comparison falco.xml @ 4:959a14c1f2dd draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/falco commit a71120623d1dc818a107ca32f2c232fd47d819ea

3:babbcf02d35c

<tool id="falco" name="Falco" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
    <description>An alternative, more performant implementation of FastQC for high throughput sequence quality control</description>
    <macros>
        <token name="@TOOL_VERSION@">1.2.3</token>
        <token name="@VERSION_SUFFIX@">0</token>
    </macros>
    <xrefs>
        <xref type="bio.tools">falco</xref>
    </xrefs>

        <data format="txt" name="summary_file" from_work_dir="summary.txt" label="${tool.name} on ${on_string}: SummaryData">
            <filter>generate_summary</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq"/>
            <output name="html_file" file="fastqc_report.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_data.txt" ftype="txt"/>
        </test>
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="contaminants" value="contaminant_list.txt" ftype="tabular"/>
            <output name="html_file" file="fastqc_report_contaminants.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_data_contaminants.txt" ftype="txt"/>
        </test>
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="adapters" value="adapter_list.txt" ftype="tabular"/>
            <output name="html_file" file="fastqc_report_adapters.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_data_adapters.txt" ftype="txt"/>
        </test>
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="limits" value="limits.txt" ftype="txt"/>
            <output name="html_file" file="fastqc_report_customlimits.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_data_customlimits.txt" ftype="txt"/>
        </test>
        <!-- ## The kmers param is ignored in Falco and always set to 7. If this ever gets reconsidered, this test could be uncommented.
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq" ftype="fastq"/>
            <param name="kmers" value="7"/>

            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="min_length" value="108"/>
            <output name="html_file" file="fastqc_report_min_length.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_data_min_length.txt" ftype="txt"/>
        </test> -->
        <test expect_num_outputs="3">
            <param name="input_file" value="1000trimmed.fastq" ftype="fastq"/>
            <param name="nogroup" value="--nogroup"/>
            <param name="generate_summary" value="true"/>
            <output name="html_file" file="fastqc_report_nogroup.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_data_nogroup.txt" ftype="txt"/>
            <output name="summary_file" file="fastqc_data_nogroup_summary.txt" ftype="txt"/>
            <assert_command>
                <has_text text="--nogroup"/>
            </assert_command>
        </test>
        <test expect_num_outputs="3">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="subsample" value="10"/>
            <param name="generate_summary" value="true"/>
            <output name="html_file" file="fastqc_report_subsample.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_report_subsample.txt" ftype="txt"/>
            <output name="summary_file" file="fastqc_report_subsample_summary.txt" ftype="txt"/>
        </test>
        <test expect_num_outputs="3">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="bisulfite" value="-bisulfite"/>
            <param name="generate_summary" value="true"/>
            <output name="html_file" file="fastqc_report_bisulfite.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_report_bisulfite.txt" ftype="txt"/>
            <output name="summary_file" file="fastqc_report_bisulfite_summary.txt" ftype="txt"/>
        </test>
        <test expect_num_outputs="3">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="reverse_complement" value="-reverse-complement"/>
            <param name="generate_summary" value="true"/>
            <output name="html_file" file="fastqc_report_reverse_complement.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_report_reverse_complement.txt" ftype="txt"/>
            <output name="summary_file" file="fastqc_report_reverse_complement_summary.txt" ftype="txt"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

Falco_ is a high-speed emulation of the popular FastQC software for quality control of sequencing data.

💚️ With its superior performance Falco saves computational resources and gives you back results faster than FastQC.

We recommend it for most use cases (but see below for exceptions). 💚️

The main functions of Falco are very similar to those of FastQC:

- Import of data from BAM, SAM or FastQ/FastQ.gz files (any variant),
- Providing a quick overview to tell you in which areas there may be problems
- Summary graphs and tables to quickly assess your data
- Export of results to an HTML based permanent report
- Offline operation to allow automated generation of reports without running the interactive application

.. class:: infomark

The plain text report generated by Falco can be used as a "FastQC" report in MultiQC and its data is very similar though not 100% identical to that generated by FastQC on the same inputs.

- your input is bz2-compressed fastq

  Falco doesn't currently support fastq.bz2 as input format meaning Galaxy has to perform a relatively slow format conversion before running the tool, which together makes the analysis slower than with FastQC.

- you are interested in PolyA and PolyG statistics in the Adapter Content section of the quality report

  Falco doesn't currently calculate statistics for these "Adapters" by default.

- your input consists of *mapped* reads in SAM/BAM format

  Due to a bug in the current version of Falco, reads mapped to the reverse strand of the reference genome are not handled correctly and reported metrics are wrong!

-----

**Inputs and outputs**

4:959a14c1f2dd

<tool id="falco" name="Falco" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
    <description>An alternative, more performant implementation of FastQC for high throughput sequence quality control</description>
    <macros>
        <token name="@TOOL_VERSION@">1.2.4</token>
        <token name="@VERSION_SUFFIX@">0</token>
    </macros>
    <xrefs>
        <xref type="bio.tools">falco</xref>
    </xrefs>

        <data format="txt" name="summary_file" from_work_dir="summary.txt" label="${tool.name} on ${on_string}: SummaryData">
            <filter>generate_summary</filter>
        </data>
    </outputs>
    <tests>
        <!-- Test with fastq input -->
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq - report.+"/>
                </assert_contents>
            </output>
            <!-- two lines diff to allow for reported version to change -->
            <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="2"/>
        </test>
        <!-- Test with fastq.gz input -->
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq.gz"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq_gz - report.+"/>
                </assert_contents>
            </output>
            <!-- four lines diff to allow for reported version to change; two more to accomodate changed input file name -->
            <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="4"/>
        </test>
        <!-- Test with BAM input -->
        <test expect_num_outputs="2">
            <param name="input_file" value="hisat_output_1.bam"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     hisat_output_1_bam - report.+"/>
                </assert_contents>
            </output>
            <!-- four lines diff to allow for reported version to change; two more to accomodate changed input file name -->
            <output name="text_file" file="fastqc_data_hisat.txt" ftype="txt" lines_diff="4"/>
        </test>
        <!-- Test summary file option -->
        <test expect_num_outputs="3">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="generate_summary" value="true"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq - report.+"/>
                </assert_contents>
            </output>
            <output name="text_file" file="fastqc_data.txt" ftype="txt" lines_diff="2"/>
            <output name="summary_file" file="fastqc_data_summary.txt" ftype="txt"/>
        </test>
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="contaminants" value="contaminant_list.txt" ftype="tabular"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq - report.+"/>
                </assert_contents>
            </output>
            <output name="text_file" file="fastqc_data_contaminants.txt" ftype="txt" lines_diff="2"/>
        </test>
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="adapters" value="adapter_list.txt" ftype="tabular"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq - report.+"/>
                </assert_contents>
            </output>
            <output name="text_file" file="fastqc_data_adapters.txt" ftype="txt" lines_diff="2"/>
        </test>
        <test expect_num_outputs="3">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="limits" value="limits.txt" ftype="txt"/>
            <param name="generate_summary" value="true"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq - report.+"/>
                </assert_contents>
            </output>
            <output name="summary_file" file="fastqc_data_customlimits_summary.txt" ftype="txt"/>
        </test>
        <!-- ## The kmers param is ignored in Falco and always set to 7. If this ever gets reconsidered, this test could be uncommented.
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq" ftype="fastq"/>
            <param name="kmers" value="7"/>

            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="min_length" value="108"/>
            <output name="html_file" file="fastqc_report_min_length.html" ftype="html" lines_diff="2"/>
            <output name="text_file" file="fastqc_data_min_length.txt" ftype="txt"/>
        </test> -->
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq" ftype="fastq"/>
            <param name="nogroup" value="--nogroup"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq - report.+"/>
                </assert_contents>
            </output>
            <output name="text_file" file="fastqc_data_nogroup.txt" ftype="txt" lines_diff="2"/>
        </test>
        <test expect_num_outputs="3">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="subsample" value="10"/>
            <param name="generate_summary" value="true"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq - report.+"/>
                </assert_contents>
            </output>
            <output name="text_file" file="fastqc_report_subsample.txt" ftype="txt" lines_diff="2"/>
            <output name="summary_file" file="fastqc_report_subsample_summary.txt" ftype="txt"/>
        </test>
        <test expect_num_outputs="3">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="bisulfite" value="-bisulfite"/>
            <param name="generate_summary" value="true"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq - report.+"/>
                </assert_contents>
            </output>
            <output name="text_file" file="fastqc_report_bisulfite.txt" ftype="txt" lines_diff="2"/>
            <output name="summary_file" file="fastqc_report_bisulfite_summary.txt" ftype="txt"/>
        </test>
        <test expect_num_outputs="2">
            <param name="input_file" value="1000trimmed.fastq"/>
            <param name="reverse_complement" value="-reverse-complement"/>
            <output name="html_file" ftype="html">
                <assert_contents>
                  <has_line_matching expression="&lt;html&gt;&lt;head&gt;.+&lt;title&gt;     1000trimmed_fastq - report.+"/>
                </assert_contents>
            </output>
            <output name="text_file" file="fastqc_report_reverse_complement.txt" ftype="txt" lines_diff="2"/>
        </test>
    </tests>
    <help><![CDATA[
**What it does**

Falco_ is a high-speed emulation of the popular FastQC software for quality control of sequencing data.

💚️ With its superior performance Falco saves computational resources and gives you back results faster than FastQC.

We recommend it for most use cases (but see below for rare exceptions). 💚️

The main functions of Falco are very similar to those of FastQC:

- Import of data from BAM, SAM or FastQ/FastQ.gz files (any variant),
- Providing a quick overview to tell you in which areas there may be problems
- Summary graphs and tables to quickly assess your data
- Export of results to an HTML-based report


.. class:: infomark

The plain text report generated by Falco can be used as a "FastQC" report in MultiQC and its data is very similar though not 100% identical to that generated by FastQC on the same inputs.

- your input is bz2-compressed fastq

  Falco doesn't currently support fastq.bz2 as input format meaning Galaxy has to perform a relatively slow format conversion before running the tool, which together makes the analysis slower than with FastQC.

- you need the HTML report to be viewable offline

  The current version of Falco relies on plotly to generate the graphs in the HTML report dynamically each time it's viewed.
  MultiQC plots generated from Falco's raw data output are, of course, viewable offline just like the ones generated from FastQC output.

-----

**Inputs and outputs**