Mercurial > repos > peterjc > mira_assembler
changeset 0:03b240624b5a
Migrated tool version 0.0.1 from old tool shed archive to new tool shed repository
| author | peterjc |
|---|---|
| date | Tue, 07 Jun 2011 16:23:51 -0400 |
| parents | |
| children | e53a79816f5f |
| files | tools/sr_assembly/mira.py tools/sr_assembly/mira.txt tools/sr_assembly/mira.xml |
| diffstat | 3 files changed, 288 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/sr_assembly/mira.py Tue Jun 07 16:23:51 2011 -0400 @@ -0,0 +1,80 @@ +#!/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) + tcs_to_tabular("%s/%s_assembly/%s_d_results/%s_out.tcs" % n3, out_tcs) + for old, new in [("%s/%s_assembly/%s_d_results/%s_out.unpadded.fasta" % n3, out_fasta), + ("%s/%s_assembly/%s_d_results/%s_out.unpadded.fasta.qual" % n3, out_qual), + ("%s/%s_assembly/%s_d_results/%s_out.wig" % n3, out_wig), + ("%s/%s_assembly/%s_d_results/%s_out.caf" % n3, out_caf), + ("%s/%s_assembly/%s_d_results/%s_out.ace" % n3, out_ace)]: + if not os.path.isfile(old): + stop_err("Missing %s output file" % os.path.splitext(old)[-1]) + else: + shutil.move(old, new) + +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? +temp = "." +name, out_fasta, out_qual, out_tcs, out_ace, out_caf, out_wig, out_log = sys.argv[1:9] +start_time = time.time() +try: + cmd = " ".join(sys.argv[9:]) + child = subprocess.Popen(sys.argv[9:], + stdout=subprocess.PIPE, stderr=subprocess.STDOUT) +except Exception, err: + sys.stderr.write("Error invoking command:\n%s\n\n%s\n" % (cmd, err)) + sys.exit(1) +#Use .communicate as can get deadlocks with .wait(), +stdout, stderr = child.communicate() +run_time = time.time() - start_time +return_code = child.returncode +handle = open(out_log, "w") +handle.write(stdout) +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"
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/sr_assembly/mira.txt Tue Jun 07 16:23:51 2011 -0400 @@ -0,0 +1,77 @@ +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: + +<tool file="sr_assembly/seq_primer_clip.xml" /> + +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) + + +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.
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tools/sr_assembly/mira.xml Tue Jun 07 16:23:51 2011 -0400 @@ -0,0 +1,131 @@ +<tool id="mira_assembler" name="Assemble with MIRA" version="0.0.1"> + <description>Takes Sanger, Roche, and Illumina data</description> + <command interpreter="python">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 + + </command> + <inputs> + <param name="job_method" type="select" label="Assembly method" help="Mapping mode requires backbone/reference sequence(s)"> + <option value="denovo">De novo</option> + <option value="mapping">Mapping</option> + </param> + <param name="job_type" type="select" label="Assembly type"> + <option value="genome">Genome</option> + <option value="est">EST (transcriptome)</option> + </param> + <param name="job_quality" type="select" label="Assembly quality grade"> + <option value="normal">Normal</option> + <option value="draft">Draft</option> + <option value="accurate">Accurate</option> + </param> + <!-- Backbone --> + <conditional name="condBackbone"> + <param name="use" type="select" label="Backbones/reference chromosomes?" help="Required for mapping, optional for de novo assembly."> + <option value="false">No</option> + <option value="true">Yes</option> + </param> + <when value="false" /> + <when value="true"> + <!-- MIRA also allows CAF and GenBank, but Galaxy doesn't define those (yet) --> + <param name="filename" type="data" format="fasta" label="Backbone/reference sequences" help="FASTA format" /> + </when> + </conditional> + <!-- Sanger --> + <conditional name="condSanger"> + <param name="use" type="select" label="Sanger/Capillary reads?"> + <option value="false">No</option> + <option value="true">Yes</option> + </param> + <when value="false" /> + <when value="true"> + <param name="filename" type="data" format="fastq" label="Sanger/Capillary reads file" help="FASTQ format" /> + </when> + </conditional> + <!-- Roche 454 --> + <conditional name="condRoche"> + <param name="use" type="select" label="454 reads?"> + <option value="false">No</option> + <option value="true">Yes</option> + </param> + <when value="false" /> + <when value="true"> + <param name="filename" type="data" format="fastq,sff" label="Roche 454 reads file" help="FASTQ format" /> + </when> + </conditional> + <!-- Illumina --> + <conditional name="condIllumina"> + <param name="use" type="select" label="Solexa/Illumina reads?"> + <option value="false">No</option> + <option value="true">Yes</option> + </param> + <when value="false" /> + <when value="true"> + <param name="filename" type="data" format="fastq" label="Solexa/Illumina reads file" help="FASTQ format" /> + </when> + </conditional> + </inputs> + <outputs> + <data name="out_fasta" format="fasta" label="MIRA contigs (FASTA)" /> + <data name="out_qual" format="qual454" label="MIRA contigs (QUAL)" /> + <data name="out_tcs" format="tabular" label="MIRA contigs summary" /> + <data name="out_caf" format="txt" label="MIRA contigs (CAF)" /> + <data name="out_ace" format="txt" label="MIRA contigs (ACE)" /> + <data name="out_wig" format="wig" label="MIRA coverage (Wiggle)" /> + <data name="out_log" format="txt" label="MIRA log" /> + </outputs> + <tests> + </tests> + <requirements> + <requirement type="python-module">Bio</requirement> + </requirements> + <help> + +**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. + + </help> +</tool>