Mercurial > repos > greg > gene_family_aligner
changeset 6:badd2d0f1689 draft
Uploaded
author | greg |
---|---|
date | Mon, 10 Apr 2017 09:36:08 -0400 |
parents | b52d29988df8 |
children | 529f4635ddb4 |
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, 10 insertions(+), 201 deletions(-) [+] |
line wrap: on
line diff
--- a/.shed.yml Fri Apr 07 14:37:29 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,13 +0,0 @@ -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
--- a/gene_family_aligner.py Fri Apr 07 14:37:29 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,59 +0,0 @@ -#!/usr/bin/env python -import argparse -import os -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.codon_alignments is not None: - cmd += ' --codon_alignments' -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) -if args.codon_alignments is None: - src_output_dir = OUTPUT_DIR -else: - src_output_dir = os.path.join(OUTPUT_DIR, 'orthogroups_aln') -utils.move_directory_files(src_output_dir, args.output_dir) -utils.write_html_output(args.output, 'Aligned gene family sequences', args.output_dir)
--- a/gene_family_aligner.xml Fri Apr 07 14:37:29 2017 -0400 +++ b/gene_family_aligner.xml Mon Apr 10 09:36:08 2017 -0400 @@ -1,4 +1,4 @@ -<tool id="plant_tribes_gene_family_aligner" name="GeneFamilyAligner" version="0.8.0"> +<tool id="plant_tribes_gene_family_aligner" name="GeneFamilyAligner" version="@WRAPPER_VERSION@.0"> <description>aligns gene family sequences</description> <macros> <import>macros.xml</import> @@ -23,18 +23,11 @@ --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': @@ -57,6 +50,8 @@ #end if #end if #end if + --output '$output' + --output_dir '$output.files_path' ]]> </command> <inputs> @@ -88,12 +83,7 @@ </conditional> </inputs> <outputs> - <data name="output_ptortho" format="ptortho" label="Aligned gene family sequences on ${on_string}"> - <filter>input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'no')</filter> - </data> - <data name="output_ptorthocs" format="ptorthocs" label="Aligned gene family sequences and corresponding coding sequences on ${on_string}"> - <filter>input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'yes'</filter> - </data> + <data name="output" format="ptalign" label="Aligned gene family sequences on ${on_string}" /> </outputs> <tests> <!-- Test framework does not currently support inputs whose associated files_path contains files to be analyzed.
--- a/macros.xml Fri Apr 07 14:37:29 2017 -0400 +++ b/macros.xml Mon Apr 10 09:36:08 2017 -0400 @@ -1,5 +1,6 @@ <?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> @@ -25,6 +26,11 @@ <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:"/>
--- a/plant_tribes_scaffolds.loc.sample Fri Apr 07 14:37:29 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,4 +0,0 @@ -## 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)
--- a/run_pasta.py Fri Apr 07 14:37:29 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,63 +0,0 @@ -#! /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)
--- a/tool_data_table_conf.xml.sample Fri Apr 07 14:37:29 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,6 +0,0 @@ -<tables> - <table name="plant_tribes_scaffolds" comment_char="#"> - <columns>value, name, path, description</columns> - <file path="tool-data/plant_tribes_scaffolds.loc" /> - </table> -</tables>
--- a/utils.py Fri Apr 07 14:37:29 2017 -0400 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 @@ -1,42 +0,0 @@ -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')