 deletions(-) [+] |
line wrap: on
line diff
--- a/README.rst Mon Jun 01 07:18:31 2015 -0400 +++ b/README.rst Thu Sep 10 05:11:49 2015 -0400 @@ -1,8 +1,8 @@ FeatureCounts wrapper for Galaxy ================================ -http://bioinf.wehi.edu.au/featureCounts/ -http://subread.sourceforge.net/ +* http://bioinf.wehi.edu.au/featureCounts/ +* http://subread.sourceforge.net/ FeatureCounts as part of the SUBREAD package is "a highly efficient and accurate read summarization program". @@ -13,7 +13,7 @@ * Repository-Maintainer: Youri Hoogstrate * Repository-Developers: Youri Hoogstrate, Marius van den Beek -* Repository-Development: https://bitbucket.org/EMCbioinf/galaxy-tool-shed-tools +* Repository-Development: https://github.com/ErasmusMC-Bioinformatics/featurecounts_galaxy_wrapper The tool wrapper has been written by Youri Hoogstrate from the Erasmus Medical Center (Rotterdam, Netherlands) on behalf of the Translational @@ -34,22 +34,22 @@ **This wrapper**: - Copyright (C) 2013-2014 Youri Hoogstrate +``Copyright (C) 2013-2015 Youri Hoogstrate`` - This program is free software: you can redistribute it and/or modify - it under the terms of the GNU General Public License as published by - the Free Software Foundation, either version 3 of the License, or - (at your option) any later version. +``This program is free software: you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation, either version 3 of the License, or +(at your option) any later version.`` - This program is distributed in the hope that it will be useful, - but WITHOUT ANY WARRANTY; without even the implied warranty of - MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - GNU General Public License for more details. +``This program is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details.`` - You should have received a copy of the GNU General Public License - along with this program. If not, see <http://www.gnu.org/licenses/>. +``You should have received a copy of the GNU General Public License +along with this program. If not, see <http://www.gnu.org/licenses/>.`` Acknowledgements ---------------- -I would like to thank Marius van den Beek for his contributions to this project. \ No newline at end of file +I would like to thank Marius van den Beek for his contributions to this project.
--- a/featurecounts.xml Mon Jun 01 07:18:31 2015 -0400 +++ b/featurecounts.xml Thu Sep 10 05:11:49 2015 -0400 @@ -1,211 +1,207 @@ <?xml version="1.0" encoding="UTF-8"?> <tool id="featurecounts" name="featureCounts" version="1.4.6.p1"> - <description>Measure gene expression in RNA-Seq experiments from SAM or BAM files.</description> - <requirements> - <requirement type="package" version="1.4.6.p1">featurecounts</requirement> - <requirement type="package" version="1.0.0">featurecounts2bed</requirement> - </requirements> - <version_command>featureCounts -v</version_command> - <command> - #* - The following script is written in the "Cheetah" language: - http://www.cheetahtemplate.org/docs/users_guide_html_multipage/contents.html - *# - - ## Check 01: do the alignments have a dbkey and is the option set to using it? - #if $reference_gene_sets_source.source_select == "attribute" and len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) != 1 - echo "Invalid number of dbkeys are found: ${ len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) }, while only one should be used. Make sure that the alignments are done on the same reference genome and that 'tool-data/gene_sets.loc' is configured properly!" >&2 - #else - ## Check 02: are all alignments from the same type (bam || sam) - #if len({ alignment.extension:True for alignment in $alignments }.keys()) != 1 - echo "Either all files must be SAM or all files must be BAM, no mixture is allowed." >&2 - #else - featureCounts - -a - #if $reference_gene_sets_source.source_select == "indexed_filtered" - "$reference_gene_sets_source.reference_gene_sets" - #else if $reference_gene_sets_source.source_select == "indexed_all" - "$reference_gene_sets_source.reference_gene_sets" - #else if $reference_gene_sets_source.source_select == "history" - "$reference_gene_sets_source.reference_gene_sets" - #else - #* - This is a workaround to obtain the "genome.fa" file that - corresponds to the dbkey of the alignments. - Because this file is "calculated" during run-time, it can - be used in a workflow. - *# - "${ filter( lambda x: str( x[0] ) == str( { alignment.metadata.dbkey:True for alignment in $alignments }.keys()[0] ), $__app__.tool_data_tables[ 'gene_sets' ].get_fields() )[0][2] }" - #end if - - -o "$output" - -T \${GALAXY_SLOTS:-2} - - #if $extended_parameters.parameters == "extended" - -t $extended_parameters.gff_feature_type - -g $extended_parameters.gff_feature_attribute - $extended_parameters.summarization_level - $extended_parameters.contribute_to_multiple_features - $extended_parameters.protocol - $extended_parameters.multimapping_counts - -Q $extended_parameters.mapping_quality - $extended_parameters.fragment_counting - $extended_parameters.check_distance - -d $extended_parameters.minimum_fragment_length - -D $extended_parameters.maximum_fragment_length - $extended_parameters.only_both_ends - $extended_parameters.exclude_chimerics - $extended_parameters.namesort - #end if - - #for $alignment in $alignments - ${alignment} - #end for - - 2>&1 - - #set $columns = [str(i+7) for i, alignment in enumerate($alignments)] - #set $columns=",".join($columns) - - #if $format == "tabdel_default" or $format.value == "tabdel_default" - ; cp $output tmp.txt - ; egrep -v "^#" tmp.txt > tmp2.txt - ; cut -f 1,$columns tmp2.txt > tmp_left.txt - ; cut -f 6 tmp2.txt > tmp_right.txt - ; paste tmp_left.txt tmp_right.txt > $output - #elif $format == "tabdel_short" or $format.value == "tabdel_short" - ; cp $output tmp.txt - ; egrep -v "^#" tmp.txt | cut -f 1,$columns > $output - #end if - - ## For every alignment, replace its filename for: "hid: sample name" - #for $alignment in $alignments - #set $alignment_escaped = str($alignment).replace('/', '\/').replace('.', '\.') - #set $alignment_name_escaped = str(alignment.hid)+": "+str($alignment.name).replace('\t',' ').replace('\\','\\\\').replace("'","\\'").replace('/','\/') - - #if $format.value == "tabdel_default" or $format.value == "tabdel_short" - ; sed -e '1 s/$alignment_escaped/${alignment_name_escaped}/g' $output > tmp.txt - #elif $format.value == "bed": - ; featurecounts2bed.sh -f "$output" > tmp.txt - #else - ; sed -e '1,2 s/$alignment_escaped/${alignment_name_escaped}/g' $output > tmp.txt - #end if - - ; mv tmp.txt $output - - ; sed -e '1 s/$alignment_escaped/${alignment_name_escaped}/g' $output".summary" > tmp.txt - ; mv tmp.txt $output".summary" - #end for - ; mv $output".summary" $output_summary - #end if - #end if - </command> - - <inputs> - <param name="alignments" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) where the gene expression has to be counted. The file can have a SAM or BAM format; but ALL files in the series must be in THE SAME format." multiple="true" /> - - <!-- Find out how to access the the GTF/GFF file(s) --> - <conditional name="reference_gene_sets_source"> - <param name="source_select" type="select" label="GFF/GTF Source"> - <option value="indexed_filtered">Use a built-in index (which fits your reference)</option> - <option value="history">Use reference from the history</option> - <option value="indexed_all">Use a built-in index (entire list) - avoid this option if possible; only useful if you design a workflow</option> - <option value="attribute">Use a built-in index based on the 'metadata.dbkey' attribute; ideal in workflows</option> - </param> - <when value="indexed_filtered"> - <param name="reference_gene_sets" type="select" label="Reference Gene Sets used during alignment (GFF/GTF)" > - <options from_data_table="gene_sets"><!-- replaces 'from_file="gene_sets"' - more strict --> - <column name="name" index="0"/> - <column name="dbkey" index="1"/> - <column name="value" index="2"/> - <filter type="data_meta" ref="alignments" multiple="false" key="dbkey" column="1" /> - <validator type="no_options" message="No indexes are available for the selected input dataset" /> - </options> - </param> - </when> - <when value="history"> - <param name="reference_gene_sets" format="gff" type="data" label="Gene annotation file" help="The program assumes that the provided annotation file is in GTF format. Make sure that the gene annotation file corresponds to the same reference genome as used for the alignment." /> - </when> - <when value="indexed_all"> - <param name="reference_gene_sets" type="select" label="Reference Gene Sets used during alignment (GFF/GTF)" > - <options from_data_table="gene_sets"><!-- replaces 'from_file="gene_sets"' - more strict --> - <column name="name" index="0"/> - <column name="dbkey" index="1"/> - <column name="value" index="2"/> - <validator type="no_options" message="No indexes are available for the selected input dataset" /> - </options> - </param> - </when> - <when value="attribute"> - <!-- Do nothing, determine GTF/GFF file at runtime --> - </when> - </conditional> - - <param name="format" type="select" label="Output format"> - <option value="complex">featureCounts 1.4.0+ default (extensive; complex)</option> - <option value="tabdel_default" selected="true">Gene-name "\t" gene-count "\t" gene-length (tab-delimited)</option> - <option value="tabdel_short">Gene-name "\t" gene-count (tab-delimited)</option> - <option value="bed">BED format (line per exon): chr "\t" start "\t" stop "\t" description "\t" readcount (tab-delimited)</option> - </param> - - <conditional name="extended_parameters"> - <param name="parameters" type="select" label="featureCounts parameters" help="For more advanced featureCounts settings."> - <option value="default">Default settings</option> - <option value="extended">Extended settings</option> - </param> - <when value="default"> - </when> - <when value="extended"> - <param name="gff_feature_type" type="text" value="exon" label="GFF feature type filter" help="Specify the feature type. Only rows which have the matched matched feature type in the provided GTF annotation file will be included for read counting. `exon' by default." /> - - <param name="gff_feature_attribute" type="text" value="gene_id" label="GFF gene identifier" help="Specify the attribute type used to group features (eg. exons) into meta-features (eg. genes), when GTF annotation is provided. `gene_id' by default. This attribute type is usually the gene identifier. This argument is useful for the meta-feature level summarization." /> - - <param name ="summarization_level" type="boolean" truevalue=" -f" falsevalue="" label="On feature level" help="If specified, read summarization will be performed at the feature level. By default (-f is not specified), the read summarization is performed at the meta-feature level." /> - - <param name ="contribute_to_multiple_features" type="boolean" truevalue=" -O" falsevalue="" label="Allow read to contribute to multiple features" help="If specified, reads (or fragments if -p is specified) will be allowed to be assigned to more than one matched meta- feature (or matched feature if -f is specified)" /> - - <param name="protocol" type="select" label="Strand specific protocol" help="Indicate if strand-specific read counting should be performed. It has three possible values: 0 (unstranded), 1 (stranded) and 2 (reversely stranded). 0 by default."> - <option value=" -s 0" selected="true">Unstranded</option> - <option value=" -s 1">Stranded (forwards)</option> - <option value=" -s 2">Stranded (reverse)</option> - </param> - - <param name="multimapping_counts" type="boolean" truevalue=" -M" falsevalue="" label="Count multi-mapping reads/fragments" help="If specified, multi-mapping reads/fragments will be counted (ie. a multi-mapping read will be counted up to N times if it has N reported mapping locations). The program uses the `NH' tag to find multi-mapping reads." /> - - <param name="mapping_quality" type="integer" value="0" label="Minimum read quality" help="The minimum mapping quality score a read must satisfy in order to be counted. For paired-end reads, at least one end should satisfy this criteria. 0 by default." /> - - <param name="fragment_counting" type="boolean" truevalue=" -p" falsevalue="" label="PE: Count fragments instead of reads" help="Paired-end specific: If specified, fragments (or templates) will be counted instead of reads. The two reads from the same fragment must be adjacent to each other in the provided SAM/BAM file. If SAM/BAM input does not meet this requirement, the -S (sorting) option should be provided as well." /> - - <param name="check_distance" type="boolean" truevalue=" -P" falsevalue="" label="PE: Check paired-end distance" help="Paired-end specific: If specified, paired-end distance will be checked when assigning fragments to meta-features or features. This option is only applicable when -p (Count fragments instead of reads) is specified. The distance thresholds should be specified using -d and -D (minimum and maximum fragment/template length) options." /> - - <param name="minimum_fragment_length" type="integer" value="50" label="PE: Minimum fragment/template length." /> - <param name="maximum_fragment_length" type="integer" value="600" label="PE: Maximum fragment/template length." /> - - <param name="only_both_ends" type="boolean" truevalue=" -B" falsevalue="" label="PE: only allow fragments with both reads aligned" help="Paired-end specific: If specified, only fragments that have both ends successfully aligned will be considered for summarization. This option is only applicable for paired-end reads." /> - - <param name="exclude_chimerics" type="boolean" truevalue=" -C" falsevalue="" label="PE: Exclude chimeric fragments" help="Paired-end specific: If specified, the chimeric fragments (those fragments that have their two ends aligned to different chromosomes) will NOT be included for summarization. This option is only applicable for paired-end read data." /> - - <param name="namesort" type="boolean" truevalue=" -S" falsevalue="" label="PE: Name-sort reads (slow!)" help="Paired-end specific: If specified, the program will reorder input reads according to their names and make reads from the same pair be adjacent to each other. This option should be provided when reads from the same pair are not adjacent to each other in input SAM/BAM files (for instance sorting reads by chromosomal locations could decouple reads from the same pair)." /> - </when> - </conditional> - </inputs> - - <outputs> - <data format="tabular" name="output" label="${tool.name} on ${', '.join([ str(a.hid)+': '+a.name for a in $alignments ])}" /> - <data format="tabular" name="output_summary" label="${tool.name} on ${', '.join([ str(a.hid)+': '+a.name for a in $alignments ])} summary" /> - </outputs> - - <tests> - <test> - <param name="alignments" value="featureCounts_input1.bam,featureCounts_input2.bam" ftype="bam" /> - <param name="source_select" value="history" /> - <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" /> - <output name="output" file="output.tab"/> - <output name="output_summary" file="output_summary.tab"/> - </test> - </tests> - - <help> + <description>Measure gene expression in RNA-Seq experiments from SAM or BAM files.</description> + <requirements> + <requirement type="package" version="1.4.6.p1">featurecounts</requirement> + <requirement type="package" version="1.0.0">featurecounts2bed</requirement> + </requirements> + <version_command>featureCounts -v</version_command> + <command><![CDATA[ + ## Check 01: do the alignments have a dbkey and is the option set to using it? + + #if $reference_gene_sets_source.source_select == "attribute" and len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) != 1 + echo "Invalid number of dbkeys are found: ${ len({ alignment.metadata.dbkey:True for alignment in $alignments }.keys()) }, while only one should be used. Make sure that the alignments are done on the same reference genome and that 'tool-data/gene_sets.loc' is configured properly!" >&2 + #else + ## Check 02: are all alignments from the same type (bam || sam) + #if len({ alignment.extension:True for alignment in $alignments }.keys()) != 1 + echo "Either all files must be SAM or all files must be BAM, no mixture is allowed." >&2 + #else + featureCounts + -a + #if $reference_gene_sets_source.source_select == "indexed_filtered" + "$reference_gene_sets_source.reference_gene_sets" + #else if $reference_gene_sets_source.source_select == "indexed_all" + "$reference_gene_sets_source.reference_gene_sets" + #else if $reference_gene_sets_source.source_select == "history" + "$reference_gene_sets_source.reference_gene_sets" + #else + #* + This is a workaround to obtain the "genome.fa" file that + corresponds to the dbkey of the alignments. + Because this file is "calculated" during run-time, it can + be used in a workflow. + *# + "${ filter( lambda x: str( x[0] ) == str( { alignment.metadata.dbkey:True for alignment in $alignments }.keys()[0] ), $__app__.tool_data_tables[ 'gene_sets' ].get_fields() )[0][2] }" + #end if + + -o "$output" + -T \${GALAXY_SLOTS:-2} + + #if $extended_parameters.parameters == "extended" + -t $extended_parameters.gff_feature_type + -g $extended_parameters.gff_feature_attribute + $extended_parameters.summarization_level + $extended_parameters.contribute_to_multiple_features + $extended_parameters.protocol + $extended_parameters.multimapping_counts + -Q $extended_parameters.mapping_quality + $extended_parameters.fragment_counting + $extended_parameters.check_distance + -d $extended_parameters.minimum_fragment_length + -D $extended_parameters.maximum_fragment_length + $extended_parameters.only_both_ends + $extended_parameters.exclude_chimerics + $extended_parameters.namesort + #end if + + #for $alignment in $alignments + ${alignment} + #end for + + 2>&1 + + #set $columns = [str(i+7) for i, alignment in enumerate($alignments)] + #set $columns=",".join($columns) + + #if $format == "tabdel_default" or $format.value == "tabdel_default" + ; cp $output tmp.txt + ; egrep -v "^#" tmp.txt > tmp2.txt + ; cut -f 1,$columns tmp2.txt > tmp_left.txt + ; cut -f 6 tmp2.txt > tmp_right.txt + ; paste tmp_left.txt tmp_right.txt > $output + #elif $format == "tabdel_short" or $format.value == "tabdel_short" + ; cp $output tmp.txt + ; egrep -v "^#" tmp.txt | cut -f 1,$columns > $output + #end if + + ## For every alignment, replace its filename for: "hid: sample name" + #for $alignment in $alignments + #set $alignment_escaped = str($alignment).replace('/', '\/').replace('.', '\.') + #set $alignment_name_escaped = str(alignment.hid)+": "+str($alignment.name).replace('\t',' ').replace('\\','\\\\').replace("'","\\'").replace('/','\/') + + #if $format.value == "tabdel_default" or $format.value == "tabdel_short" + ; sed -e '1 s/$alignment_escaped/${alignment_name_escaped}/g' $output > tmp.txt + #elif $format.value == "bed": + ; featurecounts2bed.sh -f "$output" > tmp.txt + #else + ; sed -e '1,2 s/$alignment_escaped/${alignment_name_escaped}/g' $output > tmp.txt + #end if + + ; mv tmp.txt $output + + ; sed -e '1 s/$alignment_escaped/${alignment_name_escaped}/g' $output".summary" > tmp.txt + ; mv tmp.txt $output".summary" + #end for + ; mv $output".summary" $output_summary + #end if + #end if + ]]></command> + + <inputs> + <param name="alignments" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) where the gene expression has to be counted. The file can have a SAM or BAM format; but ALL files in the series must be in THE SAME format." multiple="true" /> + + <!-- Find out how to access the the GTF/GFF file(s) --> + <conditional name="reference_gene_sets_source"> + <param name="source_select" type="select" label="GFF/GTF Source"> + <option value="indexed_filtered">Use a built-in index (which fits your reference)</option> + <option value="history">Use reference from the history</option> + <option value="indexed_all">Use a built-in index (entire list) - avoid this option if possible; only useful if you design a workflow</option> + <option value="attribute">Use a built-in index based on the 'metadata.dbkey' attribute; ideal in workflows</option> + </param> + <when value="indexed_filtered"> + <param name="reference_gene_sets" type="select" label="Reference Gene Sets used during alignment (GFF/GTF)" > + <options from_data_table="gene_sets"><!-- replaces 'from_file="gene_sets"' - more strict --> + <column name="name" index="0"/> + <column name="dbkey" index="1"/> + <column name="value" index="2"/> + <filter type="data_meta" ref="alignments" multiple="false" key="dbkey" column="1" /> + <validator type="no_options" message="No indexes are available for the selected input dataset" /> + </options> + </param> + </when> + <when value="history"> + <param name="reference_gene_sets" format="gff" type="data" label="Gene annotation file" help="The program assumes that the provided annotation file is in GTF format. Make sure that the gene annotation file corresponds to the same reference genome as used for the alignment." /> + </when> + <when value="indexed_all"> + <param name="reference_gene_sets" type="select" label="Reference Gene Sets used during alignment (GFF/GTF)" > + <options from_data_table="gene_sets"><!-- replaces 'from_file="gene_sets"' - more strict --> + <column name="name" index="0"/> + <column name="dbkey" index="1"/> + <column name="value" index="2"/> + <validator type="no_options" message="No indexes are available for the selected input dataset" /> + </options> + </param> + </when> + <when value="attribute"> + <!-- Do nothing, determine GTF/GFF file at runtime --> + </when> + </conditional> + + <param name="format" type="select" label="Output format"> + <option value="complex">featureCounts 1.4.0+ default (extensive; complex)</option> + <option value="tabdel_default" selected="true">Gene-name "\t" gene-count "\t" gene-length (tab-delimited)</option> + <option value="tabdel_short">Gene-name "\t" gene-count (tab-delimited)</option> + <option value="bed">BED format (line per exon): chr "\t" start "\t" stop "\t" description "\t" readcount (tab-delimited)</option> + </param> + + <conditional name="extended_parameters"> + <param name="parameters" type="select" label="featureCounts parameters" help="For more advanced featureCounts settings."> + <option value="default">Default settings</option> + <option value="extended">Extended settings</option> + </param> + <when value="default"> + </when> + <when value="extended"> + <param name="gff_feature_type" type="text" value="exon" label="GFF feature type filter" help="Specify the feature type. Only rows which have the matched matched feature type in the provided GTF annotation file will be included for read counting. `exon' by default." /> + + <param name="gff_feature_attribute" type="text" value="gene_id" label="GFF gene identifier" help="Specify the attribute type used to group features (eg. exons) into meta-features (eg. genes), when GTF annotation is provided. `gene_id' by default. This attribute type is usually the gene identifier. This argument is useful for the meta-feature level summarization." /> + + <param name ="summarization_level" type="boolean" truevalue=" -f" falsevalue="" label="On feature level" help="If specified, read summarization will be performed at the feature level. By default (-f is not specified), the read summarization is performed at the meta-feature level." /> + + <param name ="contribute_to_multiple_features" type="boolean" truevalue=" -O" falsevalue="" label="Allow read to contribute to multiple features" help="If specified, reads (or fragments if -p is specified) will be allowed to be assigned to more than one matched meta- feature (or matched feature if -f is specified)" /> + + <param name="protocol" type="select" label="Strand specific protocol" help="Indicate if strand-specific read counting should be performed. It has three possible values: 0 (unstranded), 1 (stranded) and 2 (reversely stranded). 0 by default."> + <option value=" -s 0" selected="true">Unstranded</option> + <option value=" -s 1">Stranded (forwards)</option> + <option value=" -s 2">Stranded (reverse)</option> + </param> + + <param name="multimapping_counts" type="boolean" truevalue=" -M" falsevalue="" label="Count multi-mapping reads/fragments" help="If specified, multi-mapping reads/fragments will be counted (ie. a multi-mapping read will be counted up to N times if it has N reported mapping locations). The program uses the `NH' tag to find multi-mapping reads." /> + + <param name="mapping_quality" type="integer" value="0" label="Minimum read quality" help="The minimum mapping quality score a read must satisfy in order to be counted. For paired-end reads, at least one end should satisfy this criteria. 0 by default." /> + + <param name="fragment_counting" type="boolean" truevalue=" -p" falsevalue="" label="PE: Count fragments instead of reads" help="Paired-end specific: If specified, fragments (or templates) will be counted instead of reads. The two reads from the same fragment must be adjacent to each other in the provided SAM/BAM file. If SAM/BAM input does not meet this requirement, the -S (sorting) option should be provided as well." /> + + <param name="check_distance" type="boolean" truevalue=" -P" falsevalue="" label="PE: Check paired-end distance" help="Paired-end specific: If specified, paired-end distance will be checked when assigning fragments to meta-features or features. This option is only applicable when -p (Count fragments instead of reads) is specified. The distance thresholds should be specified using -d and -D (minimum and maximum fragment/template length) options." /> + + <param name="minimum_fragment_length" type="integer" value="50" label="PE: Minimum fragment/template length." /> + <param name="maximum_fragment_length" type="integer" value="600" label="PE: Maximum fragment/template length." /> + + <param name="only_both_ends" type="boolean" truevalue=" -B" falsevalue="" label="PE: only allow fragments with both reads aligned" help="Paired-end specific: If specified, only fragments that have both ends successfully aligned will be considered for summarization. This option is only applicable for paired-end reads." /> + + <param name="exclude_chimerics" type="boolean" truevalue=" -C" falsevalue="" label="PE: Exclude chimeric fragments" help="Paired-end specific: If specified, the chimeric fragments (those fragments that have their two ends aligned to different chromosomes) will NOT be included for summarization. This option is only applicable for paired-end read data." /> + + <param name="namesort" type="boolean" truevalue=" -S" falsevalue="" label="PE: Name-sort reads (slow!)" help="Paired-end specific: If specified, the program will reorder input reads according to their names and make reads from the same pair be adjacent to each other. This option should be provided when reads from the same pair are not adjacent to each other in input SAM/BAM files (for instance sorting reads by chromosomal locations could decouple reads from the same pair)." /> + </when> + </conditional> + </inputs> + + <outputs> + <data format="tabular" name="output" label="${tool.name} on ${', '.join([ str(a.hid)+': '+a.name for a in $alignments ])}" /> + <data format="tabular" name="output_summary" label="${tool.name} on ${', '.join([ str(a.hid)+': '+a.name for a in $alignments ])} summary" /> + </outputs> + + <tests> + <test> + <param name="alignments" value="featureCounts_input1.bam,featureCounts_input2.bam" ftype="bam" /> + <param name="source_select" value="history" /> + <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" /> + <output name="output" file="output.tab"/> + <output name="output_summary" file="output_summary.tab"/> + </test> + </tests> + + <help><![CDATA[ featureCounts ############# @@ -252,8 +248,6 @@ More tools by the Translational Research IT (TraIT) project can be found in the following toolsheds: -http://toolshed.dtls.nl/ - http://toolshed.g2.bx.psu.edu/ http://testtoolshed.g2.bx.psu.edu/ @@ -271,9 +265,9 @@ Acknowledgements ---------------- -I would like to thank Marius van den Beek for his contributions to this project. -</help> - <citations> - <citation type="doi">10.1093/bioinformatics/btt656</citation> - </citations> +I would like to thank Marius van den Beek for his contribution to this galaxy wrapper. + ]]></help> + <citations> + <citation type="doi">10.1093/bioinformatics/btt656</citation> + </citations> </tool>
--- a/featurecounts2bed.sh Mon Jun 01 07:18:31 2015 -0400 +++ b/featurecounts2bed.sh Thu Sep 10 05:11:49 2015 -0400 @@ -19,10 +19,6 @@ # Medical Center (Rotterdam, Netherlands) on behalf of the Translational # Research IT (TraIT) project: # http://www.ctmm.nl/en/programmas/infrastructuren/traitprojecttranslationeleresearch -# -# More tools by the Translational Research IT (TraIT) project can be -# found in the following repository: -# http://toolshed.dtls.nl/ exon_level="true"
--- a/tool_dependencies.xml Mon Jun 01 07:18:31 2015 -0400 +++ b/tool_dependencies.xml Thu Sep 10 05:11:49 2015 -0400 @@ -1,21 +1,24 @@ <?xml version="1.0"?> <tool_dependency> - <package name="featurecounts" version="1.4.6.p1"> - <repository changeset_revision="a4c247fdd71b" name="package_featurecounts_1_4_6" owner="yhoogstrate" toolshed="https://toolshed.g2.bx.psu.edu" /> - </package> - - <package name="featurecounts2bed" version="1.0.0"> - <install version="1.0"> - <actions> - <action type="shell_command">mkdir $INSTALL_DIR/bin ; cp $REPOSITORY_INSTALL_DIR/featurecounts2bed.sh $INSTALL_DIR/bin/</action> - <action type="chmod"> - <file mode="755">$INSTALL_DIR/bin/featurecounts2bed.sh</file> - </action> - <action type="set_environment"> - <environment_variable action="prepend_to" name="PATH">$INSTALL_DIR/bin</environment_variable> - <environment_variable action="prepend_to" name="PATH">$REPOSITORY_INSTALL_DIR</environment_variable> - </action> - </actions> - </install> - </package> + <package name="featurecounts" version="1.4.6.p1"> + <repository changeset_revision="42796f06052f" name="package_featurecounts_1_4_6" owner="yhoogstrate" toolshed="https://toolshed.g2.bx.psu.edu" /> + </package> + + <package name="featurecounts2bed" version="1.0.0"> + <install version="1.0"> + <actions> + <action type="shell_command"> + mkdir $INSTALL_DIR/bin && + cp $REPOSITORY_INSTALL_DIR/featurecounts2bed.sh $INSTALL_DIR/bin/ + </action> + <action type="chmod"> + <file mode="755">$INSTALL_DIR/bin/featurecounts2bed.sh</file> + </action> + <action type="set_environment"> + <environment_variable action="prepend_to" name="PATH">$INSTALL_DIR/bin</environment_variable> + <environment_variable action="prepend_to" name="PATH">$REPOSITORY_INSTALL_DIR</environment_variable> + </action> + </actions> + </install> + </package> </tool_dependency>