Mercurial > repos > peterjc > mira4_assembler

changeset 20:aeb3e35f8236 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded v0.0.4 preview, made MAF and BAM output optional
author peterjc
date Tue, 10 Jun 2014 10:11:58 -0400
parents 8487d70e82aa
children 4abe8d59a438
files tools/mira4/README.rst tools/mira4/mira4.py tools/mira4/mira4_de_novo.xml tools/mira4/mira4_mapping.xml tools/mira4/repository_dependencies.xml tools/mira4/tool_dependencies.xml
diffstat 6 files changed, 97 insertions(+), 20 deletions(-) [+]
line wrap: on
line diff
--- a/tools/mira4/README.rst	Wed May 21 06:56:06 2014 -0400
+++ b/tools/mira4/README.rst	Tue Jun 10 10:11:58 2014 -0400
@@ -91,6 +91,8 @@
           (``$TMPDIR``, ``$TEMP``, or ``$TMP`` in that order). This was
           previously hard coded as ``/tmp``.
 v0.0.3  - Updated to target MIRA 4.0.2
+v0.0.4  - Using optparse for the Python wrapper script API
+        - Made MAF and BAM outputs optional
 ======= ======================================================================
 
 
--- a/tools/mira4/mira4.py	Wed May 21 06:56:06 2014 -0400
+++ b/tools/mira4/mira4.py	Tue Jun 10 10:11:58 2014 -0400
@@ -7,11 +7,12 @@
 import shutil
 import time
 import tempfile
+from optparse import OptionParser
 
 #Do we need any PYTHONPATH magic?
 from mira4_make_bam import make_bam
 
-WRAPPER_VER = "0.0.1" #Keep in sync with the XML file
+WRAPPER_VER = "0.0.4" #Keep in sync with the XML file
 
 def stop_err(msg, err=1):
     sys.stderr.write(msg+"\n")
@@ -34,6 +35,35 @@
     del child
     return ver.split("\n", 1)[0].strip()
 
+#Parse Command Line
+usage = """Galaxy MIRA4 wrapper script v%s - use as follows:
+
+$ python mira4.py ...
+
+This will run the MIRA binary and collect its output files as directed.
+""" % WRAPPER_VER
+parser = OptionParser(usage=usage)
+parser.add_option("-m", "--manifest", dest="manifest",
+                  default=None, metavar="FILE",
+                  help="MIRA manifest filename")
+parser.add_option("--maf", dest="maf",
+                  default="-", metavar="FILE",
+                  help="MIRA MAF output filename")
+parser.add_option("--bam", dest="bam",
+                  default="-", metavar="FILE",
+                  help="Unpadded BAM output filename")
+parser.add_option("--fasta", dest="fasta",
+                  default="-", metavar="FILE",
+                  help="Unpadded FASTA output filename")
+parser.add_option("--log", dest="log",
+                  default="-", metavar="FILE",
+                  help="MIRA logging output filename")
+options, args = parser.parse_args()
+manifest = options.manifest
+out_maf = options.maf
+out_bam = options.bam
+out_fasta = options.fasta
+out_log = options.log
 
 try:
     mira_path = os.environ["MIRA4"]
@@ -60,6 +90,11 @@
         print "WARNING: miraconvert %s" % mira_convert_ver
     sys.exit(0)
 
+if not manifest:
+    stop_err("Manifest is required")
+elif not os.path.isfile(manifest):
+    stop_err("Missing input MIRA manifest file: %r" % manifest)
+
 
 try:
     threads = int(os.environ.get("GALAXY_SLOTS", "1"))
@@ -143,6 +178,8 @@
                      (old_fasta, out_fasta)]:
         if not os.path.isfile(old):
             missing = True
+        elif not new or new == "-":
+            handle.write("Ignoring %s\n" % old)
         else:
             handle.write("Capturing %s\n" % old)
             shutil.move(old, new)
@@ -154,9 +191,10 @@
 
     #For mapping mode, probably most people would expect a BAM file
     #using the reference FASTA file...
-    msg = make_bam(mira_convert, out_maf, ref_fasta, out_bam, handle)
-    if msg:
-        stop_err(msg)
+    if out_bam and out_bam != "-":
+        msg = make_bam(mira_convert, out_maf, ref_fasta, out_bam, handle)
+        if msg:
+            stop_err(msg)
 
 def clean_up(temp, name):
     folder = "%s/%s_assembly" % (temp, name)
@@ -167,14 +205,12 @@
 #Currently Galaxy puts us somewhere safe like:
 #/opt/galaxy-dist/database/job_working_directory/846/
 temp = "."
-#name, out_fasta, out_qual, out_ace, out_caf, out_wig, out_log = sys.argv[1:8]
+
 name = "MIRA"
-manifest, out_maf, out_bam, out_fasta, out_log = sys.argv[1:]
 
 override_temp(manifest)
 
 start_time = time.time()
-#cmd_list =sys.argv[8:]
 cmd_list = [mira_binary, "-t", str(threads), manifest]
 cmd = " ".join(cmd_list)
 
@@ -192,7 +228,10 @@
 #print os.path.abspath(".")
 #print cmd
 
-handle = open(out_log, "w")
+if out_log and out_log != "-":
+    handle = open(out_log, "w")
+else:
+    handle = open(os.devnull, "w")
 handle.write("======================== MIRA manifest (instructions) ========================\n")
 m = open(manifest, "rU")
 for line in m:
--- a/tools/mira4/mira4_de_novo.xml	Wed May 21 06:56:06 2014 -0400
+++ b/tools/mira4/mira4_de_novo.xml	Tue Jun 10 10:11:58 2014 -0400
@@ -1,4 +1,4 @@
-<tool id="mira_4_0_de_novo" name="MIRA v4.0 de novo assember" version="0.0.3">
+<tool id="mira_4_0_de_novo" name="MIRA v4.0 de novo assember" version="0.0.4">
     <description>Takes Sanger, Roche 454, Solexa/Illumina, Ion Torrent and PacBio reads</description>
     <requirements>
         <requirement type="binary">mira</requirement>
@@ -8,8 +8,16 @@
         <requirement type="package" version="0.1.19">samtools</requirement>
     </requirements>
     <version_command interpreter="python">mira4.py --version</version_command>
-    <command interpreter="python">
-mira4.py "$manifest" "$out_maf" "$out_bam" "$out_fasta" "$out_log"
+    <command interpreter="python">mira4.py
+--manifest "$manifest"
+#if str($maf_wanted)=="true":
+--maf "$out_maf"
+#end if
+#if str($bam_wanted)=="true":
+--bam "$out_bam"
+#end if
+--fasta "$out_fasta"
+--log "$out_log"
     </command>
     <stdio>
         <!-- Assume anything other than zero is an error -->
@@ -67,12 +75,18 @@
             <param name="filenames" type="data" format="fastq,mira" multiple="true" required="true" label="Read file(s)"
                   help="Multiple files allowed, for example paired reads can be given as two files (MIRA looks at read names to identify pairs)." />
         </repeat>
+        <param name="maf_wanted" type="boolean" label="Output assembly in MIRA's own format?" checked="False" />
+        <param name="bam_wanted" type="boolean" label="Convert assembly into BAM format?" checked="True" />
     </inputs>
     <code file="mira4_validator.py" />
     <outputs>
         <data name="out_fasta" format="fasta" label="MIRA de novo contigs (FASTA)" />
-        <data name="out_bam" format="bam" label="MIRA de novo assembly (BAM)" />
-        <data name="out_maf" format="mira" label="MIRA de novo assembly" />
+        <data name="out_bam" format="bam" label="MIRA de novo assembly (BAM)">
+            <filter>bam_wanted is True</filter>
+        </data>
+        <data name="out_maf" format="mira" label="MIRA de novo assembly">
+            <filter>maf_wanted is True</filter>
+        </data>
         <!-- TODO?
         <data name="out_contigstats" format="tabular" label="MIRA contig stats" />
         -->
@@ -162,6 +176,8 @@
             <param name="technology" value="sanger" />
             <param name="type" value="none" />
             <param name="filenames" value="U13small_m.fastq" ftype="fastqsanger" />
+            <param name="maf_wanted" value="true"/>
+            <param name="bam_wanted" value="true"/>
             <output name="out_fasta" file="U13small_m.mira4_de_novo.fasta" ftype="fasta" />
             <output name="out_bam" file="empty_file.dat" compare="contains" />
             <output name="out_maf" file="empty_file.dat" compare="contains" />
@@ -176,6 +192,8 @@
             <param name="job_quality" value="accurate" />
             <param name="type" value="none" />
             <param name="filenames" value="ecoli.fastq" ftype="fastqsanger" />
+            <param name="maf_wanted" value="true"/>
+            <param name="bam_wanted" value="true"/>
             <output name="out_fasta" file="ecoli.mira4_de_novo.fasta" ftype="fasta" />
             <output name="out_bam" file="empty_file.dat" compare="contains" />
             <output name="out_maf" file="empty_file.dat" compare="contains" />
--- a/tools/mira4/mira4_mapping.xml	Wed May 21 06:56:06 2014 -0400
+++ b/tools/mira4/mira4_mapping.xml	Tue Jun 10 10:11:58 2014 -0400
@@ -1,4 +1,4 @@
-<tool id="mira_4_0_mapping" name="MIRA v4.0 mapping" version="0.0.3">
+<tool id="mira_4_0_mapping" name="MIRA v4.0 mapping" version="0.0.4">
     <description>Maps Sanger, Roche 454, Solexa/Illumina, Ion Torrent and PacBio reads</description>
     <requirements>
         <requirement type="binary">mira</requirement>
@@ -8,8 +8,16 @@
         <requirement type="package" version="0.1.19">samtools</requirement>
     </requirements>
     <version_command interpreter="python">mira4.py --version</version_command>
-    <command interpreter="python">
-mira4.py "$manifest" "$out_maf" "$out_bam" "$out_fasta" "$out_log"
+    <command interpreter="python">mira4.py
+--manifest "$manifest"
+#if str($maf_wanted) == "true":
+--maf "$out_maf"
+#end if
+#if str($bam_wanted) == "true":
+--bam "$out_bam"
+#end if
+--fasta "$out_fasta"
+--log "$out_log"
     </command>
     <stdio>
         <!-- Assume anything other than zero is an error -->
@@ -69,11 +77,17 @@
             <param name="filenames" type="data" format="fastq,mira" multiple="true" required="true" label="Read file(s)"
                    help="Multiple files allowed, for example paired reads can be given as two files (MIRA looks at read names to identify pairs)." />
         </repeat>
+        <param name="maf_wanted" type="boolean" label="Output mapping in MIRA's own format?" checked="False" />
+        <param name="bam_wanted" type="boolean" label="Convert mapping into BAM format?" checked="True" />
     </inputs>
     <outputs>
         <data name="out_fasta" format="fasta" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping contigs (FASTA)" />
-        <data name="out_bam" format="bam" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping assembly (BAM)" />
-        <data name="out_maf" format="mira" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping assembly" />
+        <data name="out_bam" format="bam" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping assembly (BAM)">
+            <filter>bam_wanted is True</filter>
+        </data>
+        <data name="out_maf" format="mira" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping assembly">
+            <filter>maf_wanted is True</filter>
+        </data>
         <data name="out_log" format="txt" label="MIRA #if str($strain_setup)=='same' then 'same strain' else 'reference' # mapping log" />
     </outputs>
     <configfiles>
@@ -168,6 +182,8 @@
             <param name="strain_setup" value="default" />
             <param name="type" value="none" />
             <param name="filenames" value="tvc_mini.fastq" ftype="fastqsanger" />
+            <param name="maf_wanted" value="true"/>
+            <param name="bam_wanted" value="true"/>
             <output name="out_fasta" file="tvc_map_ref_strain.fasta" ftype="fasta" />
             <output name="out_bam" file="empty_file.dat" compare="contains" />
             <output name="out_maf" file="empty_file.dat" compare="contains" />
@@ -180,6 +196,8 @@
             <param name="strain_setup" value="same" />
             <param name="type" value="none" />
             <param name="filenames" value="tvc_mini.fastq" ftype="fastqsanger" />
+            <param name="maf_wanted" value="true"/>
+            <param name="bam_wanted" value="true"/>
             <output name="out_fasta" file="tvc_map_same_strain.fasta" ftype="fasta" />
             <output name="out_bam" file="empty_file.dat" compare="contains" />
             <output name="out_maf" file="empty_file.dat" compare="contains" />
--- a/tools/mira4/repository_dependencies.xml	Wed May 21 06:56:06 2014 -0400
+++ b/tools/mira4/repository_dependencies.xml	Tue Jun 10 10:11:58 2014 -0400
@@ -1,4 +1,4 @@
 <?xml version="1.0"?>
 <repositories description="This requires the MIRA datatype definitions (e.g. the MIRA Assembly Format).">
-    <repository changeset_revision="29ff2a2b6eaa" name="mira_datatypes" owner="peterjc" toolshed="http://testtoolshed.g2.bx.psu.edu" />
+    <repository changeset_revision="29ff2a2b6eaa" name="mira_datatypes" owner="peterjc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
 </repositories>
--- a/tools/mira4/tool_dependencies.xml	Wed May 21 06:56:06 2014 -0400
+++ b/tools/mira4/tool_dependencies.xml	Tue Jun 10 10:11:58 2014 -0400
@@ -1,7 +1,7 @@
 <?xml version="1.0"?>
 <tool_dependency>
     <package name="samtools" version="0.1.19">
-        <repository changeset_revision="40250a414486" name="package_samtools_0_1_19" owner="iuc" toolshed="http://testtoolshed.g2.bx.psu.edu" />
+        <repository changeset_revision="40250a414486" name="package_samtools_0_1_19" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
     </package>
     <package name="MIRA" version="4.0">
         <install version="1.0">