# HG changeset patch
# User peterjc
# Date 1308213840 14400
# Node ID e53a79816f5fb23ce6092eaf0032a87fe5c97ec6
# Parent 03b240624b5aae30ae004d94dfc6828dc7b3e748
v0.0.2 - Improve capture of stdout/stderr (should see it as it runs)
diff -r 03b240624b5a -r e53a79816f5f mira_wrapper_v0.0.2.tar.gz/tools/sr_assembly/mira.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mira_wrapper_v0.0.2.tar.gz/tools/sr_assembly/mira.py Thu Jun 16 04:44:00 2011 -0400
@@ -0,0 +1,107 @@
+#!/usr/bin/env python
+"""A simple wrapper script to call MIRA and collect its output.
+"""
+import os
+import sys
+import subprocess
+import shutil
+import time
+
+def stop_err(msg, err=1):
+ sys.stderr.write(msg+"\n")
+ sys.exit(err)
+
+def tcs_to_tabular(old, new):
+ in_handle = open(old, "rU")
+ out_handle = open(new, "w")
+ assert in_handle.readline() == "#TCS V1.0\n"
+ assert in_handle.readline() == "#\n"
+ assert in_handle.readline() == "# contig name padPos upadPos | B Q | tcov covA covC covG covT cov* | qA qC qG qT q* | S | Tags\n"
+ assert in_handle.readline() == "#\n"
+ out_handle.write("#%s\n" % "\t".join(["contig", "pasPos", "upadPos", "B", "Q",
+ "tcov", "covA", "covC", "covG", "covT", "cov*",
+ "qA", "qC", "qG", "qT", "q*", "S", "Tags"]))
+ for line in in_handle:
+ parts = line.rstrip("\n").split(None,22)
+ assert parts[3] == parts[6] == parts[13] == parts[19] == parts[21] == "|"
+ wanted = parts[:3] + parts[4:6]+parts[7:13]+parts[14:19]+parts[20:21]+parts[22:]
+ out_handle.write("%s\n" % "\t".join(wanted))
+ out_handle.close()
+ in_handle.close()
+
+def collect_output(temp, name):
+ n3 = (temp, name, name, name)
+ f = "%s/%s_assembly/%s_d_results" % (temp, name, name)
+ if not os.path.isdir(f):
+ stop_err("Missing output folder")
+ if not os.listdir(f):
+ stop_err("Empty output folder")
+ for old, new in [("%s/%s_out.unpadded.fasta" % (f, name), out_fasta),
+ ("%s/%s_out.unpadded.fasta.qual" % (f, name), out_qual),
+ ("%s/%s_out.wig" % (f, name), out_wig),
+ ("%s/%s_out.caf" % (f, name), out_caf),
+ ("%s/%s_out.ace" % (f, name), out_ace)]:
+ if not os.path.isfile(old):
+ stop_err("Missing %s output file" % os.path.splitext(old)[-1])
+ else:
+ shutil.move(old, new)
+ tcs_to_tabular("%s/%s_assembly/%s_d_results/%s_out.tcs" % n3, out_tcs)
+
+def clean_up(temp, name):
+ folder = "%s/%s_assembly" % (temp, name)
+ if os.path.isdir(folder):
+ shutil.rmtree(folder)
+
+#TODO - Run MIRA in /tmp or a configurable directory?
+#Currently Galaxy puts us somewhere safe like:
+#/opt/galaxy-dist/database/job_working_directory/846/
+temp = "."
+name, out_fasta, out_qual, out_tcs, out_ace, out_caf, out_wig, out_log = sys.argv[1:9]
+
+start_time = time.time()
+cmd = " ".join(sys.argv[9:])
+
+assert os.path.isdir(temp)
+d = "%s_assembly" % name
+assert not os.path.isdir(d)
+try:
+ #Check path access
+ os.mkdir(d)
+except Exception, err:
+ sys.stderr.write("Error making directory %s\n%s" % (d, err))
+ sys.exit(1)
+
+#print os.path.abspath(".")
+#print cmd
+
+handle = open(out_log, "w")
+try:
+ #Run MIRA
+ child = subprocess.Popen(sys.argv[9:],
+ stdout=handle,
+ stderr=subprocess.STDOUT)
+except Exception, err:
+ sys.stderr.write("Error invoking command:\n%s\n\n%s\n" % (cmd, err))
+ #TODO - call clean up?
+ handle.write("Error invoking command:\n%s\n\n%s\n" % (cmd, err))
+ handle.close()
+ sys.exit(1)
+#Use .communicate as can get deadlocks with .wait(),
+stdout, stderr = child.communicate()
+assert not stdout and not stderr #Should be empty as sent to handle
+run_time = time.time() - start_time
+return_code = child.returncode
+handle.write("\n\nMIRA took %0.2f minutes\n" % (run_time / 60.0))
+print "MIRA took %0.2f minutes" % (run_time / 60.0)
+if return_code:
+ handle.write("Return error code %i from command:\n" % return_code)
+ handle.write(cmd + "\n")
+ handle.close()
+ clean_up(temp, name)
+ stop_err("Return error code %i from command:\n%s" % (return_code, cmd),
+ return_code)
+handle.close()
+
+collect_output(temp, name)
+clean_up(temp, name)
+print "Done"
diff -r 03b240624b5a -r e53a79816f5f mira_wrapper_v0.0.2.tar.gz/tools/sr_assembly/mira.txt
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mira_wrapper_v0.0.2.tar.gz/tools/sr_assembly/mira.txt Thu Jun 16 04:44:00 2011 -0400
@@ -0,0 +1,78 @@
+Galaxy tool to wrap the MIRA sequence assembly program
+======================================================
+
+This tool is copyright 2011 by Peter Cock, The James Hutton Institute
+(formerly SCRI, Scottish Crop Research Institute), UK. All rights reserved.
+See the licence text below.
+
+This tool is a short Python script (to collect the MIRA output and move it
+to where Galaxy expects the files, and convert MIRA's TCS file into a tab
+separate file for use in Galaxy). There are just two files to install:
+
+* mira.py (the Python script)
+* mira.xml (the Galaxy tool definition)
+
+The suggested location is the tools/sr_assembly folder. You will also need to
+modify the tools_conf.xml file to tell Galaxy to offer the tool and also do
+this to tools_conf.xml.sample in order to run any tests:
+
+
+
+You will also need to install MIRA, we used version 3.2.1. See:
+
+http://chevreux.org/projects_mira.html
+http://sourceforge.net/projects/mira-assembler/
+
+WARNING: This tool was developed to construct viral genome assembly and
+mapping pipelines, for which the run time and memory requirements are
+negligible. For larger tasks, be aware that MIRA can require vast amounts
+of RAM and run-times of over a week are possible. This tool wrapper makes
+no attempt to spot and reject such large jobs.
+
+
+History
+=======
+
+v0.0.1 - Initial version (working prototype)
+v0.0.2 - Improve capture of stdout/stderr (should see it as it runs)
+
+
+Developers
+==========
+
+This script and related tools are being developed on the following hg branch:
+http://bitbucket.org/peterjc/galaxy-central/src/tools
+
+For making the "Galaxy Tool Shed" http://community.g2.bx.psu.edu/ tarball use
+the following command from the Galaxy root folder:
+
+tar -czf mira_wrapper.tar.gz tools/sr_assembly/mira.*
+
+Check this worked:
+
+$ tar -tzf mira_wrapper.tar.gz
+tools/sr_assembly/mira.py
+tools/sr_assembly/mira.txt
+tools/sr_assembly/mira.xml
+
+
+Licence (MIT/BSD style)
+=======================
+
+Permission to use, copy, modify, and distribute this software and its
+documentation with or without modifications and for any purpose and
+without fee is hereby granted, provided that any copyright notices
+appear in all copies and that both those copyright notices and this
+permission notice appear in supporting documentation, and that the
+names of the contributors or copyright holders not be used in
+advertising or publicity pertaining to distribution of the software
+without specific prior permission.
+
+THE CONTRIBUTORS AND COPYRIGHT HOLDERS OF THIS SOFTWARE DISCLAIM ALL
+WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL THE
+CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT
+OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
+OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
+OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE
+OR PERFORMANCE OF THIS SOFTWARE.
diff -r 03b240624b5a -r e53a79816f5f mira_wrapper_v0.0.2.tar.gz/tools/sr_assembly/mira.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mira_wrapper_v0.0.2.tar.gz/tools/sr_assembly/mira.xml Thu Jun 16 04:44:00 2011 -0400
@@ -0,0 +1,131 @@
+
+ Takes Sanger, Roche, and Illumina data
+ mira.py mira $out_fasta $out_qual $out_tcs $out_ace $out_caf $out_wig $out_log
+##Give the wrapper script list of output filenames, then the mira command...
+mira --job=$job_method,$job_type,$job_quality
+
+##Input files
+#if $condBackbone.use == "true":
+ ## Can this be linked to job_method as well? If mapping we need the backbone...
+ -SB:lb=yes -SB:bft=fasta -FN:bbin=${condBackbone.filename}
+#end if
+#if $condSanger.use == "true":
+ Sanger_SETTINGS
+ ## Not easy to add sanger to --job, so use load_sequence_data(lsd) instead
+ -LR:lsd=yes
+ ## I expect hard trimmed FASTQ files with no NCBI traceinfo XML file
+ -LR:mxti=no -LR:ft=fastq -FN:fqi=${condSanger.filename}
+#end if
+#if $condRoche.use == "true":
+ 454_SETTINGS
+ ## Not easy to add 454 to --job, so use load_sequence_data(lsd) instead
+ -LR:lsd=yes
+ ## I expect hard trimmed FASTQ files with no NCBI traceinfo XML file
+ -LR:mxti=no -LR:ft=fastq -FN:fqi=${condRoche.filename}
+#end if
+#if $condIllumina.use == "true":
+ SOLEXA_SETTINGS
+ ## Not easy to add solexa to --job, so use load_sequence_data(lsd) instead
+ -LR:lsd=yes -LR:ft=fastq -FN:fgi=${condIllumina.filename}
+ ##TODO - Look at -LR FASTQ qual offset (fqqo)
+#end if
+
+
+##Output files
+COMMON_SETTINGS
+##remove_rollover_logs, remove_log_directory
+-OUT:rrol=yes -OUT:rld=yes
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Bio
+
+
+
+**What it does**
+
+Runs MIRA v3, collects the output, and throws away all the temporary files.
+
+The MIRA transposed contig summary (TCS) file is converted into a tabular file for use within Galaxy.
+This records one line per base per contig, and including things like the base, quality, coverage and any tags.
+
+**Citation**
+
+This tool uses MIRA. If you use this tool in scientific work leading to a
+publication, please cite:
+
+Chevreux et al. (1999) Genome Sequence Assembly Using Trace Signals and Additional Sequence Information Computer Science and Biology: Proceedings of the German Conference on Bioinformatics (GCB) 99, pp. 45-56.
+
+
+