changeset 0:545d934aed81 draft

planemo upload for repository https://github.com/xiaeryu/SpoTyping-v2.0/tree/master/SpoTyping-v2.0-commandLine commit 71c2659a468b7d83f0d438ca6dc888bd8d66d3f5
author iuc
date Tue, 08 May 2018 10:22:03 -0400
parents
children f82981245fbe
files spotyping.xml test-data/input.fastq.gz
diffstat 2 files changed, 104 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/spotyping.xml	Tue May 08 10:22:03 2018 -0400
@@ -0,0 +1,104 @@
+<tool id="spotyping" name="SpoTyping" version="@TOOL_VERSION@+galaxy0" profile="17.01">
+  <description>fast and accurate in silico Mycobacterium spoligotyping from sequence reads</description>
+
+  <macros>
+    <token name="@TOOL_VERSION@">2.1</token>
+  </macros>
+
+  <requirements>
+    <requirement type="package" version="@TOOL_VERSION@">spotyping</requirement>
+  </requirements>
+
+  <command detect_errors="exit_code"><![CDATA[
+    #set $input_file='input.' + $input.extension
+    ln -s '${input}' $input_file &&
+    SpoTyping.py
+    --noQuery
+    $advanced.seq
+    $advanced.swift
+    $advanced.filter
+    $advanced.sorted
+    $input_file &&
+    cat SpoTyping.log SpoTyping > '${output_txt}'
+    ]]>
+  </command>
+
+  <inputs>
+    <param name="input" type="data" format="fastq,fastq.gz,fasta" label="Sequence reads" />
+    <section name="advanced" title="Advanced options" expanded="false">
+      <param type="boolean" argument="--seq" label="Input is assembled sequence" help="Input is either a complete genomic sequence or assembled contigs from an isolate" truevalue="--seq" falsevalue="" checked="false" />
+      <param type="boolean" argument="--swift" label="Swift mode" checked="true" truevalue="--swift=on" falsevalue="--swift=off" />
+      <param type="boolean" argument="--filter" label="Stringent filtering of reads" truevalue="--filter" falsevalue="" checked="false" />
+      <param type="boolean" argument="--sorted" label="Reads are sorted to a reference genome" truevalue="--sorted" falsevalue="" />
+    </section>
+  </inputs>
+
+  <outputs>
+    <data name="output_txt" label="SpoTyping spoligotyping on ${on_string}" format="txt" />
+  </outputs>
+
+  <tests>
+    <test>
+      <param name="input" value="input.fastq.gz" ftype="fastq.gz" />
+      <output name="output_txt">
+        <assert_contents>
+          <has_text text="1111111111111111101111111111111100001111111" />
+        </assert_contents>
+      </output>
+    </test>
+  </tests>
+
+  <help><![CDATA[
+    SpoTyping_ is a software for predicting spoligotype_ from sequencing reads, complete genomic sequences and assembled contigs.
+
+    **Input:**
+
+    - Fastq file - if paired end data is used, you may choose to concatenate paired reads into a single input (e.g. using the cat tool)
+    - Fasta file of a complete genomic sequence or assembled contigs of an isolate (with --seq option)
+
+    *Note on input size*: In swift mode the sampling threshold is reached in approximately 30x coverage when using
+    paired end sequencing of a *M. tuberculosis* genome.
+
+    **Output:**
+
+    Count of hits from BLAST result for each spacer sequence and predicted spoligotype in the format of binary code and octal code.
+
+    **Options:**
+
+    \--seq
+    Set this if input is a fasta file that contains only complete genomic sequence or assembled contigs from an isolate. [Default is off]
+
+    \-s SWIFT, --swift=SWIFT
+    Swift mode, either "on" or "off" [Default: on] - swift mode samples 250 million bases to use for spoligotyping
+
+    \--sorted
+    Set if input reads are sorted relative to positions on a reference genome. If reads are sorted and swift mode is used, swift mode's sampling is adjusted
+    to sample reads across positions in the genome evenly.
+
+    \--filter
+    Filter reads such that:
+
+    1. Leading and trailing 'N's would be removed.
+    2. Any read with more than 3 'N's in the middle would be removed.
+    3. Any read with more than 7 consecutive bases identical would be trimmed/filtered out given
+       the length of the flanking regions.
+
+    **Got weird spoligotype prediction?**
+
+    Sequencing throughput is very low (<40Mbp, for example): SpoTyping may not be able to give accurate prediction due to the relatively low read depth.
+
+    **Interpreting the spoligotype**
+
+    The binary or octal spoligotype can be used to look up lineage information using a service
+    like `TB Lineage`_.
+
+  .. _SpoTyping: https://github.com/xiaeryu/SpoTyping-v2.0/tree/master/SpoTyping-v2.0-commandLine
+  .. _spoligotype: https://www.ncbi.nlm.nih.gov/pubmed/19521871
+  .. _TB Lineage: http://tbinsight.cs.rpi.edu/run_tb_lineage.html
+    ]]>
+  </help>
+
+  <citations>
+    <citation type="doi">10.1186/s13073-016-0270-7</citation>
+  </citations>
+</tool>
Binary file test-data/input.fastq.gz has changed