annotate fasttree.xml @ 2:e005e659ae21 draft default tip

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/fasttree commit 3b044152a60cd46b50ab58bc15af2d9a9cf2c86d"

<?xml version="1.0"?>
<tool id="fasttree" name="FASTTREE" version="@VERSION@+galaxy1" profile="18.01">
    <description>build maximum-likelihood phylogenetic trees</description>
    <macros>
        <token name="@VERSION@">2.1.10</token>
    </macros>
    <requirements>
        <requirement type="package" version="@VERSION@">fasttree</requirement>
    </requirements>
    <version_command>FastTree</version_command>
    <command detect_errors="aggressive">
<![CDATA[
FastTree

$model_selector.format
$model_selector.model
-nopr
#if $input_selector.select_format == 'fasta':
    $input_selector.quote
#else if $input_selector.select_format == 'phylip':
    -n $input_selector.num
#end if
#set $inform = $input_selector.intree_selector.intree_format
#if $inform == 'one':
    -intree1 '$input_selector.intree_selector.start_tree'
 #else if $inform == 'many':
    -intree '$input_selector.intree_selector.start_tree'
 #end if
 #if $advanced_selector.maximize == 'max':
    #if $advanced_selector.cat_selector.conrate == 'no':
        -cat $advanced_selector.cat_selector.ratecat
    #else if $advanced_selector.cat_selector.conrate == 'yes':
        -nocat
    #end if
    $advanced_selector.gamma
    $advanced_selector.nosupport
    $advanced_selector.mllen
    $advanced_selector.likelihood
    $advanced_selector.fastest
    $advanced_selector.pseudo
#end if

< '$input' > '$output'

#if $save_logfile:
    2> '$log'
#end if

]]>
    </command>
    <inputs>
        <conditional name="input_selector">
            <param name="select_format" type="select" label="Aligned sequences file (FASTA or Phylip format)">
                <option value="fasta" selected="true">fasta</option>
                <option value="phylip">phylip</option>
            </param>
            <when value="fasta">
                <param format="fasta" name="input" type="data" multiple="false" label="FASTA file"/>
                <param name="quote" argument="-quote" type="boolean" truevalue="-quote" falsevalue="" checked="false" label="Allow spaces and other restricted characters (but not ') in sequence and quote names in the output tree." help="This tool is only available for fasta input only; FastTree will not be able to read these trees back in." />
                <conditional name="intree_selector">
                    <param name="intree_format" type="select" label="Set starting tree(s)">
                        <option value="none" selected="true">No starting trees</option>
                        <option value="one">Use starting tree</option>
                    </param>
                    <when value="none">
                    </when>
                    <when value="one">
                        <param format="nhx" name="start_tree" type="data" label="Newick file" />
                    </when>
                </conditional>
            </when>
            <when value="phylip">
                <param format="phylip" name="input" type="data" label="PHYLIP file" />
                <param name="num" type="integer" value="1" optional="true" label="Number of multiple alignments" />
                <conditional name="intree_selector">
                    <param name="intree_format" type="select" label="Set starting tree(s)">
                        <option value="none" selected="true">No starting trees</option>
                        <option value="one">One tree for multiple alignments</option>
                        <option value="many">Multiple trees for multiple alignments</option>
                    </param>
                    <when value="none">
                    </when>
                    <when value="one">
                        <param format="nhx" name="start_tree" type="data" multiple="false" label="Newick file" />
                    </when>
                    <when value="many">
                        <param format="nhx" name="start_tree" type="data" label="Newick file" multiple="false" help="The tree produced by the full alignment to be used as a starting point for each bootstrapping replicate. This will save considerable computation time." />
                    </when>
                </conditional>
            </when>
        </conditional>
        <param name="save_logfile" type="boolean" truevalue="" falsevalue="" checked="false" label="Save log file output" />
        <conditional name="model_selector">
            <param name="format" type="select" label="Protein or nucleotide alignment" help="Specify if the aligned sequences are nucleotide or protein sequences">
                <option value="-nt">Nucleotide</option>
                <option value="" selected="true">Protein</option>
            </param>
            <when value="-nt">
                <param name="model" type="select" label="Nucleotide evolution model">
                    <option value="-gtr" selected="true">GTR+CAT</option>
                    <option value="">Jukes-Cantor + CAT</option>
                </param>
            </when>
            <when value="">
                <param name="model" type="select" label="Protein evolution model">
                    <option value="" selected="true">JTT + CAT</option>
                    <option value="-wag">WAG + CAT</option>
                    <option value="-lg">LG + CAT</option>
                </param>
            </when>
        </conditional>
        <conditional name="advanced_selector">
            <param name="maximize" type="select" label="Show advanced options">
                <option value="min" selected="true">No</option>
                <option value="max">Yes</option>
            </param>
            <when value="min">
            </when>
            <when value="max">
                <conditional name="cat_selector">
                    <param name="conrate" type="select" label="Use constant rates?">
                        <option value="no" selected="true">Do not use constant rates.</option>
                        <option value="yes">Use constant rates.</option>
                    </param>
                    <when value="no">
                        <param name="ratecat" type="integer" value="20" label="Specify the number of rate categories of sites (default 20)" />
                    </when>
                    <when value="yes">
                    </when>
                </conditional>
                <param value="gamma" argument="-gamma" type="boolean" truevalue="-gamma" falsevalue="" checked="false" label="Use Gamma20" help="After optimizing the tree under the CAT approximation, rescale the lengths to optimize the Gamma20 likelihood." />
                <param value="nosupport" argument="-nosupport" type="boolean" truevalue="-nosupport" falsevalue="" checked="false" label="Eliminates the support value computation. Support value computation is not recommended for wide alignments."/>
                <param name="likelihood" argument="-noml" type="boolean" truevalue="-noml" falsevalue="" checked="false" label = "Turn off maximum-likelihood." />
                <param name="fastest" argument="-fastest" type="boolean" truevalue="-fastest" falsevalue="" checked="false" label="Speed up the neighbor joining phase and reduce memory usage (recommended for >50,000 sequences)" />
                <param name="pseudo" argument="-pseudo" type="boolean" truevalue="-pseudo" falsevalue="" checked="false" label="Use pseudocounts" help="Recommended for highly gapped/fragmentary sequences." />
                <param name="mllen" argument="-mllen" type="boolean" truevalue="-mllen" falsevalue="" checked="false" label="Optimize branch lengths without ML NNIs." />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="output" format="nhx" label="${tool.name} on ${on_string}:tree.nhx" />
        <data name="log" format="txt" label="${tool.name} on ${on_string}:log_FastTree_run.txt">
            <filter>save_logfile</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="select_format" value="fasta" />
            <param name="model" value="" />
            <param name="input" value="aligned.fasta" />
            <param name="format" value="-nt" />
            <param name="save_logfile" value="true" />
            <output name="output" file="tree.nhx" ftype="nhx" lines_diff="2" />
            <output name="log" file="log.txt" ftype="txt" compare="contains" />
        </test>
    </tests>
    <help>
<![CDATA[

===========
Description
===========

.. class:: infomark

FastTree_ infers approximately-maximum-likelihood phylogenetic trees from alignments of nucleotide or protein sequences. FastTree can handle alignments with up to a million of sequences in a reasonable amount of time and memory. For large alignments, FastTree is 100-1,000 times faster than PhyML 3.0 or RAxML 7. FastTree is open-source software.

.. _FastTree: http://meta.microbesonline.org/fasttree

-----

-----
Input
-----

A) Aligned sequences file in FASTA format (e.g. the alignment from the 'PyNAST' tool) or PHYLIP format.
B) Newick file to set the starting tree(s) (optional)

----------
Parameters
----------

Nucleotide or protein alignment
 To specify the type of sequence alignment (nucleotide or protein) you are providing.

Nucleotide evolution model
 Specify GTR+CAT (Generalized Time Reversable Model) or Jukes-Cantor + CAT.

Protein evolution model
 Specify JTT (Jones-Taylor-Thornton 1992 model) + CAT, WAG (Whelan-And-Goldman 2001 model) + CAT, or LG (Le-Gascuel 2008 model) + CAT.

Allow spaces and other restricted characters (but not ') in sequence and quote names in the output tree. (fasta only)
 FastTree will not be able to read these trees back in. (-quote)

Number of multiple alignments (phylip only)
 (-n)

-------------------
Advanced Parameters
-------------------

Number of rates of sites
 Defaults to 20. Specify whether you wish to choose constant rates. (-cat/-nocat)

Use Gamma20
 After optimizing the tree under the CAT approximation, rescale the lengths to optimize the Gamma20 likelihood. (-gamma)

Eliminates the support value computation. Support value computation is not recommended for wide alignments.
 (-nosupport)

Turn off maximum-likelihood.
 (-noml)

Speed up the neighbor joining phase and reduce memory usage
 Recommended for >50,000 sequences. (-fastest)

Use pseudocounts
 Recommended if you have many fragmentary sequences. (-pseudo)

Optimize branch lengths without ML NNIs.
 (-mllen)

------
Output
------

This tool produces two output files, one of which is optional (the log file).

(A) The phylogenetic tree in Newick_ format (nhx).

(B) *(optional)* The log file, containing information of the FastTree run to build the phylogenetic tree.

.. class:: infomark

 The placement of the root is not biologically meaningful. The local support values are given as names for the internal nodes, and range from 0 to 1, not from 0 to 100 or 0 to 1,000. If all sequences are unique, then the tree will be fully resolved (the root will have three children and other internal nodes will have two children). If there are multiple sequences that are identical to each other, then there will be a multifurcation. Also, there are no support values for the parent nodes of redundant sequences.

.. _Newick: http://en.wikipedia.org/wiki/Newick_format

-----


=========
Resources
=========

FastTree_v2.1.10_

.. _FastTree_v2.1.10: http://meta.microbesonline.org/fasttree/#Install
]]>
    </help>
    <citations>
      <citation type="doi">10.1371/journal.pone.0009490</citation>
    </citations>
</tool>