comparison phylogenomics_analysis.xml @ 40:0bf214a0646a draft

Uploaded

39:53f404994667

        <requirement type="package" version="0.3">plant_tribes_phylogenomics_analysis</requirement>
    </requirements>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <!-- In case the return code has not been set properly check stderr too -->
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <command>
        <![CDATA[
            #import os
            #import sys

            #set invalid_input_msg = "The selected input is not a valid list of sequences classified into gene family clusters.  Select an input with the label 'Sequences classified into gene family clusters on...'."
            #set no_coding_sequences_msg = "No corresponding coding sequences were generated for the selected input.  You must not have selected 'Yes' for the 'Create corresponding coding sequences?' option in the GeneFamilyClassifier tool for the selected input."

            #set input_extra_files_path = $orthogroup_faa.extra_files_path
            #if not $os.path.exists($input_extra_files_path):
                #raise Exception($invalid_input_msg)
            #end if

            #set num_orthogroup_faa = $len([f for f in $os.listdir($input_extra_files_path) if f.endswith('.faa')])
            #if $num_orthogroup_faa == 0:
                #raise Exception($invalid_input_msg)
            #end if

            #set num_orthogroup_fna = $len([f for f in $os.listdir($input_extra_files_path) if f.endswith('.fna')])

            #set src_fasta_dir = $os.path.join('phylogenomicsAnalysis_dir', 'orthogroups_fasta')
            #set dest_fasta_dir = $output_fasta.extra_files_path

            #if str($options_type.options_type_selector) == 'advanced' and str($options_type.multiple_sequence_alignments_cond.multiple_sequence_alignments) == 'yes':
                #set generate_output_aln = True

            mkdir -p $dest_fasta_dir &&

            PhylogenomicsAnalysis
            --num_threads \${GALAXY_SLOTS:-4}
            --orthogroup_faa "$orthogroup_faa.extra_files_path"
            --scaffold_dir "${GALAXY_DATA_INDEX_DIR}/plant_tribes/scaffolds"
            --scaffold "$scaffold"
            --method $method

            #if str($options_type.options_type_selector) == 'advanced':
                #if str($options_type.multiple_sequence_alignments_cond.multiple_sequence_alignments) == 'yes':
                    #set multiple_sequence_alignments_option_cond = $options_type.multiple_sequence_alignments_cond.multiple_sequence_alignments_option_cond

                    #if str($multiple_sequence_alignments_option) == 'create_alignments':
                        --create_alignments
                    #else if str($multiple_sequence_alignments_option) == 'add_alignments':
                        --add_alignments
                    #else if str($multiple_sequence_alignments_option) == 'pasta_alignments':
                        --pasta_script_path "$__tool_directory__/run_pasta.py"
                        --pasta_alignments
                        --pasta_iter_limit $multiple_sequence_alignments_option_cond.pasta_iter_limit
                    #end if

                    #if str($input_includes_coding_sequences) == 'yes':
                        #if str($multiple_codon_alignments) == 'yes':
                            --codon_alignments
                            #if str($use_corresponding_coding_sequences) == 'yes':
                                #if $num_orthogroup_fna == 0:
                                    #raise Exception($no_coding_sequences_msg)
                                #end if
                                --orthogroup_fna
                            #end if
                            --sequence_type $multiple_codon_alignments_cond.sequence_type
                        #end if
                    #end if
                #end if

                    --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.rooting_order"
                        #end if
                        --bootstrap_replicates $tree_inference_cond.bootstrap_replicates
                    #end if
                    --max_orthogroup_size $options_type.phylogenetic_trees_cond.max_orthogroup_size
                    --min_orthogroup_size $options_type.phylogenetic_trees_cond.min_orthogroup_size

                && mv $src_tree_dir/* $dest_tree_dir || true
            #end if
        ]]>
    </command>
    <inputs>
        <param name="orthogroup_faa" format="txt" type="data" label="Select sequences classified into gene family clusters"/>
        <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
            <options from_data_table="plant_tribes_scaffolds" />
            <validator type="no_options" message="No PlantTribes scaffolds are available.  Use the PlantTribes Scaffolds Download Data Manager tool to install and populate the PlantTribes scaffolds data table."/>
        </param>
        <param name="method" type="select" label="Protein clustering method">

                            <when value="pasta_alignments">
                                <param name="pasta_iter_limit" type="integer" value="3" min="0" label="Maximum number of iteration that the PASTA algorithm will run"/>
                            </when>
                        </conditional>
                        <conditional name="input_includes_coding_sequences_cond">
                            <param name="input_includes_coding_sequences" type="select" label="Input sequences include corresponding coding sequences?" help="Selected 'Yes' for the 'Create corresponding coding sequences?' option in the GeneFamilyClassifier tool for the selected input">
                                <option value="no" selected="true">No</option>
                                <option value="yes">Yes</option>
                            </param>
                            <when value="no"/>
                            <when value="yes">

        </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 produces by the
**Classify gene sequences into precomputed orthologous gene family clusters** tool.

-----

**Options**

* **Required options**

 - **Select sequences classified into gene family clusters** - A history item with the label 'Sequences classified into gene family clusters on...'.
 - **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 options**

 - **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 'Yes' was selected for the 'Create orthogroup fasta files?' option on the 'Classify gene sequences into precomputed orthologous gene family clusters' tool when generating the selected input.  This tool will produce an error if 'No' was selected.
 - **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 'Yes' was selected for the 'Create corresponding coding sequences?' option on the 'Classify gene sequences into precomputed orthologous gene family clusters' tool when generating the selected input.  This tool will produce an error if 'No' was selected.

* **Phylogenetic trees options**

 - **Phylogenetic trees inference method** - Phylogenetic trees inference method.
 - **Select history item containing strings matching sequence identifiers of species for determining the most basal taxa in the orthogroups for rooting trees?** - If 'No' is selected, trees will be rooted using the most distant taxon present in the orthogroup.

            <citation type="bibtex">
                @unpublished{None,
                author = {Eric Wafula},
                title = {None},
                year = {None},
                eprint = {None},
                url = {None}
            }</citation>
    </citations>
</tool>

40:0bf214a0646a

        <requirement type="package" version="0.3">plant_tribes_phylogenomics_analysis</requirement>
    </requirements>
    <stdio>
        <!-- Anything other than zero is an error -->
        <exit_code range="1:" />
        <exit_code range=":-1" />
        <!-- In case the return code has not been set propery check stderr too -->
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <command>
        <![CDATA[
            #import os
            #import sys

        	#set scaffold_path = $scaffold.fields.path
        	#set scaffold_dir = $os.path.split($scaffold_path)[0]
        	#set scaffold_selection = $os.path.split($scaffold_path)[1]
            #set src_fasta_dir = $os.path.join('phylogenomicsAnalysis_dir', 'orthogroups_fasta')
            #set dest_fasta_dir = $output_fasta.extra_files_path

            #if str($options_type.options_type_selector) == 'advanced' and str($options_type.multiple_sequence_alignments_cond.multiple_sequence_alignments) == 'yes':
                #set generate_output_aln = True

            mkdir -p $dest_fasta_dir &&

            PhylogenomicsAnalysis
            --num_threads \${GALAXY_SLOTS:-4}
            --orthogroup_faa '$input.extra_files_path'
            --scaffold_dir '$scaffold_dir'
            --scaffold '$scaffold_selection'
            --method $method

            #if str($options_type.options_type_selector) == 'advanced':
                #if str($options_type.multiple_sequence_alignments_cond.multiple_sequence_alignments) == 'yes':
                    #set multiple_sequence_alignments_option_cond = $options_type.multiple_sequence_alignments_cond.multiple_sequence_alignments_option_cond

                    #if str($multiple_sequence_alignments_option) == 'create_alignments':
                        --create_alignments
                    #else if str($multiple_sequence_alignments_option) == 'add_alignments':
                        --add_alignments
                    #else if str($multiple_sequence_alignments_option) == 'pasta_alignments':
                        --pasta_script_path '$__tool_directory__/run_pasta.py'
                        --pasta_alignments
                        --pasta_iter_limit $multiple_sequence_alignments_option_cond.pasta_iter_limit
                    #end if

                    #if str($input_includes_coding_sequences) == 'yes':
                        #if str($multiple_codon_alignments) == 'yes':
                            --codon_alignments
                            #if str($use_corresponding_coding_sequences) == 'yes':
                            	#if str($input.ext) == 'pgfccs):
                                	--orthogroup_fna
                              	#else:
                              		raise Exception("Selected input does not include corresponding coding sequences")
                              	#end if
                            #end if
                            --sequence_type $multiple_codon_alignments_cond.sequence_type
                        #end if
                    #end if
                #end if

                    --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.rooting_order'
                        #end if
                        --bootstrap_replicates $tree_inference_cond.bootstrap_replicates
                    #end if
                    --max_orthogroup_size $options_type.phylogenetic_trees_cond.max_orthogroup_size
                    --min_orthogroup_size $options_type.phylogenetic_trees_cond.min_orthogroup_size

                && mv $src_tree_dir/* $dest_tree_dir || true
            #end if
        ]]>
    </command>
    <inputs>
        <param name="input" format="pgfc,pgfccs" type="data" label="Select gene family clusters" help="Selection may optionally include corresponding coding sequences"/>
        <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
            <options from_data_table="plant_tribes_scaffolds" />
            <validator type="no_options" message="No PlantTribes scaffolds are available.  Use the PlantTribes Scaffolds Download Data Manager tool to install and populate the PlantTribes scaffolds data table."/>
        </param>
        <param name="method" type="select" label="Protein clustering method">

                            <when value="pasta_alignments">
                                <param name="pasta_iter_limit" type="integer" value="3" min="0" label="Maximum number of iteration that the PASTA algorithm will run"/>
                            </when>
                        </conditional>
                        <conditional name="input_includes_coding_sequences_cond">
                            <param name="input_includes_coding_sequences" type="select" label="Input sequences include corresponding coding sequences?" help="Selected input data format must be 'pgfccs'">
                                <option value="no" selected="true">No</option>
                                <option value="yes">Yes</option>
                            </param>
                            <when value="no"/>
                            <when value="yes">

        </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 options**

 - **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 options**

 - **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 'pgfccs'.
 - **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 'pgfccs' or this tool will produce an error.

* **Phylogenetic trees options**

 - **Phylogenetic trees inference method** - Phylogenetic trees inference method.
 - **Select history item containing strings matching sequence identifiers of species for determining the most basal taxa in the orthogroups for rooting trees?** - If 'No' is selected, trees will be rooted using the most distant taxon present in the orthogroup.

            <citation type="bibtex">
                @unpublished{None,
                author = {Eric Wafula},
                title = {None},
                year = {None},
                url = {https://github.com/dePamphilis/PlantTribes}
            }</citation>
            <citation type="doi">10.1093/bioinformatics/btw412</citation>
            <citation type="bibtex">
                @published{Research in Computational Molecular Biology (RECOMB) (pp. 177–191),
                author = {Mirarab, S., Nguyen, N., Warnow, T.},
                title = {PASTA: Ultra-Large Multiple Sequence Alignment. In R. Sharan (Ed.)},
                year = {2014},
                url = {https://github.com/smirarab/pasta}
            }</citation>
            <citation type="bibtex">
                @published{Bioinformatics,
                author = {Salvador Capella-Gutierrez, Jose M. Silla-Martinez, Toni Gabaldon},
                title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
                year = {2009},
                url = {http://trimal.cgenomics.org}
            }</citation>
            <citation type="bibtex">
                @published{Bioinformatics,
                author = {A. Stamatakis},
                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="doi">10.1371/journal.pone.0009490</citation>
    </citations>
</tool>