view filter.xml @ 6:3c50a937d7c1 draft

Uploaded

<tool id="PHYLO_filter" name="Filter and trim" version="1.2.0">
  <description>sequences</description>
  <macros>
    <import>macros.xml</import>
  </macros>
  <requirements>
    <requirement type="package">yapp_env</requirement>
  </requirements>
  <stdio>
    <expand macro="basic_errors"/>
  </stdio>
  <version_command>seqmagick --version</version_command>
  <command interpreter="bash">
    filter-wrapper.sh ${config}
  </command>
  <inputs>
    <!-- TODO: can take either fasta+qual or fastq -->
    <param name="plate_id" type="integer" value="1" label="Plate number"/>
    <param name="zone_id" type="integer" value="1" label="Zone number"/>
    <param name="raw_seqs" type="data" format="fasta" label="Unfiltered sequences"/>
    <param name="input_qual" type="data" format="qual" label="Sequence quality data"/>
    <!-- TODO: handle MID format for multi-sample sequencing; see http://qiime.org/scripts/split_libraries.html -->
    <param name="barcodes" type="data" format="csv" label="Barcodes"/>
    <param name="primer" type="text" label="Primer" value="GCGGACTACCVGGGTATCTAAT" area="True" size="1x40"/>
    <param name="min_length" type="integer" min="100" max="1000" value="350" label="Minimum sequence length"/>
    <param name="min_quality" type="integer" min="0" max="63" value="35" label="Minimum mean sequence quality"/>
    <param name="reverse_complement" type="boolean" truevalue="TRUE" falsevalue="FALSE" label="Reads uniformly correspond to negative strands"/>
  </inputs>
  <outputs>
    <data name="filtered_seqs" format="fasta" label="Filtered sequences"/>
    <data name="filter_report" format="tabular" label="Filtering report"/>
    <data name="filter_details" format="data" label="Filtering details"/>
    <data name="split_map" format="csv" label="Read-to-specimen map"/>
    <data name="seq_qual_report" format="html" label="Sequence quality report"/>
  </outputs>
  <configfiles>
    <configfile name="plate_json">
{
  "plate": ${plate_id},
  "name": "Plate ${plate_id}",
  "zones": [
    {
      "zone": ${zone_id},
      "cleaning_stats": "${filter_details}"
    }
  ]
}
    </configfile>
    <configfile name="config">
RAW_SEQS="${raw_seqs}"
INPUT_QUAL="${input_qual}"
BARCODES="${barcodes}"
PRIMER="${primer}"
MIN_LENGTH="${min_length}"
MIN_QUALITY="${min_quality}"
REVERSE_COMPLEMENT="${reverse_complement}"
PLATE_JSON="${plate_json}"

FILTERED_SEQS="${filtered_seqs}"
FILTER_REPORT="${filter_report}"
FILTER_DETAILS="${filter_details}"
SPLIT_MAP="${split_map}"
SQR="${seq_qual_report}"
SQR_DIR="${seq_qual_report.files_path}"
    </configfile>
  </configfiles>
  <!-- The contents of the help tag is parsed as reStructuredText. Please see
       help-template.rst for examples of commonly-used sections in other Galaxy
       tools. -->
  <help>

.. class:: infomark

**What it does**

This tool truncates and removes sequences that don’t match a set of quality
criteria, as well as mapping sequence barcodes to specimens. It takes input
sequences in FASTA format and a quality file, and outputs the filtered
sequences as well as a filtering summary and a sequence quality report.

The default quality filter settings are:

+---------------------------+------+
|parameter                  |value |
+===========================+======+
|--min-length               |350   |
+---------------------------+------+
|--min-mean-quality         |35    |
+---------------------------+------+
|--quality-window           |30    |
+---------------------------+------+
|--quality-window-prop      |0.9   |
+---------------------------+------+
|--quality-window-mean-qual |15    |
+---------------------------+------+

See seqmagick's `quality filter documentation`_ for full explanations of these
parameters.

.. _quality filter documentation: http://fhcrc.github.io/seqmagick/quality_filter.html

  </help>
  <citations>
    <expand macro="cite_seqmagick"/>
    <expand macro="cite_biopython"/>
  </citations>
</tool>