annotate seqkit_locate.xml @ 2:13604b5e9d30 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/seqkit commit d3d2bb547caccd2d217e5b77d62ea181f8e870c7

<tool id="seqkit_locate" name="SeqKit locate" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>subsequences/motifs, mismatch allowed</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
#import re

#set input_identifier = re.sub('[^\s\w\-]', '_', str($input.element_identifier))
ln -s '${input}' '${input_identifier}' &&

seqkit locate 
--threads \${GALAXY_SLOTS:-4}
#if $conditional_pattern.mode == 'expression'
    --pattern '"$conditional_pattern.pattern"'
    $conditional_pattern.use_regexp
#else
    --pattern-file '$conditional_pattern.pattern_file'
#end if
$output_mode
--validate-seq-length $advanced_options.validate_seq_length
$advanced_options.circular
$advanced_options.degenerate
$advanced_options.hide_matched
$advanced_options.ignore_case
#if not $advanced_options.degenerate
    --max-mismatch $advanced_options.max_mismatch
    $advanced_options.use_fmi
#end if
$advanced_options.non_greedy
$advanced_options.only_positive_strand
$advanced_options.id_ncbi
--seq-type $seq_type
'${input_identifier}'
> '$output'
]]></command>
    <inputs>
        <param name="input" type="data" format="fasta,fasta.gz" label="Input file"/>
        <conditional name="conditional_pattern">
            <param name="mode" type="select" label="Pattern mode" 
                help="Specify a pattern/motif sequence or a FASTA file with the motif of interest. Motifs could be EITHER plain sequence containing 'ACTGN' OR regular
                    expression like 'A[TU]G(?:.{3})+?[TU](?:AG|AA|GA)' for ORFs">
                <option value="expression">Pattern/motif sequence</option>
                <option value="file">FASTA file with the pattern/motif of interest</option>
            </param>
            <when value="expression">
                <param argument="--pattern" type="text" value="" label="Pattern/motif sequence" help="Perl regular expressions are allowed">
                    <sanitizer invalid_char="">
                        <valid initial="string.letters,string.digits">
                        <add value="^"/>
                        <add value="$"/>
                        <add value="("/>
                        <add value=")"/>
                        <add value="|"/>
                        <add value="?"/>
                        <add value="*"/>
                        <add value="+"/>
                        <add value="{"/>
                        <add value="}"/>
                        <add value="\"/>
                        <add value="["/>
                        <add value="]"/>
                        <add value="."/>
                        <add value=","/>
                        </valid>
                    </sanitizer>
                    <validator type="regex" message="Pattern must not end with backslash.">.*[^\\]$</validator>
                </param>
                <param argument="--use-regexp" type="boolean" truevalue="--use-regexp" falsevalue="" checked="false" label="Pattern/motifs are regular expressions"/>
            </when>
            <when value="file">
                <param argument="--pattern-file" type="data" format="fasta" label="Pattern/motif file"/>
            </when>
        </conditional>
        <param argument="--seq-type" type="select" label="Sequence type" help="For automatic detection, it automatically detect by the first sequence. Default: auto">
            <option value="auto">Automatic detection</option>
            <option value="dna">DNA</option>
            <option value="rna">RNA</option>
            <option value="protein">Protein</option>
        </param>
        <param name="output_mode" type="select" label="Output mode">
            <option value="">Tabular (default format)</option>
            <option value="--gtf">GTF</option>
            <option value="--bed">BED6</option>
        </param>
        <section name="advanced_options" title="Advanced options">
            <param argument="--validate-seq-length" type="integer" min="0" value="10000" label="Lenth of the sequence to validate" help="Default: 10000" />
            <param argument="--circular" type="boolean" truevalue="--circular" falsevalue="" checked="false" label="Circular genome" 
                help="When using flag --circular, end position of matched subsequence that crossing genome sequence end would be greater than sequence length" />
            <param argument="--degenerate" type="boolean" truevalue="--degenerate" falsevalue="" checked="false" label="Pattern/motif contains degenerate bases"
                help="Do not use degenerate bases/residues in regular expression, you need convert them to regular expression, e.g., change 'N' or 'X'  to '.'"/>
            <param argument="--hide-matched" type="boolean" truevalue="--hide-matched" falsevalue="" checked="false" label="Do not show matched sequences"/>
            <param argument="--ignore-case" type="boolean" truevalue="--ignore-case" falsevalue="" checked="false" label="Ignore case"/>
            <param argument="--max-mismatch" type="integer" min="0" value="0" label="Maximum mismatch" help="For large genomes like human genome, using mapping/alignment tools would be faster" />
            <param argument="--non-greedy" type="boolean" truevalue="--non-greedy" falsevalue="" checked="false" label="Non-greedy mode" help="Faster, but muy miss motifs overlapping with others" />
            <param argument="--only-positive-strand" type="boolean" truevalue="--only-positive-strand" falsevalue="" checked="false" label="Only search on positive strand"/>
            <param argument="--use-fmi" type="boolean" truevalue="--use-fmi" falsevalue="" checked="false" label="FM-index" 
                help="Use FM-index for much faster search of lots of sequence patterns. This option is not compatible with the --degenerate option"/>
            <param argument="--id-ncbi" type="boolean" truevalue="--id-ncbi" falsevalue="" checked="false" label="FASTA head is NCBI stype" help="Example: >gi|110645304|ref|NC_002516.2| Pseud..." />
        </section>
    </inputs>
    <outputs>
        <data name="output" format="tabular" label="${tool.name} on ${on_string}">
            <change_format>
                <when input="output_mode" value="--gtf" format="gtf"/>
                <when input="output_mode" value="--bed" format="bed"/>
            </change_format>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="input" value="input1.fasta.gz" ftype="fasta.gz"/>
            <conditional name="conditional_pattern">
                <param name="mode" value="expression"/>
                <param name="pattern" value="ATAGAT"/>
            </conditional>
            <section name="advanced_options">
                <param name="max_mismatch" value="1"/>
            </section>
            <output name="output" file="locate_output1.tabular" ftype="tabular"/>
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="input1.fasta.gz" ftype="fasta.gz"/>
            <conditional name="conditional_pattern">
                <param name="mode" value="expression"/>
                <param name="pattern" value="A[TU]G"/>
                <param name="use_regexp" value="true"/>
            </conditional>
            <param name="output_mode" value="--bed"/>
            <section name="advanced_options">
                <param name="circular" value="true"/>
                <param name="hide_matched" value="true"/>
                <param name="ignore_case" value="true"/>
                <param name="only_positive_strand" value="true"/>
                <param name="id_ncbi" value="true"/>
            </section>
            <output name="output" file="locate_output2.bed" ftype="bed"/>
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="input1.fasta.gz" ftype="fasta.gz"/>
            <conditional name="conditional_pattern">
                <param name="mode" value="file"/>
                <param name="pattern_file" value="motif_sequence.fasta"/>
            </conditional>
            <param name="output_mode" value="--gtf"/>
            <section name="advanced_options">
                <param name="use_fmi" value="true"/>
            </section>
            <output name="output" file="locate_output3.gtf" ftype="gtf"/>
        </test>
        <test expect_num_outputs="1">
            <param name="input" value="input1.fasta.gz" ftype="fasta.gz"/>
            <conditional name="conditional_pattern">
                <param name="mode" value="expression"/>
                <param name="pattern" value="ATAGAT"/>
            </conditional>
            <param name="seq_type" value="dna"/>
            <section name="advanced_options">
                <param name="max_mismatch" value="1"/>
            </section>
            <output name="output" file="locate_output1.tabular" ftype="tabular"/>
        </test>
    </tests>
    <help>
.. class:: infomark

**Purpose**

Locate subsequences/motifs, mismatch allowed.

------

.. class:: infomark

**Attention**

  1. Motifs could be EITHER plain sequence containing "ACTGN" OR regular
     expression like "A[TU]G(?:.{3})+?[TU](?:AG|AA|GA)" for ORFs.     
  2. Degenerate bases/residues like "RYMM.." are also supported by flag -d.
     But do not use degenerate bases/residues in regular expression, you need
     convert them to regular expression, e.g., change "N" or "X"  to ".".
  3. When providing search patterns (motifs) via flag '-p',
     please use double quotation marks for patterns containing comma, 
     e.g., -p '"A{2,}"' or -p "\"A{2,}\"". Because the command line argument
     parser accepts comma-separated-values (CSV) for multiple values (motifs).
     Patterns in file do not follow this rule.     
  4. Mismatch is allowed using flag "-m/--max-mismatch",
     you can increase the value of "-j/--threads" to accelerate processing.
  5. When using flag --circular, end position of matched subsequence that 
     crossing genome sequence end would be greater than sequence length.
    </help>
    <expand macro="citations"/>
</tool>