comparison prinseq.xml @ 2:74afc47f326c draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/prinseq/ commit 626b990b38e0585abfb6a06a2516ff498dc2257b

1:6b865dde1baa

<tool id="prinseq" name="PRINSEQ" version="0.1.0">
    <description>to process quality of sequences</description>
    
    <requirements>
        <requirement type="package" version="5.18.1">perl</requirement>
        <!--<requirement type="package" version="2.90">perl-json</requirement>
        <requirement type="package" version="1.106">perl-cairo</requirement>-->
        <requirement type="package" version="0.20.4">prinseq</requirement>
    </requirements>

    <stdio>
        <exit_code range="1:"   level="fatal"   description="" />

        &&

        prinseq-lite.pl
            #if $seq_type.seq_type_opt == "single":
                -fastq "$seq_type.input_singles"
                #if $seq_type.input_singles.is_of_type('fastqillumina'):
                    -phred64
                #end if
            #else:
                -fastq "$seq_type.input_mate1"
                -fastq2 "$seq_type.input_mate2"
                #if $seq_type.input_mate1.ext != $seq_type.input_mate2.ext:
                    #import sys
                    #silent sys.stderr.write( 'Both pairs from your paired-end library need to be from the same filetype.' )
                #end if
                #if $seq_type.input_mate1.is_of_type('fastqillumina'):

                    #end if
                #end if

                #set quality_filter_treatments=$filter_treatments.quality_filter_treatments
                #if $quality_filter_treatments.apply_quality_filter_treatments == "true":
                    #set min_quality_filter_treatments=$quality_filter_treatments.min_quality_filter_treatments 
                    #if $min_quality_filter_treatments.apply_min_quality_filter_treatments == "true":
                        -min_qual_score $min_quality_filter_treatments.min_quality_filter_treatment_value
                    #end if

                    #set max_quality_filter_treatments=$quality_filter_treatments.max_quality_filter_treatments

                    -trim_qual_rule $quality_trimming_treatments.rule_quality_trimming_treatments
                    -trim_qual_window $quality_trimming_treatments.window_quality_trimming_treatments
                    -trim_qual_step $quality_trimming_treatments.step_quality_trimming_treatments
                #end if

            #end if    

            #*
            -graph_stats "$graph_stats"
            -graph_data tmp/stats.gd

        
        && 

        prinseq-graphs-noPCA.pl -i "tmp/stats.gd" -html_all -o stats_html
        *#
]]> 
    </command>

    <inputs>
        <conditional name="seq_type">
            <param name="seq_type_opt" type="select" label="Is this library paired- or single-end?">

                            </param>
                            <when value="true">
                                <param name="min_length_filter_treatment_value" type="integer" min="0" max="3000" value="60" label="Minimum length threshold to conserve sequences" help="(-min_len)"/>
                            </when>
                            <when value="false" />
                        </conditional>  
                        <conditional name="max_length_filter_treatments">
                            <param name="apply_max_length_filter_treatments" type="select" label="Filter too big sequences?" help="By default, no treatment based on a maximal length is made.">
                              <option value="true">Yes</option>
                              <option value="false" selected="true">No</option>
                            </param>
                            <when value="true">
                                <param name="max_length_filter_treatment_value" type="integer" min="0" max="3000" value="1000" label="Maximal length threshold to conserve sequences" help="(-max_len)"/>
                            </when>
                            <when value="false" />
                        </conditional>  
                    </when>
                    <when value="false" />
                </conditional>  
                <conditional name="quality_filter_treatments">
                    <param name="apply_quality_filter_treatments" type="select" label="Filter sequences based on quality score?" help="By default, sequences with a mean score below 15 are removed.">
                      <option value="true" selected="true">Yes</option>
                      <option value="false">No</option>
                    </param>

                                <conditional name="min_mean_quality_filter_treatments">
                                    <param name="apply_min_mean_quality_filter_treatments" type="select" label="Filter sequences based with too small mean score?" help="By default, sequences with a mean score below 15 are removed.">
                                      <option value="true" selected="true">Yes</option>
                                      <option value="false">No</option>
                                    </param>
                                    <when value="true">   
                                        <param name="min_mean_quality_filter_treatment_value" type="integer" min="0" max="40" value="15" label="Minimum mean score threshold to conserve sequences" help="(-min_qual_mean)"/>
                                    </when>
                                    <when value="false" />
                                </conditional>
                                <conditional name="max_mean_quality_filter_treatments">
                                    <param name="apply_max_mean_quality_filter_treatments" type="select" label="Filter sequences based with too high mean score?" help="By default, no treatment based on a maximum mean score is made.">
                                      <option value="true">Yes</option>
                                      <option value="false" selected="true">No</option>
                                    </param>
                                    <when value="true">   
                                        <param name="max_mean_quality_filter_treatment_value" type="integer" min="0" max="40" value="40" label="Maximum mean score threshold to conserve sequences" help="(-max_qual_mean)"/>
                                    </when>
                                    <when value="false" />
                                </conditional>
                            </when>

                    </param>
                    <when value="true">
                        <param name="method_complexity_filter_treatments" type="select" display="radio" label="Method to filter low complexity sequences" help="(-lc_method)">
                            <option value="dust">Dust</option>
                            <option value="entropy" >Entropy</option>
                        </param> 
                        <param name="threshold_complexity_filter_treatments" type="integer" min="0" max="100" value="2" label="Threshold value used to filter sequences by sequence complexity" help="The dust method uses the threshold as maximum allowed score and the entropy method as minimum allowed value.(-lc_threshold)"/>
                    </when>
                    <when value="false" />
                </conditional>
            </when>
            <when value="false" />
        </conditional>  

        <conditional name="trimming_treatments">
            <param name="apply_trimming_treatments" type="select" label="Apply trimming treatments?" help="">
                <option value="true" selected="true">Yes</option>
                <option value="false">No</option>

            <option value="dn" selected="True">Dinucleotide odds ratios, includes the PCA plots</option>
        </param>-->
    </inputs>

    <outputs>
        <data format="fastq" name="good_sequence_file" 
            from_work_dir="tmp/good_sequences.fastq"
            label="${tool.name} on ${on_string}: Good sequences" >
            <filter>seq_type['seq_type_opt'] == "single"</filter>
        </data>
        <data format="fastq" name="rejected_sequence_file" 
            from_work_dir="tmp/rejected_sequences.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences" >
            <filter>seq_type['seq_type_opt'] == "single"</filter>
        </data>

        <data format="fastq" name="good_sequences_1_file" 
            from_work_dir="tmp/good_sequences_1.fastq"
            label="${tool.name} on ${on_string}: Good sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="good_sequences_1_singletons_file" 
            from_work_dir="tmp/good_sequences_1_singletons.fastq"
            label="${tool.name} on ${on_string}: Good singleton sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="rejected_sequence_1_file" 
            from_work_dir="tmp/rejected_sequences_1.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="good_sequences_2_file" 
            from_work_dir="tmp/good_sequences_2.fastq"
            label="${tool.name} on ${on_string}: Good sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="good_sequences_2_singletons_file" 
            from_work_dir="tmp/good_sequences_2_singletons.fastq"
            label="${tool.name} on ${on_string}: Good singleton sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="rejected_sequence_2_file" 
            from_work_dir="tmp/rejected_sequences_2.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>

        <!--<data format="html" name="html_file" 
            from_work_dir="stats_html.html"
            label="${tool.name} on ${on_string}: Summary" />-->
    </outputs>

    <tests>
        <test>
            <param name='seq_type_opt' value="single"/>
            <param name="input_singles" value="prinseq_input_sequences.fastq"/>
            <param name='apply_filter_treatments' value="true"/>
            <param name='apply_length_filter_treatments' value="true"/> 
            <param name='apply_min_length_filter_treatments' value="true"/>   
            <param name="min_length_filter_treatment_value" value="60"/>
            <param name='apply_max_length_filter_treatments' value="false" />
            <param name='apply_quality_filter_treatments' value="true"/>
            <param name='apply_min_quality_filter_treatments' value="false" />
            <param name='apply_max_quality_filter_treatments' value="false"/>

            <param name="min_mean_quality_filter_treatment_value" value="15"/>
            <param name='apply_max_mean_quality_filter_treatments' value="false"/>
            <param name='apply_base_content_filter_treatments' value="true"/>
            <param name='apply_GC_perc_content_filter_treatments' value="false"/>
            <param name='apply_N_number_content_filter_treatments' value="false"/>
            <param name='apply_N_percentage_content_filter_treatments' value="true"/>  
            <param name="N_percentage_content_filter_treatment_value" value="2"/>
            <param name='apply_other_base_content_filter_treatments' value="false"/>
            <param name='apply_complexity_filter_treatments' value="false"/>
            <param name='apply_trimming_treatments' value="true" />
            <param name='apply_length_trimming_treatments' value="false"/>

            <output name="good_sequence_file" file="prinseq_good_sequences.fastq"/>
        </test>
    </tests>

    <help><![CDATA[

**What it does**

PRINSEQ is a tool for easy and rapid quality control and data processing of metagenomic and metatranscriptomic datasets.
This tool allow to process the sequences with filtering and trimming. 
More information on `PRINSEQ manual <http://prinseq.sourceforge.net/manual.html>`_.

-----

**Input**

The parameters are numerous in PRINSEQ given the wanted treatments.

Several filter treatments are proposed:

  - Filters based on sequence length 
  - Filters based on quality score
  - Filters based on base content

And several trimming treatments eliminate sequence parts:

**Output**

The output file is a sequence file with sequences and quality from input file
which have undergone filter and trimming.

    ]]>
    </help>

    <citations>
        <citation type="doi">10.1093/bioinformatics/btr026</citation>

2:74afc47f326c

<tool id="prinseq" name="PRINSEQ" version="0.20.4">
    <description>to process quality of sequences</description>
    <requirements>
        <requirement type="package" version="0.20.4">prinseq</requirement>
    </requirements>

    <stdio>
        <exit_code range="1:"   level="fatal"   description="" />

        &&

        prinseq-lite.pl
            #if $seq_type.seq_type_opt == "single":
                -fastq '$seq_type.input_singles'
                #if $seq_type.input_singles.is_of_type('fastqillumina'):
                    -phred64
                #end if
            #else:
                -fastq '$seq_type.input_mate1'
                -fastq2 '$seq_type.input_mate2'
                #if $seq_type.input_mate1.ext != $seq_type.input_mate2.ext:
                    #import sys
                    #silent sys.stderr.write( 'Both pairs from your paired-end library need to be from the same filetype.' )
                #end if
                #if $seq_type.input_mate1.is_of_type('fastqillumina'):

                    #end if
                #end if

                #set quality_filter_treatments=$filter_treatments.quality_filter_treatments
                #if $quality_filter_treatments.apply_quality_filter_treatments == "true":
                    #set min_quality_filter_treatments=$quality_filter_treatments.min_quality_filter_treatments
                    #if $min_quality_filter_treatments.apply_min_quality_filter_treatments == "true":
                        -min_qual_score $min_quality_filter_treatments.min_quality_filter_treatment_value
                    #end if

                    #set max_quality_filter_treatments=$quality_filter_treatments.max_quality_filter_treatments

                    -trim_qual_rule $quality_trimming_treatments.rule_quality_trimming_treatments
                    -trim_qual_window $quality_trimming_treatments.window_quality_trimming_treatments
                    -trim_qual_step $quality_trimming_treatments.step_quality_trimming_treatments
                #end if

            #end if

            #*
            -graph_stats "$graph_stats"
            -graph_data tmp/stats.gd

        &&

        prinseq-graphs-noPCA.pl -i "tmp/stats.gd" -html_all -o stats_html
        *#
]]>
    </command>

    <inputs>
        <conditional name="seq_type">
            <param name="seq_type_opt" type="select" label="Is this library paired- or single-end?">

                            </param>
                            <when value="true">
                                <param name="min_length_filter_treatment_value" type="integer" min="0" max="3000" value="60" label="Minimum length threshold to conserve sequences" help="(-min_len)"/>
                            </when>
                            <when value="false" />
                        </conditional>
                        <conditional name="max_length_filter_treatments">
                            <param name="apply_max_length_filter_treatments" type="select" label="Filter too big sequences?" help="By default, no treatment based on a maximal length is made.">
                              <option value="true">Yes</option>
                              <option value="false" selected="true">No</option>
                            </param>
                            <when value="true">
                                <param name="max_length_filter_treatment_value" type="integer" min="0" max="3000" value="1000" label="Maximal length threshold to conserve sequences" help="(-max_len)"/>
                            </when>
                            <when value="false" />
                        </conditional>
                    </when>
                    <when value="false" />
                </conditional>
                <conditional name="quality_filter_treatments">
                    <param name="apply_quality_filter_treatments" type="select" label="Filter sequences based on quality score?" help="By default, sequences with a mean score below 15 are removed.">
                      <option value="true" selected="true">Yes</option>
                      <option value="false">No</option>
                    </param>

                                <conditional name="min_mean_quality_filter_treatments">
                                    <param name="apply_min_mean_quality_filter_treatments" type="select" label="Filter sequences based with too small mean score?" help="By default, sequences with a mean score below 15 are removed.">
                                      <option value="true" selected="true">Yes</option>
                                      <option value="false">No</option>
                                    </param>
                                    <when value="true">
                                        <param name="min_mean_quality_filter_treatment_value" type="integer" min="0" max="40" value="15" label="Minimum mean score threshold to conserve sequences" help="(-min_qual_mean)"/>
                                    </when>
                                    <when value="false" />
                                </conditional>
                                <conditional name="max_mean_quality_filter_treatments">
                                    <param name="apply_max_mean_quality_filter_treatments" type="select" label="Filter sequences based with too high mean score?" help="By default, no treatment based on a maximum mean score is made.">
                                      <option value="true">Yes</option>
                                      <option value="false" selected="true">No</option>
                                    </param>
                                    <when value="true">
                                        <param name="max_mean_quality_filter_treatment_value" type="integer" min="0" max="40" value="40" label="Maximum mean score threshold to conserve sequences" help="(-max_qual_mean)"/>
                                    </when>
                                    <when value="false" />
                                </conditional>
                            </when>

                    </param>
                    <when value="true">
                        <param name="method_complexity_filter_treatments" type="select" display="radio" label="Method to filter low complexity sequences" help="(-lc_method)">
                            <option value="dust">Dust</option>
                            <option value="entropy" >Entropy</option>
                        </param>
                        <param name="threshold_complexity_filter_treatments" type="integer" min="0" max="100" value="2" label="Threshold value used to filter sequences by sequence complexity" help="The dust method uses the threshold as maximum allowed score and the entropy method as minimum allowed value.(-lc_threshold)"/>
                    </when>
                    <when value="false" />
                </conditional>
            </when>
            <when value="false" />
        </conditional>

        <conditional name="trimming_treatments">
            <param name="apply_trimming_treatments" type="select" label="Apply trimming treatments?" help="">
                <option value="true" selected="true">Yes</option>
                <option value="false">No</option>

            <option value="dn" selected="True">Dinucleotide odds ratios, includes the PCA plots</option>
        </param>-->
    </inputs>

    <outputs>
        <data format="fastq" name="good_sequence_file" from_work_dir="tmp/good_sequences.fastq"
            label="${tool.name} on ${on_string}: Good sequences" >
            <filter>seq_type['seq_type_opt'] == "single"</filter>
        </data>
        <data format="fastq" name="rejected_sequence_file" from_work_dir="tmp/rejected_sequences.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences" >
            <filter>seq_type['seq_type_opt'] == "single"</filter>
        </data>

        <data format="fastq" name="good_sequences_1_file" from_work_dir="tmp/good_sequences_1.fastq"
            label="${tool.name} on ${on_string}: Good sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="good_sequences_1_singletons_file" from_work_dir="tmp/good_sequences_1_singletons.fastq"
            label="${tool.name} on ${on_string}: Good singleton sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="rejected_sequence_1_file" from_work_dir="tmp/rejected_sequences_1.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="good_sequences_2_file" from_work_dir="tmp/good_sequences_2.fastq"
            label="${tool.name} on ${on_string}: Good sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="good_sequences_2_singletons_file" from_work_dir="tmp/good_sequences_2_singletons.fastq"
            label="${tool.name} on ${on_string}: Good singleton sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format="fastq" name="rejected_sequence_2_file" from_work_dir="tmp/rejected_sequences_2.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>

        <!--<data format="html" name="html_file" from_work_dir="stats_html.html"
            label="${tool.name} on ${on_string}: Summary" />-->
    </outputs>

    <tests>
        <test>
            <param name='seq_type_opt' value="single"/>
            <param name="input_singles" value="prinseq_input_sequences.fastq"/>
            <param name='apply_filter_treatments' value="true"/>
            <param name='apply_length_filter_treatments' value="true"/>
            <param name='apply_min_length_filter_treatments' value="true"/>
            <param name="min_length_filter_treatment_value" value="60"/>
            <param name='apply_max_length_filter_treatments' value="false" />
            <param name='apply_quality_filter_treatments' value="true"/>
            <param name='apply_min_quality_filter_treatments' value="false" />
            <param name='apply_max_quality_filter_treatments' value="false"/>

            <param name="min_mean_quality_filter_treatment_value" value="15"/>
            <param name='apply_max_mean_quality_filter_treatments' value="false"/>
            <param name='apply_base_content_filter_treatments' value="true"/>
            <param name='apply_GC_perc_content_filter_treatments' value="false"/>
            <param name='apply_N_number_content_filter_treatments' value="false"/>
            <param name='apply_N_percentage_content_filter_treatments' value="true"/>
            <param name="N_percentage_content_filter_treatment_value" value="2"/>
            <param name='apply_other_base_content_filter_treatments' value="false"/>
            <param name='apply_complexity_filter_treatments' value="false"/>
            <param name='apply_trimming_treatments' value="true" />
            <param name='apply_length_trimming_treatments' value="false"/>

            <output name="good_sequence_file" file="prinseq_good_sequences.fastq"/>
        </test>
    </tests>

    <help><![CDATA[
**What it does**

PRINSEQ is a tool for easy and rapid quality control and data processing of metagenomic and metatranscriptomic datasets.
This tool allow to process the sequences with filtering and trimming.
More information on `PRINSEQ manual <http://prinseq.sourceforge.net/manual.html>`_.

-----

**Input**

The parameters are numerous in PRINSEQ given the wanted treatments.

Several filter treatments are proposed:

  - Filters based on sequence length
  - Filters based on quality score
  - Filters based on base content

And several trimming treatments eliminate sequence parts:

**Output**

The output file is a sequence file with sequences and quality from input file
which have undergone filter and trimming.
    ]]>
    </help>

    <citations>
        <citation type="doi">10.1093/bioinformatics/btr026</citation>