comparison htseq-count.xml @ 18:737cda668bdd draft

planemo upload for repository https://github.com/lparsons/galaxy_tools/tree/master/tools/htseq_count commit 7ed7ce73afea50d212c9470fd3b98a232e312502

17:3102bfcac0d6

<tool id="htseq_count" name="htseq-count" version="0.4.1">
    <description> - Count aligned reads in a BAM file that overlap features in a GFF file</description>
    <version_command>htseq-count -h | grep version | sed 's/^\(.*\)*\(version .*\)\./\2/'</version_command>
    <requirements>
        <requirement type="package" version="1.7.1">numpy</requirement>
        <requirement type="package" version="0.6.1">htseq</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
        <requirement type="package" version="0.7.7">pysam</requirement>
    </requirements>
    <command>
    ##set up input files
    #set $reference_fasta_filename = "localref.fa"
    #if $samout_conditional.samout:
        #if str( $samout_conditional.reference_source.reference_source_selector ) == "history":

            samtools faidx "${reference_fasta_filename}" 2>&1 || echo "Error running samtools faidx for htseq-count" >&2 &&
        #else:
            #set $reference_fasta_filename = str( $samout_conditional.reference_source.ref_file.fields.path )
        #end if
    #end if
    htseq-count 
    --format=$samfile.extension
    --order=pos
    --mode=$mode 
    --stranded=$stranded 
    --minaqual=$minaqual 
    --type=$featuretype 
    --idattr=$idattr 
    #if $samout_conditional.samout:
        --samout=$__new_file_path__/${samoutfile.id}_tmp
    #end if
    $samfile
    $gfffile 
    | awk '{if ($1 ~ "no_feature|ambiguous|too_low_aQual|not_aligned|alignment_not_unique") print $0 | "cat 1>&2"; else print $0}' > $counts 2>$othercounts
    #if $samout_conditional.samout:
        && samtools view -Su -t ${reference_fasta_filename}.fai $__new_file_path__/${samoutfile.id}_tmp | samtools sort -o - sorted > $samoutfile
    #end if</command>
    <inputs>
        <param format="sam,bam" name="samfile" type="data" label="Aligned SAM/BAM File"/>
        <param format="gff" name="gfffile" type="data" label="GFF File"/>
        <param name="mode" type="select" label="Mode">
            <help>Mode to handle reads overlapping more than one feature.</help>

        </param>
        <conditional name="samout_conditional">
            <param name="samout" type="boolean" value="False" truevalue="True" falsevalue="False" label="Additional BAM Output">
                <help>Write out all SAM alignment records into an output BAM file, annotating each line with its assignment to a feature or a special counter (as an optional field with tag ‘XF’).</help>
            </param>
            <when value="True">       
                <conditional name="reference_source">
                    <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
                        <option value="cached">Locally cached</option>
                        <option value="history">History</option>
                    </param>

        <data format="bam" name="samoutfile" metadata_source="samfile" label="${tool.name} on ${on_string} (BAM)">
            <filter>samout_conditional['samout']</filter>
        </data>
    </outputs>

    <stdio>
        <exit_code range="1:" level="fatal" description="Unknown error occurred" />
        <regex match="htseq-count: command not found" source="stderr" level="fatal" description="The HTSeq python package is not properly installed, contact Galaxy administrators" />
        <regex match="samtools: command not found" source="stderr" level="fatal" description="The samtools package is not properly installed, contact Galaxy administrators" />
        <regex match="Error: Feature (.+) does not contain a '(.+)' attribute" source="both" level="fatal" description="Error parsing the GFF file, at least one feature of the specified 'Feature type' does not have a value for the specified 'ID Attribute'" />
        <regex match="Error occured in line (\d+) of file" source="stderr" level="fatal" description="Unknown error parsing the GFF file" />
        <regex match="Error" source="stderr" level="fatal" description="Unknown error occured" />
        <regex match="Warning: Read (.+) claims to have an aligned mate which could not be found. \(Is the SAM file properly sorted\?\)" source="stderr" level="warning" description="PAIRED DATA MISSING OR NOT PROPERLY SORTED. Try reruning and selecting the paired-end option. See stderr output of this dataset for more information." />
    </stdio>

    <tests>
        <test>
            <param name="samfile" value="htseq-test.sam" />
            <param name="gfffile" value="htseq-test.gff" />
            <param name="samout" value="False" />

    <help>
Overview
--------

This tool takes an alignment file in SAM or BAM format and feature file in GFF format
and calculates the number of reads mapping to each feature. It uses the *htseq-count* 
script that is part of the HTSeq python module. See
http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details.

A feature is an interval (i.e., a range of positions) on a chromosome or a union of
such intervals.  In the case of RNA-Seq, the features are typically genes, where 
each gene is considered here as the union of all its exons. One may also consider 
each exon as a feature, e.g., in order to check for alternative splicing. For 
comparative ChIP-Seq, the features might be binding regions from a pre-determined 
list.


Overlap Modes
-------------

Special care must be taken to decide how to deal with reads that overlap more than one feature. 

The htseq-count script allows to choose between three modes: *union*, *intersection-strict*, and *intersection-nonempty*.

The following figure illustrates the effect of these three modes:

Written by Simon Anders ([e-mail]), European Molecular Biology
Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General
Public License v3. Part of the 'HTSeq' framework.
    </help>
</tool>

18:737cda668bdd

<tool id="htseq_count" name="htseq-count" version="0.4.1">
    <description> - Count aligned reads in a BAM file that overlap features in a GFF file</description>
    <requirements>
        <requirement type="package" version="0.6.1">htseq</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
        <requirement type="package" version="0.7.7">pysam</requirement>
    </requirements>

    <stdio>
        <exit_code range="1:" level="fatal" description="Unknown error occurred" />
        <regex match="htseq-count: (command ){0,1}not found" source="stderr" level="fatal" description="The HTSeq python package is not properly installed, contact Galaxy administrators" />
        <regex match="samtools: (command ){0,1}not found" source="stderr" level="fatal" description="The samtools package is not properly installed, contact Galaxy administrators" />
        <regex match="Error: Feature (.+) does not contain a '(.+)' attribute" source="both" level="fatal" description="Error parsing the GFF file, at least one feature of the specified 'Feature type' does not have a value for the specified 'ID Attribute'" />
        <regex match="Error occured in line (\d+) of file" source="stderr" level="fatal" description="Unknown error parsing the GFF file" />
        <regex match="Error" source="stderr" level="fatal" description="Unknown error occured" />
        <regex match="Warning: Read (.+) claims to have an aligned mate which could not be found. \(Is the SAM file properly sorted\?\)" source="stderr" level="warning" description="PAIRED DATA MISSING OR NOT PROPERLY SORTED. Try reruning and selecting the paired-end option. See stderr output of this dataset for more information." />
    </stdio>

    <version_command>htseq-count -h | grep version | sed 's/^\(.*\)*\(version .*\)\./\2/'</version_command>

    <command>
    ##set up input files
    #set $reference_fasta_filename = "localref.fa"
    #if $samout_conditional.samout:
        #if str( $samout_conditional.reference_source.reference_source_selector ) == "history":

            samtools faidx "${reference_fasta_filename}" 2>&1 || echo "Error running samtools faidx for htseq-count" >&2 &&
        #else:
            #set $reference_fasta_filename = str( $samout_conditional.reference_source.ref_file.fields.path )
        #end if
    #end if
    htseq-count
    --format=$samfile.extension
    --order=pos
    --mode=$mode
    --stranded=$stranded
    --minaqual=$minaqual
    --type=$featuretype
    --idattr=$idattr
    #if $samout_conditional.samout:
        --samout=$__new_file_path__/${samoutfile.id}_tmp
    #end if
    $samfile
    $gfffile
    | awk '{if ($1 ~ "no_feature|ambiguous|too_low_aQual|not_aligned|alignment_not_unique") print $0 | "cat 1>&2"; else print $0}' > $counts 2>$othercounts
    #if $samout_conditional.samout:
        && samtools view -Su -t ${reference_fasta_filename}.fai $__new_file_path__/${samoutfile.id}_tmp | samtools sort -o - sorted > $samoutfile
    #end if</command>

    <inputs>
        <param format="sam,bam" name="samfile" type="data" label="Aligned SAM/BAM File"/>
        <param format="gff" name="gfffile" type="data" label="GFF File"/>
        <param name="mode" type="select" label="Mode">
            <help>Mode to handle reads overlapping more than one feature.</help>

        </param>
        <conditional name="samout_conditional">
            <param name="samout" type="boolean" value="False" truevalue="True" falsevalue="False" label="Additional BAM Output">
                <help>Write out all SAM alignment records into an output BAM file, annotating each line with its assignment to a feature or a special counter (as an optional field with tag ‘XF’).</help>
            </param>
            <when value="True">
                <conditional name="reference_source">
                    <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
                        <option value="cached">Locally cached</option>
                        <option value="history">History</option>
                    </param>

        <data format="bam" name="samoutfile" metadata_source="samfile" label="${tool.name} on ${on_string} (BAM)">
            <filter>samout_conditional['samout']</filter>
        </data>
    </outputs>

    <tests>
        <test>
            <param name="samfile" value="htseq-test.sam" />
            <param name="gfffile" value="htseq-test.gff" />
            <param name="samout" value="False" />

    <help>
Overview
--------

This tool takes an alignment file in SAM or BAM format and feature file in GFF format
and calculates the number of reads mapping to each feature. It uses the *htseq-count*
script that is part of the HTSeq python module. See
http://www-huber.embl.de/users/anders/HTSeq/doc/count.html for details.

A feature is an interval (i.e., a range of positions) on a chromosome or a union of
such intervals.  In the case of RNA-Seq, the features are typically genes, where
each gene is considered here as the union of all its exons. One may also consider
each exon as a feature, e.g., in order to check for alternative splicing. For
comparative ChIP-Seq, the features might be binding regions from a pre-determined
list.


Overlap Modes
-------------

Special care must be taken to decide how to deal with reads that overlap more than one feature.

The htseq-count script allows to choose between three modes: *union*, *intersection-strict*, and *intersection-nonempty*.

The following figure illustrates the effect of these three modes:

Written by Simon Anders ([e-mail]), European Molecular Biology
Laboratory (EMBL). (c) 2010. Released under the terms of the GNU General
Public License v3. Part of the 'HTSeq' framework.
    </help>
    <citations>
        <citation type="bibtex">
@article{anders_htseqpython_2015,
    title = {{HTSeq}—a {Python} framework to work with high-throughput sequencing data},
    volume = {31},
    issn = {1367-4803, 1460-2059},
    url = {http://bioinformatics.oxfordjournals.org/content/31/2/166},
    doi = {10.1093/bioinformatics/btu638},
    abstract = {Motivation: A large choice of tools exists for many standard tasks in the analysis of high-throughput sequencing (HTS) data. However, once a project deviates from standard workflows, custom scripts are needed.
Results: We present HTSeq, a Python library to facilitate the rapid development of such scripts. HTSeq offers parsers for many common data formats in HTS projects, as well as classes to represent data, such as genomic coordinates, sequences, sequencing reads, alignments, gene model information and variant calls, and provides data structures that allow for querying via genomic coordinates. We also present htseq-count, a tool developed with HTSeq that preprocesses RNA-Seq data for differential expression analysis by counting the overlap of reads with genes.
Availability and implementation: HTSeq is released as an open-source software under the GNU General Public Licence and available from http://www-huber.embl.de/HTSeq or from the Python Package Index at https://pypi.python.org/pypi/HTSeq.
Contact: sanders\{at\}fs.tum.de},
    language = {en},
    number = {2},
    urldate = {2015-04-21},
    journal = {Bioinformatics},
    author = {Anders, Simon and Pyl, Paul Theodor and Huber, Wolfgang},
    month = jan,
    year = {2015},
    pmid = {25260700},
    pages = {166--169},
    file = {Full Text PDF:/Users/lparsons/Library/Application Support/Firefox/Profiles/thd2t4je.default/zotero/storage/84XQB8V6/Anders et al. - 2015 - HTSeq—a Python framework to work with high-through.pdf:application/pdf;Snapshot:/Users/lparsons/Library/Application Support/Firefox/Profiles/thd2t4je.default/zotero/storage/JKUAUCKB/166.html:text/html}
}
        </citation>
    </citations>
</tool>