comparison locarna_best_subtree.xml @ 1:c6c4a7adb099 draft

planemo upload for repository https://github.com/eteriSokhoyan/galaxytools/tree/branchForIterations/tools/GraphClust/LocARNAGraphClust commit 80c721dcfe02a2b8baf8e2c64b76cbcd71b23d86

0:15bd4fb05e5c

<tool id="locarna_best_subtree" name="locarna_best_subtree" version="0.1.0" >
	<requirements>
		<requirement type="package" version="0.1">graphclust-wrappers</requirement>
		<requirement type="package" version='1.8.10'>locarna</requirement>
		<requirement type="package" version='2.1'>rnaz</requirement>
		<requirement type="package" version='0.07'>perl-math-round</requirement>
	</requirements>
	<stdio>
		<exit_code range="1:" />
	</stdio>
	<command>
		<![CDATA[

		    'locARNAGraphClust.pl'  '$center_fa_file' '$tree_file' '$tree_matrix' $p $max_diff_am $tau $max_diff '' '$data_map' $plfold_minlen
        ]]>
	</command>
	<inputs>
		<param type="data" name="center_fa_file" label="centers" format="fa, fasta" help="fasta format" />
		<param type="data" name="tree_file" label="trees" format="text" help="text format" />
		<param type="data" name="tree_matrix" label="tree_matrix" format="text" help="text format" />
		<param type="data" name="data_map" label="data_map" format="txt" help="text format" />
		<param name="p" type="float" value="0.001" size="5" label="minimal probability" help="-p"/>
		<param name="max_diff_am" type="integer" value="50" size="5" label=" maximal difference for sizes of matched arcs" help="--max-diff-am"/>
		<param name="tau" type="integer" value="50" size="5" label="Tau factor in percent" help="--tau"/>
		<param name="max_diff" type="integer" value="100" size="5" label="maximal difference for alignment traces" help="--max-diff"/>
		<param name="plfold_minlen" type="integer" value="210" size="5" label="Minimal length of a sequences for which RNAplfold is used" />
	</inputs>
	<outputs>

		<data name="model_tree_stk" format="stockholm" label="model.tree.stk" from_work_dir="MODEL/best_subtree.aln" />
	</outputs>
	<tests>
		<test>
			<param name="tree_file" value="1.1.tree"/>
			<param name="center_fa_file" value="1.1.center.fa"/>
			<param name="data_map" value="data.map"/>
			<param name="tree_matrix" value="1.1.matrix.tree"/>
			<param name="p" value="0.001"/>
			<param name="max-diff-am" value="50"/>
			<param name="tau" value="50"/>
			<param name="max-diff-am" value="100"/>
			<output name="model_tree_stk" file="best_subtree.aln"/>
		</test>
	</tests>
	<help>
		<![CDATA[
**What it does**

MLocARNA computes a multiple sequence-structure alignment of RNA sequences.
It uses *treefile* - file with guide tree in NEWICK format. The given tree is used as guide tree for the progressive alignment.
This saves the calculation of pairwise all-vs-all similarities and construction of the guide tree.



]]>
	</help>
	<citations>
		<citation type="bibtex">@inproceedings{costa2010fast,
        title={Fast neighborhood subgraph pairwise distance kernel},
        author={Costa, Fabrizio and De Grave, Kurt},
        booktitle={Proceedings of the 26th International Conference on Machine Learning},
        pages={255--262},
        year={2010},
        organization={Omnipress}
      }
      </citation>
			<citation type="bibtex">@Article{Will_Joshi_Hofacker-LocAR_Accur_bound-2012,
  author =	 {Will, Sebastian and Joshi, Tejal and Hofacker, Ivo L. and
                  Stadler, Peter F. and Backofen, Rolf},
  title =	 {{LocARNA}-{P}: {Accurate} boundary prediction and improved
                  detection of structural {RNAs}},
  journal =	 {RNA},
  year =	 {2012},
  volume =	 {18},
  number =	 {5},
  pages =	 {900-14},
  user =	 {will},
  pmid =	 {22450757},
  doi = 	 {10.1261/rna.029041.111},
  issn = 	 {1469-9001},
  issn = 	 {1355-8382},
  abstract =	 {Current genomic screens for noncoding RNAs (ncRNAs) predict
                  a large number of genomic regions containing potential
                  structural ncRNAs. The analysis of these data requires
                  highly accurate prediction of ncRNA boundaries and
                  discrimination of promising candidate ncRNAs from weak
                  predictions. Existing methods struggle with these goals

                  additional results, a web server for LocARNA/LocARNA-P, and
                  the software package, including documentation and a pipeline
                  for refining screens for structural ncRNA, at
                  http://www.bioinf.uni-freiburg.de/Supplements/LocARNA-P/.}
}
				</citation>
				<citation type="bibtex">@Article{Will:etal:_infer_non_codin_rna_famil:PLOS2007,
  author =	 {Sebastian Will and Kristin Reiche and Ivo L. Hofacker and
                  Peter F. Stadler and Rolf Backofen},
  title =	 {Inferring Non-Coding {RNA} Families and Classes by Means of
                  Genome-Scale Structure-Based Clustering},
  journal =	 {PLoS Comput Biol},
  year =	 2007,
  volume =       {3},
  number =       {4},
  pages =        {e65},
  issn =         {1553-7358},
  issn =         {1553-734X},
  pmid =         {17432929},
  doi =          {10.1371/journal.pcbi.0030065},
  user =	 {will},
  abstract =	 {The RFAM database defines families of ncRNAs by means of
                  sequence similarities that are sufficientto establish
                  homology. In some cases, such as microRNAs, box H/ACA
                  snoRNAs, functional commonalities define classes of RNAs
                  that are characterized by structural similarities, and
                  typically consist ofmultiple RNA families. Recent advances

                  candidates, and suggests several novel classes of ncRNAs for
                  which to-date norepresentative has been experimentally
                  characterized.}
}

					</citation>
					<citation type="bibtex">@Article{Smith:Heyne:Richter:Freib_RNA_Tools:NAR2010,
  author =	 {Smith, Cameron and Heyne, Steffen and Richter, Andreas S.
                  and Will, Sebastian and Backofen, Rolf},
  title =	 {Freiburg {RNA} {Tools}: a web server integrating {IntaRNA},
                  {ExpaRNA} and {LocARNA}},
  journal =	 NAR,
  year =	 {2010},
  volume =	 {38 Suppl},
  number =	 {},
  pages =	 {W373-7},
  user =	 {arichter},
  pmid =	 {20444875},
  doi = 	 {10.1093/nar/gkq316},
  issn = 	 {0305-1048},
  issn =	 {1362-4962},
  abstract =	 {The Freiburg RNA tools web server integrates three tools
                  for the advanced analysis of RNA in a common web-based user
                  interface. The tools IntaRNA, ExpaRNA and LocARNA support
                  the prediction of RNA-RNA interaction, exact RNA matching
                  and alignment of RNA, respectively. The Freiburg RNA tools
                  web server and the software packages of the stand-alone
                  tools are freely accessible at
                  http://rna.informatik.uni-freiburg.de.}
}
						</citation>
	</citations>
</tool>

1:c6c4a7adb099

<tool id="locarna_best_subtree" name="locarna_best_subtree" version="0.1.0" >
  <requirements>
    <requirement type="package" version="0.1.7">graphclust-wrappers</requirement>
    <requirement type="package" version='1.8.10'>locarna</requirement>
    <requirement type="package" version='2.1'>rnaz</requirement>
    <requirement type="package" version='0.07'>perl-math-round</requirement>
  </requirements>
  <stdio>
    <exit_code range="1:" />
  </stdio>
  <command>
    <![CDATA[

        'locARNAGraphClust.pl'  '$center_fa_file' '$tree_file' '$tree_matrix' '$data_map'
        #if str($param_type.param_type_selector) == "gclust"
             $param_type.p
            $param_type.max_diff_am
            $param_type.max_diff
            $param_type.tau
            $param_type.plfold_minlen
            $param_type.struct_weight
            $param_type.indel_opening
            $param_type.indel
            $param_type.alifold_consensus_dp
            $param_type.plfold_span
            $param_type.plfold_winsize
         #end if
        ]]>
  </command>
  <inputs>
    <param type="data" name="center_fa_file" label="centers" format="fa, fasta" help="fasta format" />
    <param type="data" name="tree_file" label="trees" format="text" help="text format" />
    <param type="data" name="tree_matrix" label="tree_matrix" format="text" help="text format" />
    <param type="data" name="data_map" label="data_map" format="txt" help="text format" />


    <conditional name="param_type">
    <param name="param_type_selector" type="select" label="Choose the type of parameters">
        <option value="locarna">LocARNA defaults</option>
        <option value="gclust" selected="True">GrapClust defaults(changeable)</option>
    </param>
    <when value="gclust">

      <param name="p" type="float" value="0.001" size="5" label="minimal probability" help="-p"/>
      <param name="max_diff_am" type="integer" value="50" size="5" label=" maximal difference for sizes of matched arcs" help="--max-diff-am"/>
      <param argument="tau" type="integer" value="50" min="0" max="200" label="Sequence contribution at structure match in percent"/>
      <param name="max_diff" type="integer" value="100" size="5" label="maximal difference for alignment traces" help="--max-diff"/>
      <param name="plfold_minlen" type="integer" value="210" size="5" label="Minimal length of a sequences for which RNAplfold is used" />

      <param name="struct_weight" argument="struct-weight"
              label="Structure weight" type="integer"
              value="180" min="0" max="800" />
       <param name="indel_opening" argument="indel-opening"
              label="Indel opening score" type="integer"
              value="-400" max="0" min="-1500" />
       <param argument="indel" label="Indel score" type="integer"
              value="-200" min="-1000" max="0" />

       <param  name="alifold_consensus_dp"
               type="boolean" checked="True"
               truevalue="--alifold-consensus-dp" falsevalue=" "
               label="Compute consensus dot plot by alifold" />

       <param name="plfold_span"
                type="integer" value="150" min="-1" max="400"
                label="Maximum basepair span by RNAplfold (local folding); -1 for global folding" />

         <param name="plfold_winsize"
                type="integer" value="300"  min="-1" max="800"
                label="Window size for local folding" />


    </when>
    <when value="locarna">
    </when>
</conditional>

  </inputs>
  <outputs>

    <data name="model_tree_stk" format="stockholm" label="model.tree.stk" from_work_dir="MODEL/best_subtree.aln" />
  </outputs>
  <tests>
    <test>
      <param name="tree_file" value="1.1.tree"/>
      <param name="center_fa_file" value="1.1.center.fa"/>
      <param name="data_map" value="data.map"/>
      <param name="tree_matrix" value="1.1.matrix.tree"/>
      <conditional name="param_type">
        <param name="iteration_num_selector" value="gclust"/>
        <param name="p" value="0.001"/>
        <param name="max_diff_am" value="50"/>
        <param name="tau" value="50"/>
        <param name="max_diff" value="100"/>
        <param name="plfold_minlen" value="210"/>
        <param name="struct_weight" value="180"/>
        <param name="indel_opening" value="-400"/>
        <param name="indel" value="-200"/>
        <param name="alifold_consensus_dp" value="--alifold-consensus-dp"/>
        <param name="plfold_span" value="150"/>
        <param name="plfold_winsize" value="300"/>
      </conditional>
      <output name="model_tree_stk" file="best_subtree.aln"/>
    </test>
  </tests>
  <help>
    <![CDATA[
**What it does**

MLocARNA computes a multiple sequence-structure alignment of RNA sequences.
It uses *treefile* - file with guide tree in NEWICK format. The given tree is used as guide tree for the progressive alignment.
This saves the calculation of pairwise all-vs-all similarities and construction of the guide tree.



]]>
  </help>
  <citations>
    <citation type="bibtex">@inproceedings{costa2010fast,
        title={Fast neighborhood subgraph pairwise distance kernel},
        author={Costa, Fabrizio and De Grave, Kurt},
        booktitle={Proceedings of the 26th International Conference on Machine Learning},
        pages={255--262},
        year={2010},
        organization={Omnipress}
      }
      </citation>
      <citation type="bibtex">@Article{Will_Joshi_Hofacker-LocAR_Accur_bound-2012,
  author =   {Will, Sebastian and Joshi, Tejal and Hofacker, Ivo L. and
                  Stadler, Peter F. and Backofen, Rolf},
  title =   {{LocARNA}-{P}: {Accurate} boundary prediction and improved
                  detection of structural {RNAs}},
  journal =   {RNA},
  year =   {2012},
  volume =   {18},
  number =   {5},
  pages =   {900-14},
  user =   {will},
  pmid =   {22450757},
  doi =    {10.1261/rna.029041.111},
  issn =    {1469-9001},
  issn =    {1355-8382},
  abstract =   {Current genomic screens for noncoding RNAs (ncRNAs) predict
                  a large number of genomic regions containing potential
                  structural ncRNAs. The analysis of these data requires
                  highly accurate prediction of ncRNA boundaries and
                  discrimination of promising candidate ncRNAs from weak
                  predictions. Existing methods struggle with these goals

                  additional results, a web server for LocARNA/LocARNA-P, and
                  the software package, including documentation and a pipeline
                  for refining screens for structural ncRNA, at
                  http://www.bioinf.uni-freiburg.de/Supplements/LocARNA-P/.}
}
        </citation>
        <citation type="bibtex">@Article{Will:etal:_infer_non_codin_rna_famil:PLOS2007,
  author =   {Sebastian Will and Kristin Reiche and Ivo L. Hofacker and
                  Peter F. Stadler and Rolf Backofen},
  title =   {Inferring Non-Coding {RNA} Families and Classes by Means of
                  Genome-Scale Structure-Based Clustering},
  journal =   {PLoS Comput Biol},
  year =   2007,
  volume =       {3},
  number =       {4},
  pages =        {e65},
  issn =         {1553-7358},
  issn =         {1553-734X},
  pmid =         {17432929},
  doi =          {10.1371/journal.pcbi.0030065},
  user =   {will},
  abstract =   {The RFAM database defines families of ncRNAs by means of
                  sequence similarities that are sufficientto establish
                  homology. In some cases, such as microRNAs, box H/ACA
                  snoRNAs, functional commonalities define classes of RNAs
                  that are characterized by structural similarities, and
                  typically consist ofmultiple RNA families. Recent advances

                  candidates, and suggests several novel classes of ncRNAs for
                  which to-date norepresentative has been experimentally
                  characterized.}
}

          </citation>
          <citation type="bibtex">@Article{Smith:Heyne:Richter:Freib_RNA_Tools:NAR2010,
  author =   {Smith, Cameron and Heyne, Steffen and Richter, Andreas S.
                  and Will, Sebastian and Backofen, Rolf},
  title =   {Freiburg {RNA} {Tools}: a web server integrating {IntaRNA},
                  {ExpaRNA} and {LocARNA}},
  journal =   NAR,
  year =   {2010},
  volume =   {38 Suppl},
  number =   {},
  pages =   {W373-7},
  user =   {arichter},
  pmid =   {20444875},
  doi =    {10.1093/nar/gkq316},
  issn =    {0305-1048},
  issn =   {1362-4962},
  abstract =   {The Freiburg RNA tools web server integrates three tools
                  for the advanced analysis of RNA in a common web-based user
                  interface. The tools IntaRNA, ExpaRNA and LocARNA support
                  the prediction of RNA-RNA interaction, exact RNA matching
                  and alignment of RNA, respectively. The Freiburg RNA tools
                  web server and the software packages of the stand-alone
                  tools are freely accessible at
                  http://rna.informatik.uni-freiburg.de.}
}
            </citation>
  </citations>
</tool>