view phylogenomics_analysis.xml @ 73:7363c4e9423c draft

Uploaded

<tool id="plant_tribes_phylogenomics_analysis" name="PhylogenomicsAnalysis" version="0.6.0">
    <description>builds gene family multiple sequence alignments and their corresponding phylogenies</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <command>
        <![CDATA[
            #set input_format = $input_format_cond.input_format
            #set scaffold = $input_format_cond.scaffold
            #set method = $input_format_cond.method
            #set options_type_cond = $input_format_cond.options_type_cond
            #set options_type= $options_type_cond.options_type

            #if str($options_type) == 'advanced':
                #set multiple_sequence_alignments_cond = $options_type_cond.multiple_sequence_alignments_cond
                #set multiple_sequence_alignments = $multiple_sequence_alignments_cond.multiple_sequence_alignments
                #if str($multiple_sequence_alignments) == 'yes':
                    #set multiple_sequence_alignments_option_cond = $options_type_cond.multiple_sequence_alignments_cond.multiple_sequence_alignments_option_cond
                    #set multiple_sequence_alignments_option = $multiple_sequence_alignments_option_cond.multiple_sequence_alignments_option
                #end if
                #set phylogenomic_trees_cond = $options_type_cond.phylogenetic_trees_cond
                #set phylogenetic_trees = $phylogenomic_trees_cond.phylogenetic_trees
                #set remove_gappy_sequences_cond = $options_type_cond.remove_gappy_sequences_cond
                #set remove_gappy_sequences = $remove_gappy_sequences_cond.remove_gappy_sequences
            #end if

            python $__tool_directory__/phylogenomics_analysis.py
            --num_threads \${GALAXY_SLOTS:-4}
            #if str($input_format) == 'ptortho':
                --orthogroup_faa '$input_format_cond.input_ptortho.extra_files_path'
            #else:
                --orthogroup_faa '$input_format_cond.input_ptorthocs.extra_files_path'
                --orthogroup_fna 'true'
                #set multiple_codon_alignments_cond = $input_format_cond.multiple_codon_alignments_cond
                #set multiple_codon_alignments = $multiple_codon_alignments_cond.multiple_codon_alignments
                #if str($multiple_codon_alignments) == 'yes':
                    --sequence_type $multiple_codon_alignments_cond.sequence_type
                #end if
            #end if
            --config_dir '$scaffold.fields.path'
            --scaffold '$scaffold.fields.path'
            --method $method

            #if str($options_type) == 'advanced':
                #if str($multiple_sequence_alignments) == 'yes':
                    --alignments_method $multiple_sequence_alignments_option
                    #if str($multiple_sequence_alignments_option) == 'pasta_alignments':
                        --pasta_script_path '$__tool_directory__/run_pasta.py'
                        --pasta_iter_limit $multiple_sequence_alignments_option_cond.pasta_iter_limit
                    #end if
                #end if

                #if str($phylogenetic_trees) == 'yes':
                    #set tree_inference_cond = $options_type_cond.phylogenetic_trees_cond.tree_inference_cond
                    #set tree_inference_method = $tree_inference_cond.tree_inference
                    --tree_inference $tree_inference_method
                    #if str($tree_inference_method) == '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':
                            --rooting_order '$rooting_order_file_cond.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 $tree_inference_cond.bootstrap_replicates
                    #end if
                    --max_orthogroup_size $options_type_cond.phylogenetic_trees_cond.max_orthogroup_size
                    --min_orthogroup_size $options_type_cond.phylogenetic_trees_cond.min_orthogroup_size
                #end if

                #if str($remove_gappy_sequences) == 'yes':
                    #set trim_type_cond = $remove_gappy_sequences_cond.trim_type_cond
                    #set trim_type = $trim_type_cond.trim_type
                    #set remove_sequences_with_gaps_cond = $remove_gappy_sequences_cond.remove_sequences_with_gaps_cond
                    #set remove_sequences_with_gaps = $remove_sequences_with_gaps_cond.remove_sequences_with_gaps
                    #if str($remove_sequences_with_gaps) == 'yes':
                        --remove_sequences $remove_sequences_with_gaps_cond.remove_sequences_with_gaps_of
                    #end if
                    --trim_type $trim_type_cond.trim_type
                    #if str($trim_type_cond.trim_type) == 'gap_trimming':
                        --gap_trimming $trim_type_cond.gap_trimming
                    #end if
                #end if
            #end if

            #if str($input_format) == 'ptortho':
                --output_ptortho '$output_ptortho'
                --output_ptortho_dir '$output_ptortho.files_path'
            #else:
                --output_ptorthocs '$output_ptorthocs'
                --output_ptorthocs_dir '$output_ptorthocs.files_path'
            #end if

            #if str($multiple_sequence_alignments) == 'yes'
                --output_aln '$output_aln'
                --output_aln_dir '$output_aln.files_path'
            #end if

            #if str($phylogenetic_trees) == 'yes':
                --output_tree '$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="Select type of data to sub sample">
                <option value="ptortho">Precomputed orthologous gene family clusters</option>
                <option value="ptorthocs">Precomputed orthologous gene family clusters with corresponding coding sequences</option>
            </param>
            <when value="ptortho">
                <param name="input_ptortho" format="ptortho" type="data" label="Precomputed orthologous gene family clusters" />
                <expand macro="param_scaffold" />
                <expand macro="param_method" />
                <conditional name="options_type_cond">
                    <expand macro="param_options_type" />
                    <when value="basic" />
                    <when value="advanced">
                        <expand macro="cond_multiple_sequence_alignments" />
                        <expand macro="cond_phylogenomic_trees" />
                        <expand macro="cond_remove_gappy_sequences" />
                    </when>
                </conditional>
            </when>
            <when value="ptorthocs">
                <param name="input_ptorthocs" format="ptorthocs" type="data" label="Precomputed orthologous gene family clusters with corresponding coding sequences" />
                <expand macro="param_scaffold" />
                <expand macro="param_method" />
                <conditional name="options_type_cond">
                    <expand macro="param_options_type" />
                    <when value="basic" />
                    <when value="advanced">
                        <expand macro="cond_multiple_sequence_alignments" />
                        <expand macro="cond_phylogenomic_trees" />
                        <expand macro="cond_remove_gappy_sequences" />
                        <expand macro="cond_multiple_codon_alignments" />
                    </when>
                </conditional>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="output_ptortho" format="ptortho">
            <filter>input_format_cond['input_format'] == 'ptortho'</filter>
        </data>
        <data name="output_ptorthocs" format="ptorthocs">
            <filter>input_format_cond['input_format'] == 'ptorthocs'</filter>
        </data>
        <data name="output_aln" format="ptalign" label="Multiple alignments (method ${options_type_cond['multiple_sequence_alignments_cond']['multiple_sequence_alignments_option_cond']['multiple_sequence_alignments_option']}) on ${on_string}">
            <filter>options_type_cond['options_type'] == 'advanced' and options_type_cond['multiple_sequence_alignments_cond']['multiple_sequence_alignments'] == 'yes'</filter>
        </data>
        <data name="output_tree" format="pttree" label="Phylogenetic trees on ${on_string}">
            <filter>options_type_cond['options_type'] == 'advanced' and options_type_cond['phylogenetic_trees_cond']['phylogenetic_trees'] == 'yes'</filter>
        </data>
    </outputs>
    <tests>
        <test>
        </test>
    </tests>
    <help>
This tool is one of the PlantTribes collection of automated modular analysis pipelines that utilize objective classifications of
complete protein sequences from sequenced plant genomes to perform comparative evolutionary studies. It performs phylogenomic
analyses by creating multiple sequence alignments and inferred maximum likelihood phylogenies for orthogroups produced by the
**Classify gene sequences into precomputed orthologous gene family clusters** tool.

-----

**Options**

 * **Required**

  - **Select gene family clusters** - Sequences classified into gene family clusters, optionally including corresponding coding sequences.
  - **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data.
  - **Protein clustering method** - One of GFam (domain architecture based clustering), OrthoFinder (broadly defined clusters) or OrthoMCL (narrowly defined clusters).  

 * **Multiple sequence alignments**

  - **Select method for multiple sequence alignments** - Method used for setting multiple sequence alignments.
  - **Input sequences include corresponding coding sequences?** - Selecting 'Yes' for this option requires that the selected input data format is 'ptorthocs'.
  - **Construct orthogroup multiple codon alignments?** - Construct orthogroup multiple codon alignments.
  - **Sequence type used in the phylogenetic inference** - Sequence type (dna or amino acid) used in the phylogenetic inference.
  - **Use corresponding coding sequences?** - Selecting 'Yes' for this option requires that the selected input data format is 'ptorthocs' or this tool will produce an error.

 * **Phylogenetic trees**

  - **Phylogenetic trees inference method** - Phylogenetic trees inference method.
  - **Select rooting order configuration for rooting trees??** - If 'No' is selected, trees will be rooted using the most distant taxon present in the orthogroup.
  - **Number of replicates for rapid bootstrap analysis and search for the best-scoring ML tree** - Number of replicates for rapid bootstrap analysis and search for the best-scoring ML tree.
  - **Maximum number of sequences in orthogroup alignments** - Maximum number of sequences in orthogroup alignments.
  - **Minimum number of sequences in orthogroup alignments** - Minimum number of sequences in orthogroup alignments.

 * **MSA quality control**

  - **Remove sequences with gaps of** - Removes gappy sequences in alignments (i.e., 0.5 removes sequences with 50% gaps).
  - **Select process used for gap trimming** - Either nucleotide based trimming or alignments are trimed using using trimAl's ML heuristic trimming approach.
  - **Remove sites in alignments with gaps of** - If the process used for gap trimming is nucleotide based, this is the gap value used when removing gappy sites in alignments (i.e., 0.1 removes sites with 90% gaps).

    </help>
    <expand macro="citations" />
</tool>