annotate fastme.xml @ 0:e119d00db28c draft default tip

planemo upload commit 475f4d7d8442a0d75e103af326ae5881c4d2a4ac

<tool id="fastme" name="FastME" version="2.0.0">
    <description>Distance-based inference of phylogenetic trees</description>
    <requirements>
        <requirement type="package" version="2.1.5">fastme</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" level="fatal" />
    </stdio>
    <version_command>
        <![CDATA[ fastme --version ]]>
    </version_command>
    <command>fastme -f 6
                    --input_data=$input
                    --output_tree=$outputTree
                    --output_matrix=$outputMatrix
                    --output_info=$outputLog
                    --nb_threads=\${GALAXY_SLOTS:-1}

                    #if $typeChoice.datatype =="d"
                        --dna=$typeChoice.modeldna

                    #else if $typeChoice.datatype =="p"
                        --protein=$typeChoice.modelprot

                    #else if $typeChoice.datatype =="cfg":
                         ## Read information of sequence type
                         ## read an info file to choose which option set and set a model by default
                         #set $info = open( str($input_info) ).read()
                         #if 'dna' in $info:
                                --dna=T
                         #else if 'protein' in $info:
                               --protein=L
                         #end if
                    #end if

                    #if $gammaChoice.gamma == "true"
                        --gamma=$gammaChoice.rate
                    #end if

                    $distance
                    $equilibrium
                    $removeGap
                    $treeRefinement

                    #if $bootChoice.boot == "true"
                        --output_boot=$outputBoostrap
                        --bootstrap=$bootChoice.replicates
                    #end if

                    >> tmp_stdout;
                    cat tmp_stdout > $outputLog;

    </command>
    <inputs>
        <param name="input" type="data" format="phylip, phy" label="Fastme input" help="Phylip Alignment or Matrix file"/>
        <param name="fileout_label" type="text" value="Newick tree" label="Output name" help="Output name for files" />
        <conditional name="typeChoice">
            <param name="datatype" type="select" display="radio" label="Data type" >
                <option value="d">DNA</option>
                <option value="p">Protein</option>
                <option value="m">Matrix</option>
                <option value="cfg">Config file</option>
            </param>
            <when value="d">
                <param name="modeldna" type="select" label="Evolutionary model">
                    <option value="4">F84</option>
                    <option value="R">RY</option>
                    <option value="1">F81</option>
                    <option value="J">JC69</option>
                    <option value="K">K2P</option>
                    <option value="T" selected="true">TN93</option>
                    <option value="p">p-distance</option>
                </param>
            </when>
            <when value="p">
                <param name="modelprot" type="select" label="Evolutionary model">
                    <option value="L">LG</option>
                    <option value="W">WAG</option>
                    <option value="J">JTT</option>
                    <option value="h">Day off</option>
                    <option value="C">CpRev</option>
                    <option value="D">DCMut</option>
                    <option value="b">HIVb</option>
                    <option value="I">HIVw</option>
                    <option value="M">MtREV</option>
                    <option value="R">RtREV</option>
                    <option value="p">p-distance</option>
                </param>
            </when>
            <when value="m"/>
            <when value="cfg">
                 <param name="input_info" format="txt" type="data" multiple="false" label="Config file" help="Precompute file containning sequence description (dna or protein)"/>
            </when>
        </conditional>
        <param name="equilibrium" type="boolean" label="Equilibrium frequencies" truevalue="--equilibrium" falsevalue="" help="By default, frequencies are globally counted from the nucleotides alignment or defined by the proteic substitution model. By checking the box, frequencies are pairwise estimated by counting the nucleotides or estimated by counting the amino-acids in the alignment."/>
        <conditional name="gammaChoice">
            <param name="gamma" type="select" label="Gamma distributed rates across sites">
                <option value="true">Yes</option>
                <option value="false">No</option>
            </param>
            <when value="true">
                <param name="rate" type="float" label="Gamma distribution parameter" value="1" min="0"/>
            </when>
            <when value="false" />
        </conditional>
        <param name="removeGap" type="select" display="radio" label="Remove gap strategy">
            <option value="">Pairwise deletion of gaps</option>
            <option value="--remove_gap">Remove all sites with gap</option>
        </param>
        <param name="distance" type="select" label="Distance algorithm">
            <option value="--method=I">BIONJ</option>
            <option value="--method=B --branch_length=B">TaxAdd BalME</option>
            <option value="--method=O --branch_length=O">TaxAdd OLSME</option>
            <option value="--method=N">NJ</option>
            <option value="--method=U">UNJ</option>
        </param>
        <param name="treeRefinement" type="select" display="radio" label="Tree Refinement" help='(NNI) Nearest Neighbor Interchanges,(SPR) Subtree Pruning and Regrafting '>
            <option value="">None</option>
            <option value="--nni=O">OLS NNI</option>
            <option value="--nni=B">BalME NNI</option>
            <option value="--spr" selected="true">BalME SPR</option>
            <option value="--nni=B --spr">BalME NNI + SPR</option>
        </param>
        <conditional name="bootChoice">
            <param name="boot" type="select" label="Bootstrap">
                <option value="false">No</option>
                <option value="true">Yes</option>
            </param>
            <when value="false"/>
            <when value="true">
                <param name="replicates" type="integer" value="1000" label="Number of replicates"/>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="outputTree" format="nhx" label="${fileout_label}"/>
        <data name="outputLog" format="txt" label="FastME Information"/>
        <data name="outputBoostrap" format="nhx" label="FastME Bootstrap trees">
            <filter>bootChoice['boot'] == "true"</filter>
        </data>
        <data name="outputMatrix" format="txt" label="FastME Distance matrix"/>
    </outputs>
    <tests>
        <test>
         <param name="input" value="phylip" />
            <param name="modeldna" value="4"/>
            <param name="gamma" value="false"/>
            <param name="treeRefinement" value=""/>
            <param name="distance" value="--method=I"/>
            <output name="outputTree" file="newick" />
        </test>
        <test>
            <param name="input" value="phylip" />
            <param name="modeldna" value="T"/>
            <param name="distance" value="--method=I"/>
            <param name="treeRefinement" value="--nni=B --spr"/>
            <param name="fileout_label" value="TreeTn93BionjSpr.nwk" />
            <output name="outputTree" file="TreeTn93BionjSpr.nwk" />
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**FastME** version 2.1.5 http://www.atgc-montpellier.fr/fastme

.. class:: infomark

**Galaxy integration** Provided by Southgreen & Andres Gwendoline (Institut Français de Bioinformatique) & Marcon Valentin (IFB & INRA)

.. class:: infomark

**Support** For any questions about Galaxy integration, please send an e-mail to [e-mail]

-----


############
FastME 2.0
############

-----------
Description
-----------

Comprehensive, accurate and fast distance-based phylogeny inference program

FastME provides distance algorithms to infer phylogenies. It's based on balanced minimum evolution, which is the very principle of NJ.

FastME included Nearest Neighbor Interchange (NNI) and also Subtree Pruning and Regrafting (SPR), while remaining as fast as NJ and providing a number of facilities: distance estimation for DNA and proteins with various models and options, bootstrapping, and parallel computations.

For further informations, please visit FastME website_

.. _website: http://www.atgc-montpellier.fr/fastme/usersguide.php


------------
Dependencies
------------
FASTME
        fastme_ 2.1.5 , Conda version

.. _fastme: https://anaconda.org/bioconda/fastme


---------------------------------------------------

---------------
Working example
---------------

Input files
===========

**Phylip file**::


  4   120
  Orangutan   CCAAACGACA TTTCATATGC TGTCATTTCT GAAGATATGA GACAAGTGAG CTGTCCGGAA
  Gorilla     CCAAACAACA TTTCATGTGC TGTCATTTCT GAAGATATGA GACAAGTGAG CTCTCCGAAA
  Human       CCAAACAACA TTTCATGTGC TGTCATTTCT GAAGATAAGA GACAAGTGAG CTCTCCGAAA
  Chimp       CCAAACAACA TTTCATGTGC TGTCATTTCT GAAGATATGA GACAAGTGAG CTCTCCGAAA

              CCAACATATC AGACATATGT GAATTTCAAT TATTGTACGG GCATCCTGGG CTCTCAAAGT
              CCAAGATATC AGACATTTAT GAATTTCAAT TATTGTACGG GCATCCTGGG CTCTCAAAGT
              CCAAGATACC AGACATTTGT GAATTTCAAT TATTGTACTG GCATCCTGGG CTCTCAAAGT
              CCAAGATATC AGACATTTAT GAATTTCAAT TATTGTACTG GCATCCTGGG CTCTCAAAGT



Parameters
==========

::

  Output name: Newick tree
  Evolutionary model : TN93
  Distance method : BIONJ


Output file
===========

**Newick tree**::

    ((Gorilla:0.005755,Orangutan:0.020680):0.001063,Human:0.006655,Chimp:0.002132);

-----

OPTIONS
=======


  -i file, --input_data=file
        The input data file contains sequence alignment(s) or a distance matrix(ces).

  -u input_tree_file, --user_tree=input_tree_file
        FastME may use an existing topology available in the input user tree file which corresponds to the input dataset.

  -o output_tree_file, --output_tree=output_tree_file
        FastME will write the infered tree into the output tree file.

  -O output_matrix_file, --output_matrix=output_matrix_file
        Use output matrix file option if you want FastME to write the distances
        matrix computed from the input alignment in the output matrix file.

  -I output_information_file, --output_info=output_information_file
        Use this option if you want FastME to write information
        about its execution in the output information file.

  -B output_bootstrap_trees_file, --output_boot=output_bootstrap_trees_file
        Use this option if you want FastME to write bootstrap trees
        in the bootstrap trees file.

  -a, --append
        Use this option to append results to existing output files (if any).
        By default output files will be overwritten.

  -m method, --method=method
        FastME computes a tree using a distance algorithm.
        You may choose this method from:
        TaxAdd_(B)alME, TaxAdd_(O)LSME, B(I)ONJ (default),
        (N)J or (U)NJ.

  -d model, --dna=model
        Use this option if your input data file contains DNA sequences alignment(s).
        You may also indicate the evolutionary [model] which can be choosen from:
        (p)-distance, R(Y) symmetric, (R)Y, (J)C69, (K)2P, F8(1), F8(4) (default), (T)N93, (L)ogDet.

  -p model, --protein=model
        Use this option if your input data file contains protein sequences alignment(s).
        You may also indicate the evolutionary [model] which can be choosen from:
        (p)-distance, (F)81 like, (L)G (default), (W)AG, (J)TT, Day(h)off, (D)CMut, (C)pRev,
        (M)tREV, (R)tREV, HIV(b), H(I)Vw or FL(U).

  -r, --remove_gap
        Use this option to completely remove any site which has a gap in
        any sequence. By default, FastME is doing pairwise deletion of gaps.

  -e, --equilibrium
        The equilibrium frequencies for DNA are always estimated by counting
        the occurence of the nucleotides in the input alignment.
        For amino-acid sequences, the equilibrium frequencies are estimated
        using the frequencies defined by the substitution model.
        Use this option if you whish to estimate the amino-acid frequencies
        by counting their occurence in the input alignment.

  -g alpha, --gamma=alpha
       Use this option if you wish to have gamma distributed rates across sites.
       By default, FastME runs with no gamma variation.
       If running FastME with gamma distributed rates across sites, the [alpha] default value is 1.0.
       Only helpful when the input data file contains sequences alignment(s).

  -n NNI, --nni=NNI
        Use this option to do [NNI] tree topology improvement.
        You may choose the [NNI] type from:
        NNI_(B)alME (default) or NNI_(O)LS.

  -s, --spr
        Use this option to do SPR tree topology improvement.

  -w branch, --branch_length=branch
        Use this option to indicate the branch length to assign to the tree.
        Only helpful when not improving the tree topology (no NNI nor SPR).
        You may choose the branch length from:
        (B)alLS (default), (O)LS or (n)one. (n)one is only available with BIONJ, NJ or UNJ.

  -D datasets, --datasets=datasets
        Use this option to indicate the number of datasets in your input
        data file. Default value is 1.

  -b replicates, --bootstrap=replicates
        Use this option to indicate the number of replicates FastME will
        do for bootstrapping. Default value is 0.
        Only helpful when the input data file contains sequences alignment(s).

  -z seed, --seed=seed
        Use this option to initialize randomization with seed value. Only helpful when bootstrapping.

  -c  Use this option if you want FastME only to compute distance matrix.
        Only helpful when the input data file contains sequences alignment(s).

  -T number_of_threads, --nb_threads=number_of_threads
        Use this option to set the number of threads to use.
        Default number of threads is 4.

  -v value, --verbose=value
        Sets the verbose level to value [0-3]. Default value is 0

  -V, --version
        Prints the FastME version.

  -h, --help  Display this usage.


    ]]></help>
    <citations>
       <citation type="doi">10.1093/molbev/msv150</citation>
       <citation type="doi">10.1089/106652702761034136</citation>
    </citations>
</tool>