# HG changeset patch
# User greg
# Date 1496940380 14400
# Node ID 7ba9469800b93527f28489df166c464c3d3517ac
Uploaded
diff -r 000000000000 -r 7ba9469800b9 gene_family_aligner.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/gene_family_aligner.py Thu Jun 08 12:46:20 2017 -0400
@@ -0,0 +1,55 @@
+#!/usr/bin/env python
+import argparse
+import os
+
+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 trimAls 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=0, type=float, help='Remove sites in alignments with gaps of')
+parser.add_argument('--iterative_realignment', dest='iterative_realignment', type=int, default=0, help='Maximum number of iterations')
+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 files_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=0, type=float, help='Remove sequences with gaps of')
+
+args = parser.parse_args()
+
+# Build the command line.
+cmd = 'GeneFamilyAligner'
+cmd += ' --orthogroup_faa %s' % args.orthogroup_faa
+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 > 0:
+ cmd += ' --gap_trimming %4f' % args.gap_trimming
+if args.remove_sequences > 0:
+ cmd += ' --remove_sequences %4f' % args.remove_sequences
+if args.iterative_realignment > 0:
+ cmd += ' --iterative_realignment %d' % args.iterative_realignment
+
+# Run the command.
+utils.run_command(cmd)
+
+# Handle outputs.
+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)
diff -r 000000000000 -r 7ba9469800b9 gene_family_aligner.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/gene_family_aligner.xml Thu Jun 08 12:46:20 2017 -0400
@@ -0,0 +1,204 @@
+
+ aligns integrated orthologous gene family clusters
+
+ macros.xml
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ (input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'no')) and remove_gappy_sequences_cond['remove_gappy_sequences'] == 'no'
+
+
+ (input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'yes')) and remove_gappy_sequences_cond['remove_gappy_sequences'] == 'no'
+
+
+ (input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'no')) and (remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'yes')
+
+
+ (input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'yes')) and (remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'yes')
+
+
+ (input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'no')) and (remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'no')
+
+
+ (input_format_cond['input_format'] == 'ptortho' or (input_format_cond['input_format'] == 'ptorthocs' and input_format_cond['codon_alignments'] == 'yes')) and (remove_gappy_sequences_cond['remove_gappy_sequences'] == 'yes' and remove_gappy_sequences_cond['remove_sequences_with_gaps_cond']['remove_sequences_with_gaps'] == 'no')
+
+
+
+
+
+
+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 estimates protein and codon multiple sequence alignments
+of integrated orthologous gene family fasta files produced by the GeneFamilyIntegrator tool.
+
+-----
+
+**Required options**
+
+ * **Classified orthogroup fasta files** - orthogroup fasta files produced by the GeneFamilyClassifier tool selected from your history. Depending on how the GeneFamilyClassifier tool was executed, these could either be proteins or proteins and their corresponding coding sequences.
+
+ * **Multiple sequence alignment method** - method for estimating orthogroup multiple sequence alignments. PlantTribes estimates alignments using either MAFFT's L-INS-i algorithm or the divide and conquer approach implemented in the PASTA pipeline for large alignments.
+
+ - **PASTA iteration limit** - number of PASTA iterations. By default, PASTA performs 3 iterations.
+
+ * **Codon alignments** - select 'Yes' to create codon multiple sequence alignments. This option requires protein and their corresponding coding sequences to be provided as input data.
+
+**Other options**
+
+ * **Alignment post-processing configuration** - select 'Yes' to enable multiple sequence alignment post-processing configuration options.
+
+ - **Trimming method** - multiple sequence alignment trimming method. PlantTribes trims alignments using two automated approaches implemented in trimAl. Gap score based trimming removes alignments sites that do not achieve a user specified gap score. For example, a setting of 0.1 removes sites that have gaps in 90% or more of the sequences in the multiple sequence alignment. The automated heuristic trimming approach determines the best automated trimAl method to trim a given alignment as described in the trimAl tutorial `trimAl`_.
+
+ - **Gap score** - the fraction of sequences with gap allowed in an alignment site. The score is restricted to the range 0.0 - 1.0. Zero value has no effect.
+
+ - **Remove sequences** - select 'Yes' to remove sequences in multiple sequence alignments that do not achieve a user specified alignment coverage score. For example, a setting of 0.7 removes sequences with more than 30% gaps in the alignment. This option requires one of the trimming methods to be set.
+
+ - **Coverage score** - minimum fraction of sites without gaps for a sequence in a multiple sequence alignment. The score is restricted to the range 0.0 - 1.0. Zero value has no effect.
+
+ - **Realignment iteration limit** - number of iterations to perform trimming, removal of sequences, and realignment of orthogroup sequences. Zero value has no effect.
+
+.. _trimAl: http://trimal.cgenomics.org
+
+
+
+
+
+ @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},}
+
+
+ @article{Katoh2013,
+ journal = {Molecular biology and evolution},
+ author = {3. Katoh K, Standley DM},
+ title = {MAFFT multiple sequence alignment software version 7: improvements in performance and usability},
+ year = {2013},
+ volume = {30},
+ number = {4},
+ pages = {772-780},}
+
+
+ @article{Mirarab2014,
+ journal = {Research in Computational Molecular Biology (RECOMB)},
+ author = {4. Mirarab S, Nguyen N, Warnow T},
+ title = {PASTA: Ultra-Large Multiple Sequence Alignment. In R. Sharan (Ed.)},
+ year = {2014},
+ pages = {177–191},
+ url = {https://github.com/smirarab/pasta},}
+
+
+ @article{Capella-Gutierrez2009,
+ journal = {Bioinformatics,},
+ author = {5. Capella-Gutierrez S, Silla-Martínez JM, Gabaldón T},
+ title = {trimAl: a tool for automated alignment trimming in large-scale phylogenetic analyses},
+ year = {2009},
+ volume = {25},
+ number = {15},
+ pages = {1972-1973},}
+
+
+
diff -r 000000000000 -r 7ba9469800b9 macros.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml Thu Jun 08 12:46:20 2017 -0400
@@ -0,0 +1,130 @@
+
+
+ 1.0
+
+
+ plant_tribes_assembly_post_processor
+
+
+
+
+ plant_tribes_gene_family_aligner
+
+
+
+
+ plant_tribes_gene_family_classifier
+
+
+
+
+ plant_tribes_gene_family_integrator
+
+
+
+
+ plant_tribes_kaks_analysis
+
+
+
+
+ r-optparse
+
+
+
+
+ plant_tribes_gene_family_phylogeny_builder
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ @misc{None,
+ journal = {None},
+ author = {1. Wafula EK},
+ title = {Manuscript in preparation},
+ year = {None},
+ url = {https://github.com/dePamphilis/PlantTribes},}
+
+
+
diff -r 000000000000 -r 7ba9469800b9 plant_tribes_scaffolds.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/plant_tribes_scaffolds.loc.sample Thu Jun 08 12:46:20 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 7ba9469800b9 run_pasta.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/run_pasta.py Thu Jun 08 12:46:20 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 as 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 7ba9469800b9 tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Thu Jun 08 12:46:20 2017 -0400
@@ -0,0 +1,6 @@
+
+