Mercurial > repos > greg > gene_family_aligner
changeset 0:6accbd3a1449 draft
Uploaded
| author | greg |
|---|---|
| date | Fri, 07 Apr 2017 13:00:29 -0400 |
| parents | |
| children | 4f1c3b8c9ab1 |
| files | .shed.yml gene_family_aligner.py gene_family_aligner.xml macros.xml plant_tribes_scaffolds.loc.sample run_pasta.py tool_data_table_conf.xml.sample utils.py |
| diffstat | 8 files changed, 473 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/.shed.yml Fri Apr 07 13:00:29 2017 -0400 @@ -0,0 +1,13 @@ +name: plant_tribes_gene_family_aligner +owner: greg +description: | + Contains a tool that integrates de novo assembly sequences with scaffold gene family sequences. +homepage_url: https://github.com/dePamphilis/PlantTribes +long_description: | + Contains a tool that 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. This tool aligns gene family sequences. +remote_repository_url: https://github.com/gregvonkuster/galaxy_tools/tree/master/tools/plant_tribes/gene_family_aligner +type: unrestricted +categories: +- Phylogenetics
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gene_family_aligner.py Fri Apr 07 13:00:29 2017 -0400 @@ -0,0 +1,54 @@ +#!/usr/bin/env python +import argparse +import subprocess + +import utils + +OUTPUT_DIR = 'geneFamilyAlignments_dir' + +parser = argparse.ArgumentParser() +parser.add_argument('--alignment_method', dest='alignment_method', help='Multiple sequence alignments method') +parser.add_argument('--automated_trimming', dest='automated_trimming', default=None, help="Trims alignments using trimAl's ML heuristic trimming approach") +parser.add_argument('--codon_alignments', dest='codon_alignments', default=None, help="Flag for constructing orthogroup multiple codon alignments") +parser.add_argument('--gap_trimming', dest='gap_trimming', default=None, type=float, help='Remove sites in alignments with gaps of') +parser.add_argument('--iterative_realignment', dest='iterative_realignment', type=int, default=None, help='"Maximum number of iterations') +parser.add_argument('--method', dest='method', help='Protein clustering method') +parser.add_argument('--num_threads', dest='num_threads', type=int, help='Number of threads to use for execution') +parser.add_argument('--orthogroup_faa', dest='orthogroup_faa', help="Directory of input fasta datasets") +parser.add_argument('--output', dest='output', help="Output dataset") +parser.add_argument('--output_dir', dest='output_dir', help="Output dataset file_path directory") +parser.add_argument('--pasta_iter_limit', dest='pasta_iter_limit', type=int, default=None, help='"Maximum number of iteration that the PASTA algorithm will execute') +parser.add_argument('--pasta_script_path', dest='pasta_script_path', default=None, help='Path to script for executing pasta') +parser.add_argument('--remove_sequences', dest='remove_sequences', default=None, type=float, help='Remove sequences with gaps of') +parser.add_argument('--scaffold', dest='scaffold', help='Orthogroups or gene families proteins scaffold') + +args = parser.parse_args() + +# Build the command line. +cmd = 'GeneFamilyAligner' +cmd += ' --orthogroup_faa %s' % args.orthogroup_faa +cmd += ' --scaffold %s' % args.scaffold +cmd += ' --method %s' % args.method +cmd += ' --alignment_method %s' % args.alignment_method +if args.alignment_method == 'pasta': + if args.pasta_script_path is not None: + cmd += ' --pasta_script_path %s' % args.pasta_script_path + if args.pasta_iter_limit is not None: + cmd += ' --pasta_iter_limit %d' % args.pasta_iter_limit +cmd += ' --num_threads %d' % args.num_threads +if args.orthogroup_fna is not None: + cmd += ' --orthogroup_fna' +if args.automated_trimming is not None: + cmd += ' --automated_trimming' +if args.gap_trimming is not None: + cmd += ' --gap_trimming %4f' % args.gap_trimming +if args.remove_sequences is not None: + cmd += ' --remove_sequences %4f' % args.remove_sequences +if args.iterative_realignment is not None: + cmd += ' --iterative_realignment %d' % args.iterative_realignment +# 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, 'Aligned gene family sequences', args.output_dir)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/gene_family_aligner.xml Fri Apr 07 13:00:29 2017 -0400 @@ -0,0 +1,145 @@ +<tool id="plant_tribes_gene_family_aligner" name="GeneFamilyAligner" version="0.8.0"> + <description>aligns gene family sequences</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements_gene_family_aligner" /> + <expand macro="stdio" /> + <command> + <![CDATA[ + #set input_format = $input_format_cond.input_format + #set scaffold = $input_format_cond.scaffold + #set alignment_method_cond = $input_format_cond.alignment_method_cond + #set alignment_method = $alignment_method_cond.alignment_method + + python $__tool_directory__/gene_family_aligner.py + --scaffold '$scaffold.fields.path' + --method $input_format_cond.method + --alignment_method $alignment_method + #if str($alignment_method) == 'pasta': + --pasta_script_path '$__tool_directory__/run_pasta.py' + --pasta_iter_limit $alignment_method_cond.pasta_iter_limit + #end if + --num_threads \${GALAXY_SLOTS:-4} + #if str($input_format) == 'ptortho': + --orthogroup_faa '$input_format_cond.input_ptortho.extra_files_path' + --output '$output_ptortho' + --output_dir '$output_ptortho.files_path' + #else: + ## str($input_format) == 'ptorthocs' + --orthogroup_faa '$input_format_cond.input_ptorthocs.extra_files_path' + #if str($input_format_cond.codon_alignments) == 'yes': + --codon_alignments 'true' + --output '$output_ptorthocs' + --output_dir '$output_ptorthocs.files_path' + #else: + --output '$output_ptortho' + --output_dir '$output_ptortho.files_path' + #end if + #end if + #if str($options_type_cond.options_type) == 'advanced': + #set remove_gappy_sequences_cond = $options_type_cond.remove_gappy_sequences_cond + #set remove_gappy_sequences = $remove_gappy_sequences_cond.remove_gappy_sequences + #if str($remove_gappy_sequences) == 'yes': + #set trim_type_cond = $remove_gappy_sequences_cond.trim_type_cond + #set trim_type = $trim_type_cond.trim_type + #if str($trim_type) == 'gap_trimming': + --gap_trimming $trim_type_cond.gap_trimming + #else: + ## str($trim_type) == 'automated_trimming' + --automated_trimming 'true' + #end if + #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 + --iterative_realignment $remove_sequences_with_gaps_cond.iterative_realignment + #end if + #end if + #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">Gene family clusters</option> + <option value="ptorthocs">Gene family clusters with corresponding coding sequences</option> + </param> + <when value="ptortho"> + <param name="input_ptortho" format="ptortho" type="data" label="Gene family clusters" /> + <expand macro="param_scaffold" /> + <expand macro="param_method" /> + <expand macro="cond_alignment_method" /> + </when> + <when value="ptorthocs"> + <param name="input_ptorthocs" format="ptorthocs" type="data" label="Gene family clusters with corresponding coding sequences" /> + <expand macro="param_scaffold" /> + <expand macro="param_method" /> + <expand macro="cond_alignment_method" /> + <expand macro="param_codon_alignments" /> + </when> + </conditional> + <conditional name="options_type_cond"> + <expand macro="param_options_type" /> + <when value="basic" /> + <when value="advanced"> + <expand macro="cond_remove_gappy_sequences" /> + </when> + </conditional> + </inputs> + <outputs> + <data name="output_ptortho" format="ptortho" label="Integrated gene family clusters on ${on_string}"> + <filter>input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['orthogroup_fna'] == 'no')</filter> + </data> + <data name="output_ptorthocs" format="ptorthocs" label="Integrated gene family clusters and corresponding coding sequences on ${on_string}"> + <filter>input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['orthogroup_fna'] == 'yes'</filter> + </data> + </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 for comparative and evolutionary +analyses of genome-scale gene families and transcriptomes. This tool aligns gene family sequences. + +----- + +**Required options** + + * **Select type of data to sub sample** + + - **Gene family clusters** - sequences classified into gene family clusters. + - **Gene family clusters with corresponding coding sequences** - sequences classified into gene family clusters including corresponding coding sequences. + + - **Construct orthogroup multiple codon alignments** - construct orthogroup multiple codon alignments. + + * **Gene family scaffold** - one of the PlantTribes gene family scaffolds [2-4] installed into Galaxy by the PlantTribes Scaffold Data Manager tool. + * **Protein clustering method** - gene family scaffold protein clustering method as described in the AssemblyPostProcessor tool. + + * **Select method for multiple sequence alignments** + + - **MAFFT algorithm** - mafft algorithm. + - **Pasta algorithm** - pasta algorithm. + + - **Maximum number of iterations that the PASTA algorithm will execute** - maximum number of iterations that the PASTA algorithm will execute. + +**Other options** + + * **Remove gappy sequences in alignments** + + - **Select process used for gap trimming** - either nucleotide based or using trimAl's ML heuristic trimming approach + + - **Nucleotide based** + + - **Remove sites in alignments with gaps of** + - **Maximum number of iterations** - maximum number of iterations for iterative orthogroups realignment, trimming and fitering + + </help> + <citations> + <expand macro="citation1" /> + <expand macro="citations2to4" /> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Fri Apr 07 13:00:29 2017 -0400 @@ -0,0 +1,146 @@ +<?xml version='1.0' encoding='UTF-8'?> +<macros> + <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="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" display="radio" 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" display="radio" 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="cond_alignment_method"> + <conditional name="alignment_method_cond"> + <param name="alignments_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 gap trimming"> + <option value="gap_trimming" selected="true">Nucleotide based </option> + <option value="automated_trimming">Trim alignments using trimAl's ML heuristic trimming approach</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 Fri Apr 07 13:00:29 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/run_pasta.py Fri Apr 07 13:00:29 2017 -0400 @@ -0,0 +1,63 @@ +#! /usr/bin/env python + +"""Main script of PASTA in command-line mode - this simply invokes the main + function found in pasta/mainpasta.py +""" + +# This file is part of PASTA which is forked from SATe + +# PASTA like SATe is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <http://www.gnu.org/licenses/>. + +# Jiaye Yu and Mark Holder, University of Kansas + +if __name__ == "__main__": + import os + import sys + from pasta.mainpasta import pasta_main + from pasta import MESSENGER + sys.setrecursionlimit(100000) + _PASTA_DEBUG = os.environ.get('PASTA_DEBUG') + _DEVELOPER = _PASTA_DEBUG and _PASTA_DEBUG != '0' + + if not _DEVELOPER: + _PASTA_DEVELOPER = os.environ.get('PASTA_DEVELOPER') + _DEVELOPER = _PASTA_DEVELOPER and _PASTA_DEVELOPER != '0' + try: + rc, temp_dir, temp_fs = pasta_main() + if not rc: + raise ValueError("Unknown PASTA execution error") + if (temp_dir is not None) and (os.path.exists(temp_dir)): + MESSENGER.send_info("Note that temporary files from the run have not been deleted, they can be found in:\n '%s'\n" % temp_dir) + if sys.platform.lower().startswith('darwin') and ("'" not in temp_dir): + MESSENGER.send_info(''' +If you cannot see this directory in the Finder application, you may want to use +the 'open' command executed from a Terminal. You can do this by launching the +/Applications/Utilities/Terminal program and then typing + +open '%s' + +followed by a return at the prompt. If the argument to the open command is a +directory, then it should open a Finder window in the directory (even if that +directory is hidden by default). +''' % temp_dir) + except Exception, x: + if _DEVELOPER: + raise + message = "PASTA is exiting because of an error:\n%s " % str(x) + try: + from pasta import MESSENGER + MESSENGER.send_error(message) + except: + sys.stderr.write(message) + sys.exit(1)
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Fri Apr 07 13:00:29 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 Fri Apr 07 13:00:29 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')