comparison prinseq.xml @ 5:1ee282794de3 draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/prinseq/ commit 34e8262534e22f0d391a81b06374744c4af8da24"

4:654b3a274ed5

<tool id="prinseq" name="PRINSEQ" version="@TOOL_VERSION+galaxy1">
    <description>to process quality of sequences</description>
    <macros>
        <token name="@TOOL_VERSION">0.20.4</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION">prinseq</requirement>
    </requirements>

    <stdio>
        <exit_code range="1:"   level="fatal"   description="" />
        <regex match="ERROR"
               source="stderr"
               level="fatal"
               description="" />
        <regex match="WARNING"

<![CDATA[
    prinseq-lite.pl --version
]]>
    </version_command>

    <command>
<![CDATA[
        mkdir tmp/

        &&

        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
            #elif $seq_type.seq_type_opt == "paired":
                -fastq '$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 $seq_type.input_mate1.is_of_type('fastqillumina'):
                    -phred64
                #end if
            #else 
                -fastq '$seq_type.input_collection.forward'
                -fastq2 '$seq_type.input_collection.reverse'
                #if $seq_type.input_collection.forward.is_of_type('fastqillumina'):
                    -phred64
                #end if
            #end if

            -out_good "tmp/good_sequences"
            -out_bad "tmp/rejected_sequences"

            #if $filter_treatments.apply_filter_treatments == "true":
                #set length_filter_treatments=$filter_treatments.length_filter_treatments

        &&

        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?">
              <option value="single" selected="true">Single-end</option>
              <option value="paired">Paired-end</option>
              <option value="paired_collection">Paired Collection</option>
            </param>
            <when value="single">
                <param name="input_singles" type="data" format="fastqsanger,fastqillumina,fastq" label="FASTQ file" help="FASTQ files." />
            </when>
            <when value="paired">
                <param name="input_mate1" type="data" format="fastqsanger,fastqillumina,fastq" label="FASTQ file" help="FASTQ files." />
                <param name="input_mate2" type="data" format="fastqsanger,fastqillumina,fastq" label="FASTQ file" help="FASTQ files." />
            </when>
            <when value="paired_collection">
                <param name="input_collection" type="data_collection" collection_type="paired" label="FASTQ collection" help="FASTQ data in a paired collection" />
            </when>
        </conditional>

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

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

        <data format_source="input_mate1" name="good_sequences_1_file" from_work_dir="tmp/good_sequences_1.fastq"
            label="${tool.name} on ${on_string}: Good sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format_source="input_mate1" name="good_sequences_1_singletons_file" from_work_dir="tmp/good_sequences_1_singletons.fastq"
            label="${tool.name} on ${on_string}: Good singleton sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format_source="input_mate1" name="rejected_sequence_1_file" from_work_dir="tmp/rejected_sequences_1.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format_source="input_mate2" name="good_sequences_2_file" from_work_dir="tmp/good_sequences_2.fastq"
            label="${tool.name} on ${on_string}: Good sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format_source="input_mate2" name="good_sequences_2_singletons_file" from_work_dir="tmp/good_sequences_2_singletons.fastq"
            label="${tool.name} on ${on_string}: Good singleton sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data format_source="input_mate2" name="rejected_sequence_2_file" from_work_dir="tmp/rejected_sequences_2.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>

        <collection name="good_sequences_collection" type="paired">
            <filter>seq_type['seq_type_opt'] == "paired_collection"</filter>
        </collection>

        <collection name="singletons_collection" type="paired">
            <filter>seq_type['seq_type_opt'] == "paired_collection"</filter>
        </collection>

        <collection name="rejected_sequences_collection" type="paired">
            <filter>seq_type['seq_type_opt'] == "paired_collection"</filter>
        </collection>

        <!--<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" ftype="fastqsanger"/>
            <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="right_quality_trimming_treatment_value" value="20"/>
            <param name="type_quality_trimming_treatments" value="min"/>
            <param name="rule_quality_trimming_treatments" value="lt" />
            <param name="window_quality_trimming_treatments" value="1"/>
            <param name="step_quality_trimming_treatments" value="1"/>

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

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

5:1ee282794de3

<tool id="prinseq" name="PRINSEQ" version="@TOOL_VERSION+galaxy2" profile="20.05">
    <description>to process quality of sequences</description>
    <xrefs>
        <xref type="bio.tools">prinseq</xref>
    </xrefs>
    <macros>
        <token name="@TOOL_VERSION">0.20.4</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION">prinseq</requirement>
    </requirements>

    <stdio>
        <regex match="ERROR"
               source="stderr"
               level="fatal"
               description="" />
        <regex match="WARNING"

<![CDATA[
    prinseq-lite.pl --version
]]>
    </version_command>

    <command detect_errors="exit_code">
<![CDATA[
        mkdir tmp/ &&

        #if $seq_type.seq_type_opt == "single"
            #set fwd = $seq_type.input_singles
            #set rev = None
        #else if $seq_type.seq_type_opt == "paired"
            #set fwd = $seq_type.input_mate1
            #set rev = $seq_type.input_mate2
        #else
            #set fwd = $seq_type.input_collection.forward
            #set rev = $seq_type.input_collection.reverse
        #end if

        #if $rev and $fwd.ext != $rev.ext:
            >&2 echo 'Both pairs from your paired-end library need to be from the same filetype.' &&
            exit 1;
        #end if
        
        #if $fwd.ext.endswith(".gz")
            gunzip -c '$fwd' > fwd.fastq &&
        #else
            ln -s '$fwd' fwd.fastq &&
        #end if
        
        #if $rev
            #if $rev.ext.endswith(".gz")
                gunzip -c '$rev' > rev.fastq &&
            #else
                ln -s '$rev' rev.fastq &&
            #end if
        #end if

        ## create empty output files
        #if $seq_type.seq_type_opt == "single"
            touch tmp/good_sequences.fastq tmp/rejected_sequences.fastq &&
        #else
            touch tmp/good_sequences_1.fastq tmp/good_sequences_1_singletons.fastq tmp/rejected_sequences_1.fastq &&
            touch tmp/good_sequences_2.fastq tmp/good_sequences_2_singletons.fastq tmp/rejected_sequences_2.fastq &&
        #end if


        prinseq-lite.pl
            -fastq fwd.fastq
            #if $rev
                -fastq2 rev.fastq
            #end if
            #if $fwd.ext.startswith('fastqillumina'):
                -phred64
            #end if
            -out_good "tmp/good_sequences"
            -out_bad "tmp/rejected_sequences"

            #if $filter_treatments.apply_filter_treatments == "true":
                #set length_filter_treatments=$filter_treatments.length_filter_treatments

        &&

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

        #if $fwd.ext.endswith('.gz')
            && for f in tmp/*.fastq;
            do
                gzip -c \$f > tmp_file &&
                mv tmp_file \$f;
            done
        #end if
]]>
    </command>
    <inputs>
        <conditional name="seq_type">
            <param name="seq_type_opt" type="select" label="Is this library paired- or single-end?">
              <option value="single" selected="true">Single-end</option>
              <option value="paired">Paired-end</option>
              <option value="paired_collection">Paired Collection</option>
            </param>
            <when value="single">
                <param name="input_singles" type="data" format="fastqsanger,fastqsanger.gz,fastqillumina,fastqillumina.gz" label="FASTQ file" help="FASTQ files." />
            </when>
            <when value="paired">
                <param name="input_mate1" type="data" format="fastqsanger,fastqsanger.gz,fastqillumina,fastqillumina.gz" label="FASTQ file" help="FASTQ files." />
                <param name="input_mate2" type="data" format="fastqsanger,fastqsanger.gz,fastqillumina,fastqillumina.gz" label="FASTQ file" help="FASTQ files." />
            </when>
            <when value="paired_collection">
                <param name="input_collection" type="data_collection" collection_type="paired" label="FASTQ collection" help="FASTQ data in a paired collection" />
            </when>
        </conditional>

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

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

        <data name="good_sequences_1_file" format_source="input_mate1" from_work_dir="tmp/good_sequences_1.fastq"
            label="${tool.name} on ${on_string}: Good sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data name="good_sequences_1_singletons_file" format_source="input_mate1" from_work_dir="tmp/good_sequences_1_singletons.fastq"
            label="${tool.name} on ${on_string}: Good singleton sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data name="rejected_sequence_1_file" format_source="input_mate1" from_work_dir="tmp/rejected_sequences_1.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences for R1" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data name="good_sequences_2_file" format_source="input_mate2" from_work_dir="tmp/good_sequences_2.fastq"
            label="${tool.name} on ${on_string}: Good sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data name="good_sequences_2_singletons_file" format_source="input_mate2" from_work_dir="tmp/good_sequences_2_singletons.fastq"
            label="${tool.name} on ${on_string}: Good singleton sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>
        <data name="rejected_sequence_2_file" format_source="input_mate2" from_work_dir="tmp/rejected_sequences_2.fastq"
            label="${tool.name} on ${on_string}: Rejected sequences for R2" >
            <filter>seq_type['seq_type_opt'] == "paired"</filter>
        </data>

        <collection name="good_sequences_collection" format_source="input_collection" type="paired">
            <data name="forward" from_work_dir="tmp/good_sequences_1.fastq"/>
            <data name="reverse" from_work_dir="tmp/good_sequences_2.fastq"/>
            <filter>seq_type['seq_type_opt'] == "paired_collection"</filter>
        </collection>

        <collection name="singletons_collection" format_source="input_collection" type="paired">
            <data name="forward" from_work_dir="tmp/good_sequences_1_singletons.fastq"/>
            <data name="reverse" from_work_dir="tmp/good_sequences_2_singletons.fastq"/>
            <filter>seq_type['seq_type_opt'] == "paired_collection"</filter>
        </collection>

        <collection name="rejected_sequences_collection" format_source="input_collection" type="paired">
            <data name="forward" from_work_dir="tmp/rejected_sequences_1.fastq"/>
            <data name="reverse" from_work_dir="tmp/rejected_sequences_2.fastq"/>
            <filter>seq_type['seq_type_opt'] == "paired_collection"</filter>
        </collection>

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

    <tests>
        <test expect_num_outputs="2">
            <param name='seq_type_opt' value="single"/>
            <param name="input_singles" value="prinseq_input_sequences.fastq.gz" ftype="fastqsanger.gz"/>
            <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="right_quality_trimming_treatment_value" value="20"/>
            <param name="type_quality_trimming_treatments" value="min"/>
            <param name="rule_quality_trimming_treatments" value="lt" />
            <param name="window_quality_trimming_treatments" value="1"/>
            <param name="step_quality_trimming_treatments" value="1"/>
            <output name="good_sequence_file" ftype="fastqsanger.gz">
                <assert_contents>
                    <has_size value="11219" delta="1000"/>
                </assert_contents>
            </output>
            <output name="rejected_sequence_file" ftype="fastqsanger.gz">
                <assert_contents>
                    <has_size value="14208" delta="1000"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="6">
            <param name='seq_type_opt' value="paired"/>
            <param name="input_mate1" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.R1.fastq" ftype="fastqsanger"/>
            <param name="input_mate2" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.R2.fastq" ftype="fastqsanger"/>
            <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="50"/>
            <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='apply_mean_quality_filter_treatments' value="true"/>
            <param name='apply_min_mean_quality_filter_treatments' value="true"/>
            <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"/>
            <param name='apply_position_trimming_treatments' value="false"/>
            <param name='apply_tail_trimming_treatments' value="false"/>
            <param name='apply_quality_trimming_treatments' value="true"/>
            <param name='apply_left_quality_trimming_treatments' value="false"/>
            <param name='apply_right_quality_trimming_treatments' value="true" />
            <param name="right_quality_trimming_treatment_value" value="20"/>
            <param name="type_quality_trimming_treatments" value="min"/>
            <param name="rule_quality_trimming_treatments" value="lt" />
            <param name="window_quality_trimming_treatments" value="1"/>
            <param name="step_quality_trimming_treatments" value="1"/>
            <output name="good_sequences_1_file" ftype="fastqsanger">
                <assert_contents>
                    <has_n_lines n="36"/>
                </assert_contents>
            </output>
            <output name="good_sequences_1_singletons_file" ftype="fastqsanger">
                <assert_contents>
                    <has_n_lines n="44"/>
                </assert_contents>
            </output>
            <output name="rejected_sequence_1_file" ftype="fastqsanger">
                <assert_contents>
                    <has_n_lines n="0"/>
                </assert_contents>
            </output>
            <output name="good_sequences_2_file" ftype="fastqsanger">
                <assert_contents>
                    <has_n_lines n="36"/>
                </assert_contents>
            </output>
            <output name="good_sequences_2_singletons_file" ftype="fastqsanger">
                <assert_contents>
                    <has_n_lines n="8"/>
                </assert_contents>
            </output>
            <output name="rejected_sequence_2_file" ftype="fastqsanger">
                <assert_contents>
                    <has_n_lines n="36"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="9">
            <param name='seq_type_opt' value="paired_collection"/>
            <param name="input_collection">
                <collection type="paired">
                    <element name="forward" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.R1.fastq.gz" ftype="fastqsanger.gz"/>
                    <element name="reverse" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.R2.fastq.gz" ftype="fastqsanger.gz"/>
                </collection>
            </param>
            <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="50"/>
            <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='apply_mean_quality_filter_treatments' value="true"/>
            <param name='apply_min_mean_quality_filter_treatments' value="true"/>
            <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"/>
            <param name='apply_position_trimming_treatments' value="false"/>
            <param name='apply_tail_trimming_treatments' value="false"/>
            <param name='apply_quality_trimming_treatments' value="true"/>
            <param name='apply_left_quality_trimming_treatments' value="false"/>
            <param name='apply_right_quality_trimming_treatments' value="true" />
            <param name="right_quality_trimming_treatment_value" value="20"/>
            <param name="type_quality_trimming_treatments" value="min"/>
            <param name="rule_quality_trimming_treatments" value="lt" />
            <param name="window_quality_trimming_treatments" value="1"/>
            <param name="step_quality_trimming_treatments" value="1"/>
            <output_collection name="good_sequences_collection" type="paired">
                <element name="forward" ftype="fastqsanger.gz">
                    <assert_contents>
                        <has_size value="605" delta="100"/>
                    </assert_contents>
                </element>
                <element name="reverse" ftype="fastqsanger.gz">
                    <assert_contents>
                        <has_size value="667" delta="100"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="singletons_collection" type="paired">
                <element name="forward" ftype="fastqsanger.gz">
                    <assert_contents>
                        <has_size value="720" delta="100"/>
                    </assert_contents>
                </element>
                <element name="reverse" ftype="fastqsanger.gz">
                    <assert_contents>
                        <has_size value="219" delta="100"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="rejected_sequences_collection" type="paired">
                <element name="forward" ftype="fastqsanger.gz">
                    <assert_contents>
                        <has_size value="0" delta="0"/>
                    </assert_contents>
                </element>
                <element name="reverse" ftype="fastqsanger.gz">
                    <assert_contents>
                        <has_size value="718" delta="100"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>

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