Mercurial > repos > greg > gene_family_phylogeny_builder

changeset 6:0e55cec5ec6b draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Fri, 28 Apr 2017 09:43:53 -0400
parents f73151ec679b
children c03437a39e08
files .shed.yml gene_family_phylogeny_builder.xml macros.xml repository_dependencies.xml
diffstat 4 files changed, 123 insertions(+), 68 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/.shed.yml	Fri Apr 28 09:43:53 2017 -0400
@@ -0,0 +1,14 @@
+name: plant_tribes_gene_family_phylogeny_builder
+owner: greg
+description: |
+  Contains a tool that creates multiple sequence alignments and inferred maximum likelihood phylogenies for orthogroups.
+homepage_url: https://github.com/dePamphilis/PlantTribes
+long_description: |
+  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
+  GeneFamilyAligner tool.
+remote_repository_url: https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/plant_tribes/gene_family_phylogeny_builder
+type: unrestricted
+categories:
+- Phylogenetics
--- a/gene_family_phylogeny_builder.xml	Tue Apr 11 13:18:16 2017 -0400
+++ b/gene_family_phylogeny_builder.xml	Fri Apr 28 09:43:53 2017 -0400
@@ -1,5 +1,5 @@
 <tool id="plant_tribes_gene_family_phylogeny_builder" name="GeneFamilyPhylogenyBuilder" version="@WRAPPER_VERSION@.0">
-    <description>builds gene family phylogenetic trees</description>
+    <description>builds phylogenetic trees of aligned orthologous gene family clusters</description>
     <macros>
         <import>macros.xml</import>
     </macros>
@@ -65,43 +65,43 @@
     </command>
     <inputs>
         <conditional name="input_format_cond">
-            <param name="input_format" type="select" label="Select type of data">
-                <option value="ptalign">Aligned gene family sequences</option>
-                <option value="ptalignca">Aligned gene family sequences with codon alignments</option>
-                <option value="ptalignfiltered">Filtered aligned gene family sequences</option>
-                <option value="ptalignfilteredca">Filtered aligned gene family sequences with codon alignments</option>
-                <option value="ptaligntrimmed">Trimmed aligned gene family sequences</option>
-                <option value="ptaligntrimmedca">Trimmed aligned gene family sequences with codon alignments</option>
+            <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="Aligned gene family sequences">
+                <param name="input_ptalign" format="ptalign" type="data" label="Proteins orthogroup alignments">
                     <!-- <validator type="empty_files_path" /> -->
                 </param>
             </when>
             <when value="ptalignca">
-                <param name="input_ptalignca" format="ptalignca" type="data" label="Aligned gene family sequences with codon alignments">
+                <param name="input_ptalignca" format="ptalignca" type="data" label="Protein and coding sequences orthogroup alignments">
                     <!-- <validator type="empty_files_path" /> -->
                 </param>
                 <expand macro="param_sequence_type" />
             </when>
             <when value="ptalignfiltered">
-                <param name="input_ptalignfiltered" format="ptalignfiltered" type="data" label="Filtered aligned gene family sequences">
+                <param name="input_ptalignfiltered" format="ptalignfiltered" type="data" label="Filtered proteins orthogroup alignments">
                     <!-- <validator type="empty_files_path" /> -->
                 </param>
             </when>
             <when value="ptalignfilteredca">
-                <param name="input_ptalignfilteredca" format="ptalignfilteredca" type="data" label="Filtered aligned gene family sequences with codon alignments">
+                <param name="input_ptalignfilteredca" format="ptalignfilteredca" type="data" label="Filtered protein and coding sequences orthogroup alignments">
                     <!-- <validator type="empty_files_path" /> -->
                 </param>
                 <expand macro="param_sequence_type" />
             </when>
             <when value="ptaligntrimmed">
-                <param name="input_ptaligntrimmed" format="ptaligntrimmed" type="data" label="Trimmed aligned gene family sequences">
+                <param name="input_ptaligntrimmed" format="ptaligntrimmed" type="data" label="Trimmed proteins orthogroup alignments">
                     <!-- <validator type="empty_files_path" /> -->
                 </param>
             </when>
             <when value="ptaligntrimmedca">
-                <param name="input_ptaligntrimmedca" format="ptaligntrimmedca" type="data" label="Trimmed aligned gene family sequences with codon alignments">
+                <param name="input_ptaligntrimmedca" format="ptaligntrimmedca" type="data" label="Trimmed protein and coding sequences orthogroup alignments">
                     <!-- <validator type="empty_files_path" /> -->
                 </param>
                 <expand macro="param_sequence_type" />
@@ -110,13 +110,13 @@
         <expand macro="param_scaffold" />
         <expand macro="param_method" />
         <conditional name="tree_inference_cond">
-            <param name="tree_inference" type="select" label="Phylogenetic trees inference method">
+            <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="Select rooting order configuration for rooting trees?" help="Select No for the default rooting order configuration which uses the most distant taxon present in the orthogroup">
+                    <param name="rooting_order_file" type="select" label="Rooting order configuration?">
                         <option value="no" selected="true">No</option>
                         <option value="yes">Yes</option>
                     </param>
@@ -125,12 +125,12 @@
                         <param name="rooting_order" format="txt" type="data" label="Rooting order configuration for rooting trees" />
                     </when>
                 </conditional>
-                <param name="bootstrap_replicates" type="integer" value="100" min="0" label="Number of replicates for rapid bootstrap analysis and search for the best-scoring ML tree" />
+                <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="0" label="Maximum number of sequences in orthogroup alignments" />
-        <param name="min_orthogroup_size" type="integer" value="4" min="0" label="Minimum number of sequences in orthogroup alignments" />
+        <param name="max_orthogroup_size" type="integer" value="100" min="0" label="Maximum orthogroup size" />
+        <param name="min_orthogroup_size" type="integer" value="4" min="0" label="Minimum orthogroup size" />
     </inputs>
     <outputs>
         <data name="output_pttree" format="pttree" label="Gene family phylogenetic trees on ${on_string}" />
@@ -142,20 +142,87 @@
         -->
     </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
-**GeneFamilyAligner** tool.
+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 Asse3mblyPostProcessor 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 `planttribes`_.  Phylogenetic tree rooting order settings shown in these templates are used as defaults if 'No' is selected.
+
+.. _planttribes: https://github.com/dePamphillis/PlantTribes/config
+
+ * **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).
+
     </help>
     <citations>
         <expand macro="citation1" />
-        <expand macro="citations2to4" />
+        <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>
--- a/macros.xml	Tue Apr 11 13:18:16 2017 -0400
+++ b/macros.xml	Fri Apr 28 09:43:53 2017 -0400
@@ -3,7 +3,7 @@
     <token name="@WRAPPER_VERSION@">0.8</token>
     <xml name="requirements_assembly_post_processor">
         <requirements>
-            <requirement type="package" version="0.4">plant_tribes_assembly_post_processor</requirement>
+            <requirement type="package" version="0.8">plant_tribes_assembly_post_processor</requirement>
         </requirements>
     </xml>
     <xml name="requirements_gene_family_aligner">
@@ -59,13 +59,13 @@
         </param>
     </xml>
     <xml name="param_orthogroup_fna">
-        <param name="orthogroup_fna" type="select" label="Process corresponding gene family classification orthogroups CDS fasta files?">
+        <param name="orthogroup_fna" type="select" label="Orthogroups coding sequences?">
             <option value="yes" selected="true">Yes</option>
             <option value="no">No</option>
         </param>
     </xml>
     <xml name="param_scaffold">
-        <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
+        <param name="scaffold" type="select" label="Gene family 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 in Galaxy to install and populate the PlantTribes scaffolds data table." />
         </param>
@@ -78,9 +78,9 @@
     </xml>
     <xml name="cond_alignment_method">
         <conditional name="alignment_method_cond">
-            <param name="alignment_method" type="select" force_select="true" label="Select method for multiple sequence alignments">
-                <option value="mafft" selected="true">MAFFT algorithm</option>
-                <option value="pasta">PASTA algorithm</option>
+            <param name="alignment_method" type="select" force_select="true" label="Multiple sequence alignment method">
+                <option value="mafft" selected="true">MAFFT</option>
+                <option value="pasta">PASTA</option>
             </param>
             <when value="mafft" />
             <when value="pasta">
@@ -90,31 +90,31 @@
     </xml>
     <xml name="cond_remove_gappy_sequences">
         <conditional name="remove_gappy_sequences_cond">
-            <param name="remove_gappy_sequences" type="select" label="Remove gappy sequences in alignments?">
+            <param name="remove_gappy_sequences" type="select" label="Alignment post-processing configuration?">
                 <option value="no" selected="true">No</option>
                 <option value="yes">Yes</option>
             </param>
             <when value="no" />
             <when value="yes">
                 <conditional name="trim_type_cond">
-                    <param name="trim_type" type="select" label="Select process used for trimming">
-                        <option value="gap_trimming" selected="true">Remove gappy sites in alignments (gap trimming)</option>
-                        <option value="automated_trimming">Trim alignments using trimAl's ML heuristic trimming approach (automated trimming)</option>
+                    <param name="trim_type" type="select" label="Trimming method">
+                        <option value="gap_trimming" selected="true">Gap score based trimming</option>
+                        <option value="automated_trimming">Automated heuristic trimming</option>
                     </param>
                     <when value="gap_trimming">
-                        <param name="gap_trimming" type="float" value="0" min="0" max="1.0" label="Remove sites in alignments with gaps of" help="Zero value has no affect" />
+                        <param name="gap_trimming" type="float" optional="true" min="0" max="1.0" label="Gap score" />
                     </when>
                     <when value="automated_trimming" />
                 </conditional>
                 <conditional name="remove_sequences_with_gaps_cond">
-                    <param name="remove_sequences_with_gaps" type="select" label="Remove sequences with specified gaps?">
+                    <param name="remove_sequences_with_gaps" type="select" label="Remove sequences?">
                         <option value="no" selected="true">No</option>
                         <option value="yes">Yes</option>
                     </param>
                     <when value="no" />
                     <when value="yes">
-                        <param name="remove_sequences_with_gaps_of" type="float" value="0" min="0" max="1" label="Remove sequences with gaps of" help="Zero value has no affect" />
-                        <param name="iterative_realignment" type="integer" value="0" min="0" label="Maximum number of iterations" help="Zero value has no affect"/>
+                        <param name="remove_sequences_with_gaps_of" type="float" optional="true" min="0" max="1" label="Coverage score" />
+                        <param name="iterative_realignment" type="integer" optional="true" min="0" label="Realignment iteration limit" />
                     </when>
                 </conditional>
             </when>
@@ -130,34 +130,4 @@
             url = {https://github.com/dePamphilis/PlantTribes},}
         </citation>
     </xml>
-    <xml name="citations2to4">
-        <citation type="bibtex">
-            @article{Sasidharan2012,
-            journal = {Nucleic Acids Research},
-            author = {2. 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 = {3. 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 = {4. 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>
-    </xml>
 </macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/repository_dependencies.xml	Fri Apr 28 09:43:53 2017 -0400
@@ -0,0 +1,4 @@
+<?xml version="1.0"?>
+<repositories description="This tool uses the data installed by the data_manager_plant_tribes_scaffolds_downloader Data Manager tool.">
+    <repository changeset_revision="8bb32fd5b175" name="data_manager_plant_tribes_scaffolds_downloader" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+</repositories>