# HG changeset patch
# User greg
# Date 1491584429 14400
# Node ID 6accbd3a144971128b69e6672f66fab954bc44ec
Uploaded
diff -r 000000000000 -r 6accbd3a1449 .shed.yml
--- /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
diff -r 000000000000 -r 6accbd3a1449 gene_family_aligner.py
--- /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)
diff -r 000000000000 -r 6accbd3a1449 gene_family_aligner.xml
--- /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 @@
+
+ aligns gene family sequences
+
+ macros.xml
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['orthogroup_fna'] == 'no')
+
+
+ input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['orthogroup_fna'] == 'yes'
+
+
+
+
+
+
+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
+
+
+
+
+
+
+
diff -r 000000000000 -r 6accbd3a1449 macros.xml
--- /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 @@
+
+
+
+
+ plant_tribes_assembly_post_processor
+
+
+
+
+ plant_tribes_gene_family_aligner
+
+
+
+
+ plant_tribes_gene_family_classifier
+
+
+
+
+ plant_tribes_gene_family_integrator
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ @misc{None,
+ journal = {None},
+ author = {1. Wafula EK},
+ title = {Manuscript in preparation},
+ year = {None},
+ url = {https://github.com/dePamphilis/PlantTribes},}
+
+
+
+
+ @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},}
+
+
+ @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},}
+
+
+ @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},}
+
+
+
diff -r 000000000000 -r 6accbd3a1449 plant_tribes_scaffolds.loc.sample
--- /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)
diff -r 000000000000 -r 6accbd3a1449 run_pasta.py
--- /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 .
+
+# 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)
diff -r 000000000000 -r 6accbd3a1449 tool_data_table_conf.xml.sample
--- /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 @@
+
+