annotate gene_family_phylogeny_builder.xml @ 0:7000422fbaff draft

Uploaded

<tool id="plant_tribes_gene_family_phylogeny_builder" name="GeneFamilyPhylogenyBuilder" version="@WRAPPER_VERSION@.0">
    <description>builds phylogenetic trees of aligned orthologous gene family clusters</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements_gene_family_phylogeny_builder" />
    <command detect_errors="exit_code"><![CDATA[
#set input_format = $input_format_cond.input_format
#set tree_inference = $tree_inference_cond.tree_inference
#if str($tree_inference) == 'raxml':
    #set rooting_order_file_cond = $tree_inference_cond.rooting_order_file_cond
    #set rooting_order_file = $rooting_order_file_cond.rooting_order_file
    #if str($rooting_order_file) == 'yes':
        #set rooting_order = $rooting_order_file_cond.rooting_order
    #end if
    #set bootstrap_replicates = $tree_inference_cond.bootstrap_replicates
#end if

python $__tool_directory__/gene_family_phylogeny_builder.py
#if str($input_format) == 'ptalign':
    --orthogroup_aln '$input_format_cond.input_ptalign.extra_files_path'
    --alignment_type 'aln'
    --sequence_type 'protein'
#else if str($input_format) == 'ptalignca':
    --orthogroup_aln '$input_format_cond.input_ptalignca.extra_files_path'
    --alignment_type 'aln'
    --sequence_type $input_format_cond.sequence_type
#else if str($input_format) == 'ptalignfiltered':
    --orthogroup_aln '$input_format_cond.input_ptalignfiltered.extra_files_path'
    --alignment_type 'filter'
    --sequence_type 'protein'
#else if str($input_format) == 'ptalignfilteredca':
    --orthogroup_aln '$input_format_cond.input_ptalignfilteredca.extra_files_path'
    --alignment_type 'filter'
    --sequence_type $input_format_cond.sequence_type
#else if str($input_format) == 'ptaligntrimmed':
    --orthogroup_aln '$input_format_cond.input_ptaligntrimmed.extra_files_path'
    --alignment_type 'trim'
    --sequence_type 'protein'
#else if str($input_format) == 'ptaligntrimmedca':
    --orthogroup_aln '$input_format_cond.input_ptaligntrimmedca.extra_files_path'
    --alignment_type 'trim'
    --sequence_type $input_format_cond.sequence_type
#end if
--scaffold '$scaffold.fields.path'
--config_dir '$scaffold.fields.path'
--method $method
--tree_inference $tree_inference
#if str($tree_inference) == 'raxml':
    #if str($rooting_order_file) == 'yes':
        --rooting_order '$rooting_order'
        ## No else block needed here because the default rooting_order
        ## configuration will be used if the --rooting_order flag is missing.
    #end if
    --bootstrap_replicates $bootstrap_replicates
    --output_phylip '$output_phylip'
    --output_phylip_dir '$output_phylip.files_path'
#end if
--min_orthogroup_size $min_orthogroup_size
--max_orthogroup_size $max_orthogroup_size
--num_threads \${GALAXY_SLOTS:-4}
#set output_pttree_dir = $output_pttree_dir_cond.output_pttree_dir
#if str($output_pttree_dir) == 'yes':
    --output_tree '$output_tree'
    --output_tree_dir '$output_tree.files_path'
#end if
    ]]></command>
    <inputs>
        <conditional name="input_format_cond">
            <param name="input_format" type="select" label="Orthogroup alignments">
                <option value="ptalign">Proteins orthogroup alignments</option>
                <option value="ptalignca">Protein and coding sequences orthogroup alignments</option>
                <option value="ptalignfiltered">Filtered proteins orthogroup alignments</option>
                <option value="ptalignfilteredca">Filtered protein and coding sequences orthogroup alignments</option>
                <option value="ptaligntrimmed">Trimmed proteins orthogroup alignments</option>
                <option value="ptaligntrimmedca">Trimmed protein and coding sequences orthogroup alignments</option>
            </param>
            <when value="ptalign">
                <param name="input_ptalign" format="ptalign" type="data" label="Proteins orthogroup alignments">
                    <validator type="empty_extra_files_path" />
                </param>
            </when>
            <when value="ptalignca">
                <param name="input_ptalignca" format="ptalignca" type="data" label="Protein and coding sequences orthogroup alignments">
                    <validator type="empty_extra_files_path" />
                </param>
                <expand macro="param_sequence_type" />
            </when>
            <when value="ptalignfiltered">
                <param name="input_ptalignfiltered" format="ptalignfiltered" type="data" label="Filtered proteins orthogroup alignments">
                    <validator type="empty_extra_files_path" />
                </param>
            </when>
            <when value="ptalignfilteredca">
                <param name="input_ptalignfilteredca" format="ptalignfilteredca" type="data" label="Filtered protein and coding sequences orthogroup alignments">
                    <validator type="empty_extra_files_path" />
                </param>
                <expand macro="param_sequence_type" />
            </when>
            <when value="ptaligntrimmed">
                <param name="input_ptaligntrimmed" format="ptaligntrimmed" type="data" label="Trimmed proteins orthogroup alignments">
                    <validator type="empty_extra_files_path" />
                </param>
            </when>
            <when value="ptaligntrimmedca">
                <param name="input_ptaligntrimmedca" format="ptaligntrimmedca" type="data" label="Trimmed protein and coding sequences orthogroup alignments">
                    <validator type="empty_extra_files_path" />
                </param>
                <expand macro="param_sequence_type" />
            </when>
        </conditional>
        <expand macro="param_scaffold" />
        <expand macro="param_method" />
        <conditional name="tree_inference_cond">
            <param name="tree_inference" type="select" label="Phylogenetic inference method">
                <option value="raxml" selected="true">RAxML</option>
                <option value="fasttree">FastTree</option>
            </param>
            <when value="raxml">
                <conditional name="rooting_order_file_cond">
                    <param name="rooting_order_file" type="select" label="Rooting order configuration">
                        <option value="no" selected="true">No</option>
                        <option value="yes">Yes</option>
                    </param>
                    <when value="no" />
                    <when value="yes">
                        <param name="rooting_order" format="txt" type="data" label="Rooting order configuration" />
                    </when>
                </conditional>
                <param name="bootstrap_replicates" type="integer" value="100" min="0" label="Bootstrap replicates" />
            </when>
            <when value="fasttree" />
        </conditional>
        <param name="max_orthogroup_size" type="integer" value="100" min="4" label="Maximum orthogroup size" />
        <param name="min_orthogroup_size" type="integer" value="4" min="4" label="Minimum orthogroup size" />
        <conditional name="output_pttree_dir_cond">
            <param name="output_pttree_dir" type="select" label="Output additional directory of phylogenetic tree files?">
                <option value="no" selected="true">No</option>
                <option value="yes">Yes</option>
            </param>
            <when value="no" />
            <when value="yes" />
        </conditional>
    </inputs>
    <outputs>
        <collection name="tree" type="list" label="${tool.name} (phylogenetic trees, dataset collection) on ${on_string}">
            <discover_datasets pattern="__name__" directory="geneFamilyPhylogenies_dir/orthogroups_tree" format="nhx" />
        </collection>
        <data name="output_tree" format="pttree" label="${tool.name} (phylogenetic trees, directory) on ${on_string}">
            <filter>output_pttree_dir_cond['output_pttree_dir'] == 'yes'</filter>
        </data>
        <data name="output_phylip" format="ptphylip" label="${tool.name} (orthogroup phylip multiple sequence alignments) on ${on_string}">
            <filter>tree_inference_cond['tree_inference'] == 'raxml'</filter>
        </data>
    </outputs>
    <tests>
        <!-- Test framework does not currently support inputs whose associated extra_files_path contains files to be analyzed.
        <test>
        </test>
        -->
    </tests>
    <help>
This tool is one of the PlantTribes collection of automated modular analysis pipelines for comparative and evolutionary
analyses of genome-scale gene families and transcriptomes.  This tool performs gene family phylogenetic inference of
multiple sequence alignments produced by the GeneFamilyAligner tool.

-----

**Required options**

 * **Orthogroup alignments** - orthogroup alignment fasta files produced by the GeneFamilyAligner tool selected from your history.  Depending on how the GeneFamilyAligner tool was executed, these could either be pre-processed alignments, trimmed alignments or both trimmed and filtered alignments.
 * **Gene family scaffold** - one of the PlantTribes gene family scaffolds installed into Galaxy by the PlantTribes Scaffold Download Data Manager tool.
 * **Protein clustering method** - gene family scaffold protein clustering method as described in the AssemblyPostProcessor tool.
 * **Phylogenetic inference method** - method for estimating orthogroup maximum likelihood (ML) phylogenetic trees.  PlantTribes estimates ML phylogenetic trees using either RAxML or FastTree algorithms.

**Other options**

 * **Rooting order configuration** - select 'Yes' to enable selection of a rooting order configuration file for RAxML.  Scaffold configuration templates (.rootingOrder.config) of how to customize the RAxML ML tree rooting order can be found in the scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool, and is also available at the PlantTribes GitHub `repository`_.  Phylogenetic tree rooting order settings shown in these templates are used as defaults if 'No' is selected.
 * **Bootstrap replicates** - number of bootstrap replicates for RAxML to conduct a rapid bootstrap analysis and search for the best-scoring ML tree (default = 100).
 * **Maximum orthogroup size** - maximum number of sequences allowed in orthogroup alignments (default = 100).
 * **Minimum orthogroup size** - minimum number of sequences allowed in orthogroup alignments (default = 4).
 * **Output additional directory of phylogenetic tree files** - selecting 'Yes' will produce an additional output that has an associated directory of files that are copies of the  elements of the phylogenetic trees output dataset collection (this output will be used for future downstream tools).

.. _repository: https://github.com/dePamphilis/PlantTribes/tree/master/config

    </help>
    <citations>
        <expand macro="citation1" />
        <citation type="bibtex">
            @article{Wall2008,
            journal = {Nucleic Acids Research},
            author = {2. Wall PK, Leebens-Mack J, Muller KF, Field D, Altman NS},
            title = {PlantTribes: a gene and gene family resource for comparative genomics in plants},
            year = {2008},
            volume = {36},
            number = {suppl 1},
            pages = {D970-D976},}
        </citation>
        <citation type="bibtex">
            @article{Sasidharan2012,
            journal = {Nucleic Acids Research},
            author = {3. Sasidharan R, Nepusz T, Swarbreck D, Huala E, Paccanaro A},
            title = {GFam: a platform for automatic annotation of gene families},
            year = {2012},
            pages = {gks631},}
        </citation>
        <citation type="bibtex">
            @article{Li2003,
            journal = {Genome Research}
            author = {4. Li L, Stoeckert CJ, Roos DS},
            title = {OrthoMCL: identification of ortholog groups for eukaryotic genomes},
            year = {2003},
            volume = {13},
            number = {9},
            pages = {2178-2189},}
        </citation>
        <citation type="bibtex">
            @article{Emms2015,
            journal = {Genome Biology}
            author = {5. Emms DM, Kelly S},
            title = {OrthoFinder: solving fundamental biases in whole genome comparisons dramatically improves orthogroup inference accuracy},
            year = {2015},
            volume = {16},
            number = {1},
            pages = {157},}
        </citation>
        <citation type="bibtex">
            @article{Stamatakis2014,
            journal = {Bioinformatics},
            author = {6. Stamatakis A},
            title = {RAxML Version 8: A tool for Phylogenetic Analysis and Post-Analysis of Large Phylogenies},
            year = {2014},
            url = {http://sco.h-its.org/exelixis/web/software/raxml/index.html},}
        </citation>
        <citation type="bibtex">
            @article{Price2010,
            journal = {PLoS one},
            author = {7. Price MN, Dehal PS, Arkin AP},
            title = {FastTree 2-approximately maximim-likelihood trees for large alignments},
            year = {2010},
            volume = {5},
            number = {3},
            pages = {e9490},}
        </citation>
    </citations>
</tool>