Mercurial > repos > greg > gene_family_phylogeny_builder
changeset 0:f4361d941aa3 draft
Uploaded
| author | greg |
|---|---|
| date | Tue, 11 Apr 2017 11:05:24 -0400 |
| parents | |
| children | e5523659847a |
| files | gene_family_phylogeny_builder.py gene_family_phylogeny_builder.xml macros.xml plant_tribes_scaffolds.loc.sample tool_data_table_conf.xml.sample utils.py |
| diffstat | 6 files changed, 421 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gene_family_phylogeny_builder.py Tue Apr 11 11:05:24 2017 -0400 @@ -0,0 +1,49 @@ +#!/usr/bin/env python +import argparse +import subprocess + +import utils + +OUTPUT_DIR = 'phylogenomicsAnalysis_dir' + +parser = argparse.ArgumentParser() + +parser.add_argument('--alignments_type', dest='alignments_type', help='Input alignments type produced by the GeneFamilyAligner') +parser.add_argument('--bootstrap_replicates', dest='bootstrap_replicates', type=int, default=None, help='Number of replicates for rapid bootstrap analysis') +parser.add_argument('--config_dir', dest='config_dir', help='Directory containing default configuration files') +parser.add_argument('--max_orthogroup_size', dest='max_orthogroup_size', type=int, help='Maximum number of sequences in orthogroup alignments') +parser.add_argument('--method', dest='method', help='Protein clustering method') +parser.add_argument('--min_orthogroup_size', dest='min_orthogroup_size', type=int, help='Minimum number of sequences in orthogroup alignments') +parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of threads to use for execution') +parser.add_argument('--orthogroup_aln', dest='orthogroup_aln', help="Input dataset files_path") +parser.add_argument('--output', dest='output', help='Output for phylogenetic trees') +parser.add_argument('--output_dir', dest='output_dir', help='output.files_path') +parser.add_argument('--rooting_order', dest='rooting_order', default=None, help='Rooting order configuration for rooting trees') +parser.add_argument('--scaffold', dest='scaffold', help='Orthogroups or gene families proteins scaffold') +parser.add_argument('--sequence_type', dest='sequence_type', help="Sequence type used in the phylogenetic inference") +parser.add_argument('--tree_inference', dest='tree_inference', help='Phylogenetic trees inference method') + +args = parser.parse_args() + +# Build the command line. +cmd = 'GeneFamilyPhylogenyBuilder' +cmd += ' --alignment_type %s' % args.tree_inference +if args.bootstrap_replicates is not None: + cmd += ' --bootstrap_replicates %d' % args.bootstrap_replicates +cmd += ' --config_dir %s' % args.config_dir +cmd += ' --max_orthogroup_size %d' % args.max_orthogroup_size +cmd += ' --method %s' % args.method +cmd += ' --min_orthogroup_size %d' % args.min_orthogroup_size +cmd += ' --num_threads %d' % args.num_threads +cmd += ' --orthogroup_aln %s' % args.orthogroup_aln +if args.rooting_order is not None: + cmd += ' --rooting_order %s' % args.rooting_order +cmd += ' --scaffold %s' % args.scaffold +cmd += ' --sequence_type %s' % args.sequence_type +cmd += ' --tree_inference %s' % args.tree_inference +# Run the command. +proc = subprocess.Popen(args=cmd, stderr=subprocess.PIPE, stdout=subprocess.PIPE, shell=True) +rc = proc.wait() +utils.check_execution_errors(rc, proc.stderr) +utils.move_directory_files(OUTPUT_DIR, args.output_dir) +utils.write_html_output(args.output, 'Phylogenetic trees', args.output_dir)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gene_family_phylogeny_builder.xml Tue Apr 11 11:05:24 2017 -0400 @@ -0,0 +1,157 @@ +<tool id="plant_tribes_gene_family_phylogeny_builder" name="GeneFamilyPhylogenyBuilder" version="@WRAPPER_VERSION@.0"> + <description>builds gene family phylogenetic trees</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements_gene_family_phylogeny_builder" /> + <expand macro="stdio" /> + <command> + <![CDATA[ + #set input_format = $input_format_cond.input_format + #set tree_inference_cond = $phylogenetic_trees_cond.tree_inference_cond + #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 $__tool_directory__/gene_family_phylogeny_builder.py + --orthogroup_aln '$input_aln.extra_files_path' + --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 + #end if + --min_orthogroup_size $min_orthogroup_size + --max_orthogroup_size $max_orthogroup_size + --num_threads \${GALAXY_SLOTS:-4} + #if str($input_format) == 'ptalign': + --alignment_type 'aln' + --sequence_type 'protein' + #else if str($input_format) == 'ptalignca': + --alignment_type 'aln' + --sequence_type $input_format_cond.sequence_type + #else if str($input_format) == 'ptalignfiltered': + --alignment_type 'filter' + --sequence_type 'protein' + #else if str($input_format) == 'ptalignfilteredca': + --alignment_type 'filter' + --sequence_type $input_format_cond.sequence_type + #else if str($input_format) == 'ptaligntrimmed': + --alignment_type 'trim' + --sequence_type 'protein' + #else if str($input_format) == 'ptaligntrimmedca': + --alignment_type 'trim' + --sequence_type $input_format_cond.sequence_type + #end if + --output '$output_pttree' + --output_dir '$output_pttree.files_path' + ]]> + </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> + <when value="ptalign"> + <param name="input_ptalign" format="ptalign" type="data" label="Aligned gene family sequences"> + <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"> + <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"> + <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"> + <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"> + <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"> + <validator type="empty_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 trees 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"> + <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 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" /> + </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" /> + </inputs> + <outputs> + <data name="output_pttree" format="pttree" label="Gene family phylogenetic trees on ${on_string}" /> + </outputs> + <tests> + <!-- Test framework does not currently support inputs whose associated files_path contains files to be analyzed. + <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 +**GeneFamilyAligner** tool. + +----- + +**Required options** + +**Other options** + + </help> + <citations> + <expand macro="citation1" /> + <expand macro="citations2to4" /> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Tue Apr 11 11:05:24 2017 -0400 @@ -0,0 +1,163 @@ +<?xml version='1.0' encoding='UTF-8'?> +<macros> + <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> + </requirements> + </xml> + <xml name="requirements_gene_family_aligner"> + <requirements> + <requirement type="package" version="0.8">plant_tribes_gene_family_aligner</requirement> + </requirements> + </xml> + <xml name="requirements_gene_family_classifier"> + <requirements> + <requirement type="package" version="0.8">plant_tribes_gene_family_classifier</requirement> + </requirements> + </xml> + <xml name="requirements_gene_family_integrator"> + <requirements> + <requirement type="package" version="0.8">plant_tribes_gene_family_integrator</requirement> + </requirements> + </xml> + <xml name="requirements_kaks_analysis"> + <requirements> + <requirement type="package" version="0.8">plant_tribes_kaks_analysis</requirement> + </requirements> + </xml> + <xml name="requirements_gene_family_phylogeny_builder"> + <requirements> + <requirement type="package" version="0.8">plant_tribes_gene_family_phylogeny_builder</requirement> + </requirements> + </xml> + <xml name="stdio"> + <stdio> + <exit_code range="1:"/> + <exit_code range=":-1"/> + <regex match="Error:"/> + <regex match="Exception:"/> + </stdio> + </xml> + <xml name="param_codon_alignments"> + <param name="codon_alignments" type="select" label="Construct orthogroup multiple codon alignments?"> + <option value="yes" selected="true">Yes</option> + <option value="no">No</option> + </param> + </xml> + <xml name="param_method"> + <param name="method" type="select" label="Protein clustering method"> + <option value="gfam" selected="true">GFam</option> + <option value="orthofinder">OrthoFinder</option> + <option value="orthomcl">OrthoMCL</option> + </param> + </xml> + <xml name="param_options_type"> + <param name="options_type" type="select" label="Options Configuration"> + <option value="basic" selected="true">Basic</option> + <option value="advanced">Advanced</option> + </param> + </xml> + <xml name="param_orthogroup_fna"> + <param name="orthogroup_fna" type="select" label="Process corresponding gene family classification orthogroups CDS fasta files?"> + <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"> + <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> + </xml> + <xml name="param_sequence_type"> + <param name="sequence_type" type="select" label="Sequence type used in the phylogenetic inference (dna)"> + <option value="protein" selected="true">Amino acid based</option> + <option value="dna">Nucleotide based</option> + </param> + </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> + <when value="mafft" /> + <when value="pasta"> + <param name="pasta_iter_limit" type="integer" value="3" min="1" label="Maximum number of iterations that the PASTA algorithm will execute" /> + </when> + </conditional> + </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?"> + <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> + <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" /> + </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?"> + <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"/> + </when> + </conditional> + </when> + </conditional> + </xml> + <xml name="citation1"> + <citation type="bibtex"> + @misc{None, + journal = {None}, + author = {1. Wafula EK}, + title = {Manuscript in preparation}, + year = {None}, + 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/plant_tribes_scaffolds.loc.sample Tue Apr 11 11:05:24 2017 -0400 @@ -0,0 +1,4 @@ +## Plant Tribes scaffolds +#Value Name Path Description +#22Gv1.0 22Gv1.0 /plant_tribes/scaffolds/22Gv1.0 22 plant genomes (Angiosperms clusters, version 1.0; 22Gv1.0) +#22Gv1.1 22Gv1.1 /plant_tribes/scaffolds/22Gv1.1 22 plant genomes (Angiosperms clusters, version 1.1; 22Gv1.1)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Tue Apr 11 11:05:24 2017 -0400 @@ -0,0 +1,6 @@ +<tables> + <table name="plant_tribes_scaffolds" comment_char="#"> + <columns>value, name, path, description</columns> + <file path="tool-data/plant_tribes_scaffolds.loc" /> + </table> +</tables>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/utils.py Tue Apr 11 11:05:24 2017 -0400 @@ -0,0 +1,42 @@ +import os +import shutil +import sys + + +def check_execution_errors(rc, stderr): + if rc != 0: + stop_err(stderr.read()) + + +def move_directory_files(source_dir, destination_dir): + source_directory = os.path.abspath(source_dir) + destination_directory = os.path.abspath(destination_dir) + if not os.path.isdir(destination_directory): + os.makedirs(destination_directory) + for dir_entry in os.listdir(source_directory): + source_entry = os.path.join(source_directory, dir_entry) + shutil.move(source_entry, destination_directory) + + +def stop_err(msg): + sys.stderr.write(msg) + sys.exit(1) + + +def write_html_output(output, title, dir): + with open(output, 'w') as fh: + fh.write('<html><head><h3>%s</h3></head>\n' % title) + fh.write('<body><p/><table cellpadding="2">\n') + fh.write('<tr><th>Size</th><th>Name</th></tr>\n') + for index, fname in enumerate(sorted(os.listdir(dir))): + if index % 2 == 0: + bgcolor = '#D8D8D8' + else: + bgcolor = '#FFFFFF' + try: + size = str(os.path.getsize(os.path.join(dir, fname))) + except: + size = 'unknown' + link = '<a href="%s" type="text/plain">%s</a>\n' % (fname, fname) + fh.write('<tr bgcolor="%s"><td>%s</td><td>%s</td></tr>\n' % (bgcolor, size, link)) + fh.write('</table></body></html>\n')