comparison hisat2.xml @ 29:26371a1df031 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hisat2 commit f18e8826ecb395a40fc321b5f3b66ab6d7f51625"

28:d4b55e2beb12

<tool id="hisat2" name="HISAT2" version="2.1.0+galaxy6" profile="17.01">
    <description>A fast and sensitive alignment program</description>
    <macros>
        <import>hisat2_macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="2.1.0">hisat2</requirement>
        <requirement type="package" version="1.9">samtools</requirement>
        <requirement type="package" version="1.3">seqtk</requirement>
    </requirements>
    <stdio>
        <regex level="fatal" match="hisat2-align exited with value 1" source="both" />
        <regex level="fatal" match="hisat2: not found" source="both" />

    #if str($adv.reporting_options.max_primary) != '':
        -k ${adv.reporting_options.max_primary}
    #end if
#end if


## Other options

#if str( $adv.other_options.other_options_selector ) == "advanced":
    ${adv.other_options.non_deterministic}

                </when>
            </conditional>

        <!-- Summary Options -->
        <section name="sum" title="Summary Options" expanded="False">
            <param name="new_summary" argument="--new-summary" type="boolean" checked="False" label="Output alignment summary in a more machine-friendly style." help="Select this option for compatibility with MultiQC" />
            <param name="summary_file" argument="--summary-file" type="boolean" checked="False" label="Print alignment summary to a file." help="Output alignment summary to a file in addition to stderr." />
        </section>

        <!-- Advanced Options  -->
        <section name="adv" title="Advanced Options" expanded="False">
            <conditional name="input_options">

                    <param name="trim3" argument="-3" type="integer" min="0" value="0" label="Trim 3' end" help="Trim N bases from 3' (right) end of each read before alignment, default: 0"/>
                    <param name="qv_encoding" type="select" display="radio" label="Select quality score encoding" help="See help below for more details">
                         <option value="--phred33" selected="True">Input qualities are ASCII chars equal to the Phred quality plus 33. This is also called the "Phred+33" encoding, which is used by the very latest Illumina pipelines (--phred33)</option>
                         <option value="--phred64">Input qualities are ASCII chars equal to the Phred quality plus 64. This is also called the "Phred+64" encoding (--phred64)</option>
                    </param>
                    <param name="solexa_quals" argument="--solexa-quals" type="boolean" truevalue="--solexa-quals" falsevalue="" checked="False" label="Convert input qualities from Solexa (which can be negative) to Phred (which can't). This scheme was used in older Illumina GA Pipeline versions (prior to 1.3)" help="--solexa-quals; default: False"/>
                    <param name="int_quals" argument="--int-quals" type="boolean" truevalue="--int-quals" falsevalue="" checked="False" label="Are quality values provided as space separated integers?" help="Quality values are represented in the read input file as space-separated ASCII integers, e.g., 40 40 30 40..., rather than ASCII characters, e.g., II?I.... Integers are treated as being on the Phred quality scale unless --solexa-quals is also specified [default: False]"/>
                </when>
            </conditional>

            <conditional name="alignment_options">
                <param name="alignment_options_selector" type="select" label="Alignment options">

                    <option value="defaults">Use default values</option>
                    <option value="advanced">Specify output options</option>
                </param>
                <when value="defaults" />
                <when value="advanced">
                    <param name="unaligned_file" argument="--un/--un-conc" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write unaligned reads (in fastq format) to separate file(s)" help="This triggers --un parameter for single reads and --un-conc for paired reads" />
                    <param name="aligned_file" argument="--al/--al-conc" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write aligned reads (in fastq format) to separate file(s)" help="This triggers --al parameter for single reads and --al-conc for paired reads" />
                </when>
            </conditional>

            <conditional name="other_options">
                <param name="other_options_selector" type="select" label="Other options">
                    <option value="defaults">Use default values</option>

            <param name="rna_strandness" value="R" />
            <param name="adv|spliced_options|spliced_options_selector" value="advanced"/>
            <param name="adv|spliced_options|novel_splicesite_outfile" value="true" />
            <output name="output_alignments" file="hisat_output_spliced_1.bam" ftype="bam" lines_diff="2" />
            <output name="novel_splicesite_output" file="novel_splicesite_out.tab" ftype="tabular" />
        </test>
    </tests>

    <help><![CDATA[
Introduction

            By default, `hisat2` looks for discordant alignments if it cannot find any
            concordant alignments.  A discordant alignment is an alignment where both mates
            align uniquely, but that does not satisfy the paired-end constraints
            (`--fr`/`--rf`/`--ff`, `-I`, `-X`).  This option disables that behavior.


**Output options**::

    --un/--un-gz/--un-bz2
            Write unpaired reads that fail to align to file at `<path>`. These reads correspond to the SAM records with the FLAGS `0x4` bit set and neither the `0x40` nor `0x80` bits set. If `--un-gz` is specified, output will be gzip compressed. If `--un-bz2` is specified, output will be bzip2 compressed. Reads written in this way will appear exactly as they did in the input file, without any modification (same sequence, same name, same quality string, same quality encoding). Reads will not necessarily appear in the same order as they did in the input.

29:26371a1df031

<tool id="hisat2" name="HISAT2" version="2.1.0+galaxy7" profile="17.01">
    <description>A fast and sensitive alignment program</description>
    <macros>
        <import>hisat2_macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="2.1.0">hisat2</requirement>
        <requirement type="package" version="1.11">samtools</requirement>
        <requirement type="package" version="1.3">seqtk</requirement>
    </requirements>
    <stdio>
        <regex level="fatal" match="hisat2-align exited with value 1" source="both" />
        <regex level="fatal" match="hisat2: not found" source="both" />

    #if str($adv.reporting_options.max_primary) != '':
        -k ${adv.reporting_options.max_primary}
    #end if
#end if


## SAM options

#if str($adv.sam_options.sam_options_selector) == "advanced":
    #if $adv.sam_options.no_unal:
        --no-unal
    #end if
    #if str($adv.sam_options.read_groups.rg_labels) == "Yes":
        --rg-id '$adv.sam_options.read_groups.rg_id'
        #if len('$adv.sam_options.read_groups.read_groups'):
            #for $i, $id in enumerate($adv.sam_options.read_groups.read_groups):
                --rg '$id.rg'
            #end for
        #end if
    #end if
    $adv.sam_options.chr_text
    #if $adv.sam_options.omit_sec_seq:
        --omit-sec-seq
    #end if
#end if

## Other options

#if str( $adv.other_options.other_options_selector ) == "advanced":
    ${adv.other_options.non_deterministic}

                </when>
            </conditional>

        <!-- Summary Options -->
        <section name="sum" title="Summary Options" expanded="False">
            <param name="new_summary" argument="--new-summary" type="boolean" checked="false" label="Output alignment summary in a more machine-friendly style." help="Select this option for compatibility with MultiQC" />
            <param name="summary_file" argument="--summary-file" type="boolean" checked="false" label="Print alignment summary to a file." help="Output alignment summary to a file in addition to stderr." />
        </section>

        <!-- Advanced Options  -->
        <section name="adv" title="Advanced Options" expanded="False">
            <conditional name="input_options">

                    <param name="trim3" argument="-3" type="integer" min="0" value="0" label="Trim 3' end" help="Trim N bases from 3' (right) end of each read before alignment, default: 0"/>
                    <param name="qv_encoding" type="select" display="radio" label="Select quality score encoding" help="See help below for more details">
                         <option value="--phred33" selected="True">Input qualities are ASCII chars equal to the Phred quality plus 33. This is also called the "Phred+33" encoding, which is used by the very latest Illumina pipelines (--phred33)</option>
                         <option value="--phred64">Input qualities are ASCII chars equal to the Phred quality plus 64. This is also called the "Phred+64" encoding (--phred64)</option>
                    </param>
                    <param name="solexa_quals" argument="--solexa-quals" type="boolean" truevalue="--solexa-quals" falsevalue="" checked="false" label="Convert input qualities from Solexa (which can be negative) to Phred (which can't). This scheme was used in older Illumina GA Pipeline versions (prior to 1.3)" help="--solexa-quals; default: False"/>
                    <param name="int_quals" argument="--int-quals" type="boolean" truevalue="--int-quals" falsevalue="" checked="false" label="Are quality values provided as space separated integers?" help="Quality values are represented in the read input file as space-separated ASCII integers, e.g., 40 40 30 40..., rather than ASCII characters, e.g., II?I.... Integers are treated as being on the Phred quality scale unless --solexa-quals is also specified [default: False]"/>
                </when>
            </conditional>

            <conditional name="alignment_options">
                <param name="alignment_options_selector" type="select" label="Alignment options">

                    <option value="defaults">Use default values</option>
                    <option value="advanced">Specify output options</option>
                </param>
                <when value="defaults" />
                <when value="advanced">
                    <param name="unaligned_file" argument="--un/--un-conc" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Write unaligned reads (in fastq format) to separate file(s)" help="This triggers --un parameter for single reads and --un-conc for paired reads" />
                    <param name="aligned_file" argument="--al/--al-conc" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Write aligned reads (in fastq format) to separate file(s)" help="This triggers --al parameter for single reads and --al-conc for paired reads" />
                </when>
            </conditional>

            <conditional name="sam_options">
                <param name="sam_options_selector" type="select" label="SAM options">
                    <option value="defaults">Use default values</option>
                    <option value="advanced">Specify output options</option>
                </param>
                <when value="defaults" />
                <when value="advanced">
                    <param name="no_unal" argument="--no-unal" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Suppress SAM records for reads that failed to align." help="Default: false"/>
                    <conditional name="read_groups">
                        <param name="rg_labels" type="select" label="Edit Read Group IDs">
                            <option value="No" />
                            <option value="Yes" />
                        </param>
                        <when value="No"/>
                        <when value="Yes">
                            <param name="rg_id" argument="--rg-id" type="text" value="read_group" label="Read Group ID" help="Set the read group ID to the value set here. This causes the SAM @RG header line to be printed, with this input value as the value associated with the ID: tag. It also causes the RG:Z: extra field to be attached to each SAM output record, with value set to the value set here." /> 
                            <repeat name="read_groups" title="Read Groups text">
                                <param name="rg" argument="--rg" type="text" optional="true" label="Read Group text" help="Add specified text (usually of the form TAG:VAL, e.g. SM:Pool1) as a field on the @RG header line. Note: in order for the @RG line to appear, Read Group ID must also be specified. This is because the ID tag is required by the SAM Spec. Specify --rg multiple times to set multiple fields. See the SAM Spec for details about what fields are legal." /> 
                            </repeat>               
                        </when>
                    </conditional>
                    <param name="chr_text" type="select" label="Add/remove 'chr' from reference names in alignment files">
                        <option value="" selected="true">Use default values</option>
                        <option value="--remove-chrname">Remove ‘chr’ from reference names in alignment (e.g., chr18 to 18)</option>
                        <option value="--add-chrname">Add ‘chr’ to reference names in alignment (e.g., 18 to chr18)</option>
                    </param>
                    <param name="omit_sec_seq" argument="--omit-sec-seq" type="boolean" truevalue="true" falsevalue="false" checked="false" label="When printing secondary alignments, HISAT2 by default will write out the SEQ and QUAL strings. Specifying this option causes HISAT2 to print an asterisk in those fields instead." help="Default: false"/>
                </when>     
            </conditional>

            <conditional name="other_options">
                <param name="other_options_selector" type="select" label="Other options">
                    <option value="defaults">Use default values</option>

            <param name="rna_strandness" value="R" />
            <param name="adv|spliced_options|spliced_options_selector" value="advanced"/>
            <param name="adv|spliced_options|novel_splicesite_outfile" value="true" />
            <output name="output_alignments" file="hisat_output_spliced_1.bam" ftype="bam" lines_diff="2" />
            <output name="novel_splicesite_output" file="novel_splicesite_out.tab" ftype="tabular" />
        </test>
        <!-- Ensure SAM output settings work -->
        <test expect_num_outputs="1" >
            <param name="type" value="paired_interleaved" />
            <param name="source" value="history" />
            <param name="history_item" ftype="fasta" value="phiX.fa" />
            <param name="input_1" ftype="fastqsanger.bz2" value="hisat_input_1_interleaved.fastq.bz2" />
            <param name="adv|sam_options|sam_options_selector" value="advanced"/>
            <param name="adv|sam_options|no_unal" value="true"/>
            <param name="adv|sam_options|read_groups|rg_labels" value="Yes"/>
            <repeat name="adv|sam_options|read_groups|read_groups">
                <param name="rg" value="BC:test1"/> 
            </repeat> 
            <repeat name="adv|sam_options|read_groups|read_groups">
                <param name="rg" value="CN:test2"/>  
            </repeat>          
            <param name="adv|sam_options|chr_text" value="--add-chrname"/>
            <param name="adv|sam_options|omit_sec_seq" value="True"/>                        
            <output name="output_alignments" file="hisat_output_5.bam" ftype="bam" lines_diff="2" />
        </test>
    </tests>

    <help><![CDATA[
Introduction

            By default, `hisat2` looks for discordant alignments if it cannot find any
            concordant alignments.  A discordant alignment is an alignment where both mates
            align uniquely, but that does not satisfy the paired-end constraints
            (`--fr`/`--rf`/`--ff`, `-I`, `-X`).  This option disables that behavior.

-----

** SAM options

    --no-unal
        Suppress SAM records for reads that failed to align.
    --rg-id <text>

        Set the read group ID to <text>. This causes the SAM @RG header line to be printed, with <text> as the value associated with the ID: tag. It also causes the RG:Z: extra field to be attached to each SAM output record, with value set to <text>.
    --rg <text>
        Add <text> (usually of the form TAG:VAL, e.g. SM:Pool1) as a field on the @RG header line. Note: in order for the @RG line to appear, --rg-id must also be specified. This is because the ID tag is required by the SAM Spec. Specify --rg multiple times to set multiple fields. See the SAM Spec for details about what fields are legal.
    
    --remove-chrname
        Remove ‘chr’ from reference names in alignment (e.g., chr18 to 18)
    
    --add-chrname
        Add ‘chr’ to reference names in alignment (e.g., 18 to chr18)
    
    --omit-sec-seq
        When printing secondary alignments, HISAT2 by default will write out the SEQ and QUAL strings. Specifying this option causes HISAT2 to print an asterisk in those fields instead.

-----

**Output options**::

    --un/--un-gz/--un-bz2
            Write unpaired reads that fail to align to file at `<path>`. These reads correspond to the SAM records with the FLAGS `0x4` bit set and neither the `0x40` nor `0x80` bits set. If `--un-gz` is specified, output will be gzip compressed. If `--un-bz2` is specified, output will be bzip2 compressed. Reads written in this way will appear exactly as they did in the input file, without any modification (same sequence, same name, same quality string, same quality encoding). Reads will not necessarily appear in the same order as they did in the input.