comparison mashmap.xml @ 3:aa2234f3b23a draft

planemo upload

2:6c6bf2bee1ca

<tool name="mashmap" id="mashmap" version="3.1.3" profile="22.05">
  <!--Source in git at: https://github.com/fubar2/galaxy_tf_overlay-->
  <!--Created by [e-mail] at 22/02/2024 21:43:25 using the Galaxy Tool Factory.-->
  <description>Fast local alignment boundaries</description>
  <requirements>
    <requirement version="3.1.3" type="package">mashmap</requirement>
  </requirements>
  <version_command><![CDATA[echo "3.1.3"]]></version_command>

  <configfiles>
    <configfile name="runme"><![CDATA[mashmap --pi '$perc_identity' -s '$seqLength' -f '$filtermode' \
#if int($sketchSize) > 0:
-J '$sketchSize' \
#end if
#if '$dense':
--dense \
#end if
#if len($reflist) == 1:
 -r '$reflist' -q '$query' 
#else
rm -rf 'reflist'
#for i, mash in enumerate($reflist):
   #if i == 0:
       echo '$mash' > 'reflist'
   #else:
       echo '$mash' >> 'reflist'
   #end if
#end for
--rl  'reflist' -q '$query' 
#end if
cp 'mashmap.out'  '$mashout']]></configfile>
  </configfiles>
  <inputs>
    <param name="query" type="data" optional="false" label="Query sequences (as fasta) to mash against the references supplied below" help="" format="fasta" multiple="false"/>
    <param name="reflist" type="data" optional="false" label="Reference or references to mash the query sequences on" help="Choose one or more reference sequences to mash the query sequences against." format="fasta" multiple="true"/>
    <param name="perc_identity" type="float" value="85.0" label="Identity threshold" help="By default, it is set to 85, implying mappings with 85 or more identity should be reported. For example, it can be set to 80to account for more noisy long-read datasets or 95 for mapping human genome assembly to human reference."/>
    <param name="seqLength" type="integer" value="5000" label="Minimum segment length" help="Default is 5,000 bp. Sequences below this length are ignored. Mashmap provides guarantees on reporting local alignments of length twice this value."/>
    <param name="sketchSize" type="integer" value="0" label="Sketch size - leave 0 for automatic setting based" help="This parameter sets the seed density of the winnowing scheme, gauranteeing that the minhash will be calculated from a sample of sketchSize k-mers for each segment. It is set automatically based on --pi but can be manually set as well."/>
    <param name="dense" type="boolean" value="false" label="Dense sketching" help="This flag will increase the seed density substantially, resulting in a density of roughly 0.02 * (1 + (1 - pi) / .05) where pi is the perc_identity threshold. This leads to longer runtimes and higher RAM usage, but significantly more accurate estimates of ANI." checked="false" truevalue="--dense" falsevalue=""/>
    <param name="filtermode" type="select" label="Filter mode" help="Mashmap implements a plane-sweep based algorithm to perform the alignment filtering. Similar to delta-filter in nucmer, different filtering options are provided that are suitable for long read or assembly mapping. Option -f map is suitable for reporting the best mappings for long reads, whereas -f one-to-one is suitable for reporting orthologous mappings among all computed assembly to genome mappings.">
      <option value="map">map - best mapping for long reads</option>
      <option value="one-to-one">one-to-one - best for mapping orthologous reads</option>
      <option value="none">None</option>
    </param>

      <param name="query" value="query_sample"/>
      <param name="reflist" value="reflist_sample"/>
      <param name="perc_identity" value="85.0"/>
      <param name="seqLength" value="5000"/>
      <param name="sketchSize" value="0"/>
      <param name="dense" value="false"/>
      <param name="filtermode" value="map"/>
    </test>
  </tests>
  <help><![CDATA[
 *MashMap* implements a fast and approximate algorithm for computing local alignment boundaries between long DNA sequences. It can be useful for mapping genome assembly or long reads (PacBio/ONT) to reference genome(s). Given a minimum alignment length and an identity threshold for the desired local alignments, 

3:aa2234f3b23a

<tool name="mashmap" id="mashmap" version="3.1.3" profile="22.05">
  <!--Source in git at: https://github.com/fubar2/galaxy_tf_overlay-->
  <!--Created by [e-mail] at 23/02/2024 20:10:51 using the Galaxy Tool Factory.-->
  <description>Fast local alignment boundaries</description>
  <requirements>
    <requirement version="3.1.3" type="package">mashmap</requirement>
  </requirements>
  <version_command><![CDATA[echo "3.1.3"]]></version_command>

  <configfiles>
    <configfile name="runme"><![CDATA[mashmap --pi '$perc_identity' -s '$seqLength' -f '$filtermode' \
#if int($sketchSize) > 0:
-J '$sketchSize' \
#end if
#if '$dense' == 'set':
--dense \
#end if
#if len($reflist) == 1:
 -r $reflist -q '$query' 
#else
#for i, mash in enumerate($reflist):
   #if i == 0:
       echo $mash > 'reflist'
   #else:
       echo $mash >> 'reflist'
   #end if
#end for
--rl  'reflist' -q '$query' 
#end if
cp 'mashmap.out'  $mashout]]></configfile>
  </configfiles>
  <inputs>
    <param name="query" type="data" optional="false" label="Query sequences (as fasta) to mash against the references supplied below" help="" format="fasta" multiple="false"/>
    <param name="reflist" type="data" optional="false" label="Reference or references to mash the query sequences on" help="Choose one or more reference sequences to mash the query sequences against." format="fasta" multiple="true"/>
    <param name="perc_identity" type="float" value="85.0" label="Identity threshold" help="By default, it is set to 85, implying mappings with 85 or more identity should be reported. For example, it can be set to 80to account for more noisy long-read datasets or 95 for mapping human genome assembly to human reference."/>
    <param name="seqLength" type="integer" value="5000" label="Minimum segment length" help="Default is 5,000 bp. Sequences below this length are ignored. Mashmap provides guarantees on reporting local alignments of length twice this value."/>
    <param name="sketchSize" type="integer" value="0" label="Sketch size - leave 0 for automatic setting based" help="This parameter sets the seed density of the winnowing scheme, gauranteeing that the minhash will be calculated from a sample of sketchSize k-mers for each segment. It is set automatically based on --pi but can be manually set as well."/>
    <param name="dense" type="select" label="Dense sketching" help="This flag will increase the seed density substantially, resulting in a density of roughly 0.02 * (1 + (1 - pi) / .05) where pi is the perc_identity threshold. This leads to longer runtimes and higher RAM usage, but significantly more accurate estimates of ANI." display="radio">
      <option value="notset">Do not set this flag</option>
      <option value="set">Set this flag</option>
    </param>
    <param name="filtermode" type="select" label="Filter mode" help="Mashmap implements a plane-sweep based algorithm to perform the alignment filtering. Similar to delta-filter in nucmer, different filtering options are provided that are suitable for long read or assembly mapping. Option -f map is suitable for reporting the best mappings for long reads, whereas -f one-to-one is suitable for reporting orthologous mappings among all computed assembly to genome mappings.">
      <option value="map">map - best mapping for long reads</option>
      <option value="one-to-one">one-to-one - best for mapping orthologous reads</option>
      <option value="none">None</option>
    </param>

      <param name="query" value="query_sample"/>
      <param name="reflist" value="reflist_sample"/>
      <param name="perc_identity" value="85.0"/>
      <param name="seqLength" value="5000"/>
      <param name="sketchSize" value="0"/>
      <param name="dense" value="notset"/>
      <param name="filtermode" value="map"/>
    </test>
  </tests>
  <help><![CDATA[
 *MashMap* implements a fast and approximate algorithm for computing local alignment boundaries between long DNA sequences. It can be useful for mapping genome assembly or long reads (PacBio/ONT) to reference genome(s). Given a minimum alignment length and an identity threshold for the desired local alignments,