Previous changeset 5:f4b4c1712e39 (2011-11-08) Next changeset 7:561503a442f0 (2011-11-08) |
Commit message:
refactor and update README |
added:
README lib/galaxy/datatypes/gmap.py tool-data/gmap_indices.loc.sample |
removed:
gmap/README gmap/gmap_indices.loc.sample gmap/lib/galaxy/datatypes/gmap.py |
b |
diff -r f4b4c1712e39 -r 3be0e0a858fe README --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/README Tue Nov 08 13:22:34 2011 -0600 |
b |
@@ -0,0 +1,71 @@ +GMAP applications and citation info are available from: http://research-pub.gene.com/gmap/ + + + Installation instructions are in the README file in the download, + and online: http://research-pub.gene.com/gmap/src/README + + These tools were consistent with gmap version: 2011-10-16 + + +GMAP and GSNAP use added datatypes: + + add datatype definition file: lib/galaxy/datatypes/gmap.py + + add the following import line to: lib/galaxy/datatypes/registry.py + import gmap # added for gmap tools + + add to datatypes_conf.xml + <!-- Start GMAP Datatypes --> + <datatype extension="gmapdb" type="galaxy.datatypes.gmap:GmapDB" display_in_upload="False"/> + <datatype extension="gmapsnpindex" type="galaxy.datatypes.gmap:GmapSnpIndex" display_in_upload="False"/> + <datatype extension="iit" type="galaxy.datatypes.gmap:IntervalIndexTree" display_in_upload="True"/> + <datatype extension="splicesites.iit" type="galaxy.datatypes.gmap:SpliceSitesIntervalIndexTree" display_in_upload="True"/> + <datatype extension="introns.iit" type="galaxy.datatypes.gmap:IntronsIntervalIndexTree" display_in_upload="True"/> + <datatype extension="snps.iit" type="galaxy.datatypes.gmap:SNPsIntervalIndexTree" display_in_upload="True"/> + <datatype extension="tally.iit" type="galaxy.datatypes.gmap:TallyIntervalIndexTree" display_in_upload="True"/> + <datatype extension="gmap_annotation" type="galaxy.datatypes.gmap:IntervalAnnotation" display_in_upload="False"/> + <datatype extension="gmap_splicesites" type="galaxy.datatypes.gmap:SpliceSiteAnnotation" display_in_upload="True"/> + <datatype extension="gmap_introns" type="galaxy.datatypes.gmap:IntronAnnotation" display_in_upload="True"/> + <datatype extension="gmap_snps" type="galaxy.datatypes.gmap:SNPAnnotation" display_in_upload="True"/> + <datatype extension="gsnap_tally" type="galaxy.datatypes.gmap:TallyAnnotation" display_in_upload="True"/> + <datatype extension="gsnap" type="galaxy.datatypes.gmap:GsnapResult" display_in_upload="True"/> + <!-- End GMAP Datatypes --> + +Tools: + GMAP_Build - create a GmapDB set of index files for a reference sequence and optional set of annotations + GMAP - map sequences to a reference sequence GmapDB index + GSNAP - align sequences to a reference and detect splicing + + Add to tool_conf.xml ( probably in the "NGS: Mapping" section ) + <tool file="gmap/gmap.xml" /> + <tool file="gmap/gsnap.xml" /> + <tool file="gmap/gmap_build.xml" /> + <tool file="gmap/snpindex.xml" /> + <tool file="gmap/iit_store.xml" /> + +Admin built cached gmapdb indexes defined in tool-data/gmap_indices.loc + + +TODO: + + + Add classes to gmap.py + CmetIndex - an index created by cmetindex + AtoiIndex - an index created by atoiindex + + Add tally creation + gsnap default output -> gsnap_tally -> iit_store + + Add goby support + Should add separate tools and datatypes for goby + GSNAP goby output relies on goby input, might be better to have a separate gsnap tool for goby + + Possibly add Tools: + get_genome - retrieves from a gmapdb + cmetindex - create methylcytosine index + atoiindex - create A-to-I RNA editing index + + + + + |
b |
diff -r f4b4c1712e39 -r 3be0e0a858fe gmap/README --- a/gmap/README Tue Nov 08 13:07:25 2011 -0600 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
@@ -1,60 +0,0 @@ -GMAP applications and citation info are available from: http://research-pub.gene.com/gmap/ - - - Installation instructions are in the README file in the download, - and online: http://research-pub.gene.com/gmap/src/README - - These galaxy tools assume gmap is configured and built with goby support. - These tools were consistent with gmap version: 2011-10-07 - - -GMAP and GSNAP use added datatypes: - - add datatype definition file: lib/galaxy/datatypes/gmap.py - - add the following import line to: lib/galaxy/datatypes/registry.py - import gmap # added for gmap tools - - add to datatypes_conf.xml - <!-- Start GMAP Datatypes --> - <datatype extension="gmapdb" type="galaxy.datatypes.gmap:GmapDB" display_in_upload="False"/> - <datatype extension="gmapsnpindex" type="galaxy.datatypes.gmap:GmapSnpIndex" display_in_upload="False"/> - <datatype extension="iit" type="galaxy.datatypes.gmap:IntervalIndexTree" display_in_upload="True"/> - <datatype extension="splicesites.iit" type="galaxy.datatypes.gmap:SpliceSitesIntervalIndexTree" display_in_upload="True"/> - <datatype extension="introns.iit" type="galaxy.datatypes.gmap:IntronsIntervalIndexTree" display_in_upload="True"/> - <datatype extension="snps.iit" type="galaxy.datatypes.gmap:SNPsIntervalIndexTree" display_in_upload="True"/> - <datatype extension="gmap_annotation" type="galaxy.datatypes.gmap:IntervalAnnotation" display_in_upload="False"/> - <datatype extension="gmap_splicesites" type="galaxy.datatypes.gmap:SpliceSiteAnnotation" display_in_upload="True"/> - <datatype extension="gmap_introns" type="galaxy.datatypes.gmap:IntronAnnotation" display_in_upload="True"/> - <datatype extension="gmap_snps" type="galaxy.datatypes.gmap:SNPAnnotation" display_in_upload="True"/> - <!-- End GMAP tools --> - -Tools: - GMAP_Build - create a GmapDB set of index files for a reference sequence and optional set of annotations - GMAP - map sequences to a reference sequence GmapDB index - GSNAP - align sequences to a reference and detect splicing - - Add to tool_conf.xml ( probably in the "NGS: Mapping" section ) - <tool file="gmap/gmap.xml" /> - <tool file="gmap/gsnap.xml" /> - <tool file="gmap/gmap_build.xml" /> - <tool file="gmap/snpindex.xml" /> - <tool file="gmap/iit_store.xml" /> - -Admin built cached gmapdb indexes defined in tool-data/gmap_indices.loc - - -TODO: - Add classes to gmap.py - CmetIndex - an index created by cmetindex - AtoiIndex - an index created by atoiindex - - Possibly add Tools: - get_genome - retrieves from a gmapdb - cmetindex - create methylcytosine index - atoiindex - create A-to-I RNA editing index - - - - - |
b |
diff -r f4b4c1712e39 -r 3be0e0a858fe gmap/gmap_indices.loc.sample --- a/gmap/gmap_indices.loc.sample Tue Nov 08 13:07:25 2011 -0600 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
b |
@@ -1,10 +0,0 @@ -#This is a sample file distributed with Galaxy that enables tools -#to use a directory of GMAPDB indexed sequences data files. You will need -#to create these data files using gmap_build and then create a gmap_indices.loc file -#similar to this one (store it in this directory) that points to -#the directories in which those files are stored. The gmap_indices.loc -#file has this format (white space characters are TAB characters): -# -#<unique_build_id> <dbkey> <display_name> <kmers> <map,map> <snp,snp> <file_base_path> -#hg18 hg18 hg18 (cmet atoi) 12,13,14,15 splicesites,introns snps /depot/data2/galaxy/gmap/hg18 -#hg19 hg19 hg19 (cmet atoi) 12,13,14,15 splicesites,introns,snps snps,dbsnp /depot/data2/galaxy/gmap/hg19 |
b |
diff -r f4b4c1712e39 -r 3be0e0a858fe gmap/lib/galaxy/datatypes/gmap.py --- a/gmap/lib/galaxy/datatypes/gmap.py Tue Nov 08 13:07:25 2011 -0600 +++ /dev/null Thu Jan 01 00:00:00 1970 +0000 |
[ |
b'@@ -1,472 +0,0 @@\n-"""\n-GMAP indexes\n-"""\n-import logging\n-import os,os.path,re\n-import data\n-from data import Text\n-from galaxy import util\n-from metadata import MetadataElement\n-\n-log = logging.getLogger(__name__)\n-\n-class GmapDB( Text ):\n- """\n- A GMAP DB for indexes\n- """\n- MetadataElement( name="db_name", desc="The db name for this index set", default=\'unknown\', set_in_upload=True, readonly=True )\n- MetadataElement( name="basesize", default="12", desc="The basesize for offsetscomp", visible=True, readonly=True )\n- MetadataElement( name="kmers", default=[\'\'], desc="The kmer sizes for indexes", visible=True, no_value=[\'\'], readonly=True )\n- MetadataElement( name="map_dir", desc="The maps directory", default=\'unknown\', set_in_upload=True, readonly=True )\n- MetadataElement( name="maps", default=[\'\'], desc="The names of maps stored for this gmap gmapdb", visible=True, no_value=[\'\'], readonly=True )\n- MetadataElement( name="snps", default=[\'\'], desc="The names of SNP indexes stored for this gmapdb", visible=True, no_value=[\'\'], readonly=True )\n- MetadataElement( name="cmet", default=False, desc="Has a cmet index", visible=True, readonly=True )\n- MetadataElement( name="atoi", default=False, desc="Has a atoi index", visible=True, readonly=True )\n- \n- file_ext = \'gmapdb\'\n- is_binary = True\n- composite_type = \'auto_primary_file\'\n- allow_datatype_change = False\n-\n- def generate_primary_file( self, dataset = None ):\n- """ \n- This is called only at upload to write the html file\n- cannot rename the datasets here - they come with the default unfortunately\n- """\n- return \'<html><head></head><body>AutoGenerated Primary File for Composite Dataset</body></html>\'\n- \n- def regenerate_primary_file(self,dataset):\n- """\n- cannot do this until we are setting metadata \n- """\n- bn = dataset.metadata.db_name\n- log.info( "GmapDB regenerate_primary_file %s" % (bn))\n- rval = [\'<html><head><title>GMAPDB %s</title></head><p/><H3>GMAPDB %s</H3><p/>cmet %s<br>atoi %s<H4>Maps:</H4><ul>\' % (bn,bn,dataset.metadata.cmet,dataset.metadata.atoi)]\n- for i,name in enumerate(dataset.metadata.maps):\n- rval.append( \'<li>%s\' % name)\n- rval.append( \'</ul></html>\' )\n- f = file(dataset.file_name,\'w\')\n- f.write("\\n".join( rval ))\n- f.write(\'\\n\')\n- f.close()\n-\n- def set_peek( self, dataset, is_multi_byte=False ):\n- log.info( "GmapDB set_peek %s" % (dataset))\n- if not dataset.dataset.purged:\n- dataset.peek = "GMAPDB index %s\\n cmet %s\\n atoi %s\\n maps %s" % ( dataset.metadata.db_name,dataset.metadata.cmet,dataset.metadata.atoi,dataset.metadata.maps )\n- dataset.blurb = "GMAPDB %s" % ( dataset.metadata.db_name )\n- else:\n- dataset.peek = \'file does not exist\'\n- dataset.blurb = \'file purged from disk\'\n- def display_peek( self, dataset ):\n- try:\n- return dataset.peek\n- except:\n- return "GMAP index file"\n-\n- def sniff( self, filename ):\n- return False\n- def set_meta( self, dataset, overwrite = True, **kwd ):\n- """\n- Expecting:\n- extra_files_path/<db_name>/db_name>.ref<basesize><kmer>3<index>\n- extra_files_path/db_name/db_name.ref1[2345]1[2345]3offsetscomp\n- extra_files_path/db_name/db_name.ref1[2345]1[2345]3positions\n- extra_files_path/db_name/db_name.ref1[2345]1[2345]3gammaptrs\n- index maps: \n- extra_files_path/db_name/db_name.maps/*.iit\n- """\n- log.info( "GmapDB set_meta %s %s" % (dataset,dataset.extra_files_path))\n- pat = \'(.*)\\.((ref)|(met)[atgc][atgc]|(a2i)[atgc][atgc])((\\d\\d)(\\d\\d))?3positions(\\.(.+))?\'\n- efp = dataset.extra_files_path\n- flist = os.listdir(efp)\n- for i,fname in enumerate(flist):\n- log.info( "GmapDB set_meta %s %s" % (i,fname))\n- fpath = '..b' == None: # Failed to match \n- return False\n- finally:\n- fh.close()\n- return False\n-\n-class SNPAnnotation(IntervalAnnotation):\n- file_ext = \'gmap_snps\'\n- """\n- Example:\n- >rs62211261 21:14379270 CG\n- >rs62211262 21:14379281 AT\n- >rs62211263 21:14379298 WN\n- Each line must start with a ">" character, then be followed by an\n- identifier (which may have duplicates). Then there should be the\n- chromosomal coordinate of the SNP. (Coordinates are all 1-based, so\n- the first character of a chromosome is number 1.) Finally, there\n- should be the two possible alleles. (Previous versions required that\n- these be in alphabetical order: "AC", "AG", "AT", "CG", "CT", or "GT",\n- but that is no longer a requirement.) These alleles must correspond\n- to the possible nucleotides on the plus strand of the genome. If the\n- one of these two letters does not match the allele in the reference\n- sequence, that SNP will be ignored in subsequent processing as a\n- probable error.\n- \n- GSNAP also supports the idea of a wildcard SNP. A wildcard SNP allows\n- all nucleotides to match at that position, not just a given reference\n- and alternate allele. It is essentially as if an "N" were recorded at\n- that genomic location, although the index files still keep track of\n- the reference allele. To indicate that a position has a wildcard SNP,\n- you can indicate the genotype as "WN", where "W" is the reference\n- allele. Another indication of a wildcard SNP is to provide two\n- separate lines at that position with the genotypes "WX" and "WY",\n- where "W" is the reference allele and "X" and "Y" are two different\n- alternate alleles.\n- """\n- def sniff( self, filename ):\n- """\n- Determines whether the file is a gmap SNP annotation file\n- """\n- try:\n- pat = \'>(\\S+)\\s((\\S+):(\\d+)\\s([TACGW][TACGN])$\' #>label chr:position ATCG \n- fh = open( filename )\n- count = 0\n- while True and count < 10:\n- line = fh.readline()\n- if not line:\n- break #EOF\n- line = line.strip()\n- if line: #first non-empty line\n- count += 1\n- if re.match(pat,line) == None: # Failed to match \n- return False\n- finally:\n- fh.close()\n- return False\n-\n-\n-class TallyAnnotation(IntervalAnnotation):\n- file_ext = \'gsnap_tally\'\n- """\n- Output produced by gsnap_tally\n- Example:\n- >144 chr20:57268791..57268935\n- G0\n- A1(1@7|1Q-3)\n- A2(1@36,1@1|1Q2,1Q-8)\n- C2 0.889,0.912,0.889,0.889,0.933,0.912,0.912,0.889,0.889,0.889 -2.66,-2.89,-2.66,-2.66,-3.16,-2.89,-2.89,-2.66,-2.66,-2.66\n- C1 T1 0.888,0.9,0.888,0.9,0.913,0.9,0.911,0.888,0.9,0.913 -2.66,-2.78,-2.66,-2.78,-2.91,-2.78,-2.89,-2.66,-2.78,-2.91\n- """\n- def sniff( self, filename ): # TODO\n- """\n- Determines whether the file is a gmap splice site annotation file\n- """\n- try:\n- pat = \'^>(\\d+)\\s((\\S+):(\\d+)\\.\\.(\\d+))$\' #>total chr:position..position\n- pat2 = \'^[GATCN]\\d.*$\' #BaseCountDeatails\n- fh = open( filename )\n- count = 0\n- while True and count < 10:\n- line = fh.readline()\n- if not line:\n- break #EOF\n- line = line.strip()\n- if line: #first non-empty line\n- count += 1\n- if re.match(pat,line) == None and re.match(pat2,line) == None: # Failed to match \n- return False\n- finally:\n- fh.close()\n- return False\n-\n-class GsnapResult( Text ):\n- """\n- The default output format for gsnap. Can be used as input for gsnap_tally.\n- """\n- file_ext = \'gsnap\'\n-\n-\n' |
b |
diff -r f4b4c1712e39 -r 3be0e0a858fe lib/galaxy/datatypes/gmap.py --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/lib/galaxy/datatypes/gmap.py Tue Nov 08 13:22:34 2011 -0600 |
[ |
b'@@ -0,0 +1,472 @@\n+"""\n+GMAP indexes\n+"""\n+import logging\n+import os,os.path,re\n+import data\n+from data import Text\n+from galaxy import util\n+from metadata import MetadataElement\n+\n+log = logging.getLogger(__name__)\n+\n+class GmapDB( Text ):\n+ """\n+ A GMAP DB for indexes\n+ """\n+ MetadataElement( name="db_name", desc="The db name for this index set", default=\'unknown\', set_in_upload=True, readonly=True )\n+ MetadataElement( name="basesize", default="12", desc="The basesize for offsetscomp", visible=True, readonly=True )\n+ MetadataElement( name="kmers", default=[\'\'], desc="The kmer sizes for indexes", visible=True, no_value=[\'\'], readonly=True )\n+ MetadataElement( name="map_dir", desc="The maps directory", default=\'unknown\', set_in_upload=True, readonly=True )\n+ MetadataElement( name="maps", default=[\'\'], desc="The names of maps stored for this gmap gmapdb", visible=True, no_value=[\'\'], readonly=True )\n+ MetadataElement( name="snps", default=[\'\'], desc="The names of SNP indexes stored for this gmapdb", visible=True, no_value=[\'\'], readonly=True )\n+ MetadataElement( name="cmet", default=False, desc="Has a cmet index", visible=True, readonly=True )\n+ MetadataElement( name="atoi", default=False, desc="Has a atoi index", visible=True, readonly=True )\n+ \n+ file_ext = \'gmapdb\'\n+ is_binary = True\n+ composite_type = \'auto_primary_file\'\n+ allow_datatype_change = False\n+\n+ def generate_primary_file( self, dataset = None ):\n+ """ \n+ This is called only at upload to write the html file\n+ cannot rename the datasets here - they come with the default unfortunately\n+ """\n+ return \'<html><head></head><body>AutoGenerated Primary File for Composite Dataset</body></html>\'\n+ \n+ def regenerate_primary_file(self,dataset):\n+ """\n+ cannot do this until we are setting metadata \n+ """\n+ bn = dataset.metadata.db_name\n+ log.info( "GmapDB regenerate_primary_file %s" % (bn))\n+ rval = [\'<html><head><title>GMAPDB %s</title></head><p/><H3>GMAPDB %s</H3><p/>cmet %s<br>atoi %s<H4>Maps:</H4><ul>\' % (bn,bn,dataset.metadata.cmet,dataset.metadata.atoi)]\n+ for i,name in enumerate(dataset.metadata.maps):\n+ rval.append( \'<li>%s\' % name)\n+ rval.append( \'</ul></html>\' )\n+ f = file(dataset.file_name,\'w\')\n+ f.write("\\n".join( rval ))\n+ f.write(\'\\n\')\n+ f.close()\n+\n+ def set_peek( self, dataset, is_multi_byte=False ):\n+ log.info( "GmapDB set_peek %s" % (dataset))\n+ if not dataset.dataset.purged:\n+ dataset.peek = "GMAPDB index %s\\n cmet %s\\n atoi %s\\n maps %s" % ( dataset.metadata.db_name,dataset.metadata.cmet,dataset.metadata.atoi,dataset.metadata.maps )\n+ dataset.blurb = "GMAPDB %s" % ( dataset.metadata.db_name )\n+ else:\n+ dataset.peek = \'file does not exist\'\n+ dataset.blurb = \'file purged from disk\'\n+ def display_peek( self, dataset ):\n+ try:\n+ return dataset.peek\n+ except:\n+ return "GMAP index file"\n+\n+ def sniff( self, filename ):\n+ return False\n+ def set_meta( self, dataset, overwrite = True, **kwd ):\n+ """\n+ Expecting:\n+ extra_files_path/<db_name>/db_name>.ref<basesize><kmer>3<index>\n+ extra_files_path/db_name/db_name.ref1[2345]1[2345]3offsetscomp\n+ extra_files_path/db_name/db_name.ref1[2345]1[2345]3positions\n+ extra_files_path/db_name/db_name.ref1[2345]1[2345]3gammaptrs\n+ index maps: \n+ extra_files_path/db_name/db_name.maps/*.iit\n+ """\n+ log.info( "GmapDB set_meta %s %s" % (dataset,dataset.extra_files_path))\n+ pat = \'(.*)\\.((ref)|(met)[atgc][atgc]|(a2i)[atgc][atgc])((\\d\\d)(\\d\\d))?3positions(\\.(.+))?\'\n+ efp = dataset.extra_files_path\n+ flist = os.listdir(efp)\n+ for i,fname in enumerate(flist):\n+ log.info( "GmapDB set_meta %s %s" % (i,fname))\n+ fpath = '..b' == None: # Failed to match \n+ return False\n+ finally:\n+ fh.close()\n+ return False\n+\n+class SNPAnnotation(IntervalAnnotation):\n+ file_ext = \'gmap_snps\'\n+ """\n+ Example:\n+ >rs62211261 21:14379270 CG\n+ >rs62211262 21:14379281 AT\n+ >rs62211263 21:14379298 WN\n+ Each line must start with a ">" character, then be followed by an\n+ identifier (which may have duplicates). Then there should be the\n+ chromosomal coordinate of the SNP. (Coordinates are all 1-based, so\n+ the first character of a chromosome is number 1.) Finally, there\n+ should be the two possible alleles. (Previous versions required that\n+ these be in alphabetical order: "AC", "AG", "AT", "CG", "CT", or "GT",\n+ but that is no longer a requirement.) These alleles must correspond\n+ to the possible nucleotides on the plus strand of the genome. If the\n+ one of these two letters does not match the allele in the reference\n+ sequence, that SNP will be ignored in subsequent processing as a\n+ probable error.\n+ \n+ GSNAP also supports the idea of a wildcard SNP. A wildcard SNP allows\n+ all nucleotides to match at that position, not just a given reference\n+ and alternate allele. It is essentially as if an "N" were recorded at\n+ that genomic location, although the index files still keep track of\n+ the reference allele. To indicate that a position has a wildcard SNP,\n+ you can indicate the genotype as "WN", where "W" is the reference\n+ allele. Another indication of a wildcard SNP is to provide two\n+ separate lines at that position with the genotypes "WX" and "WY",\n+ where "W" is the reference allele and "X" and "Y" are two different\n+ alternate alleles.\n+ """\n+ def sniff( self, filename ):\n+ """\n+ Determines whether the file is a gmap SNP annotation file\n+ """\n+ try:\n+ pat = \'>(\\S+)\\s((\\S+):(\\d+)\\s([TACGW][TACGN])$\' #>label chr:position ATCG \n+ fh = open( filename )\n+ count = 0\n+ while True and count < 10:\n+ line = fh.readline()\n+ if not line:\n+ break #EOF\n+ line = line.strip()\n+ if line: #first non-empty line\n+ count += 1\n+ if re.match(pat,line) == None: # Failed to match \n+ return False\n+ finally:\n+ fh.close()\n+ return False\n+\n+\n+class TallyAnnotation(IntervalAnnotation):\n+ file_ext = \'gsnap_tally\'\n+ """\n+ Output produced by gsnap_tally\n+ Example:\n+ >144 chr20:57268791..57268935\n+ G0\n+ A1(1@7|1Q-3)\n+ A2(1@36,1@1|1Q2,1Q-8)\n+ C2 0.889,0.912,0.889,0.889,0.933,0.912,0.912,0.889,0.889,0.889 -2.66,-2.89,-2.66,-2.66,-3.16,-2.89,-2.89,-2.66,-2.66,-2.66\n+ C1 T1 0.888,0.9,0.888,0.9,0.913,0.9,0.911,0.888,0.9,0.913 -2.66,-2.78,-2.66,-2.78,-2.91,-2.78,-2.89,-2.66,-2.78,-2.91\n+ """\n+ def sniff( self, filename ): # TODO\n+ """\n+ Determines whether the file is a gmap splice site annotation file\n+ """\n+ try:\n+ pat = \'^>(\\d+)\\s((\\S+):(\\d+)\\.\\.(\\d+))$\' #>total chr:position..position\n+ pat2 = \'^[GATCN]\\d.*$\' #BaseCountDeatails\n+ fh = open( filename )\n+ count = 0\n+ while True and count < 10:\n+ line = fh.readline()\n+ if not line:\n+ break #EOF\n+ line = line.strip()\n+ if line: #first non-empty line\n+ count += 1\n+ if re.match(pat,line) == None and re.match(pat2,line) == None: # Failed to match \n+ return False\n+ finally:\n+ fh.close()\n+ return False\n+\n+class GsnapResult( Text ):\n+ """\n+ The default output format for gsnap. Can be used as input for gsnap_tally.\n+ """\n+ file_ext = \'gsnap\'\n+\n+\n' |
b |
diff -r f4b4c1712e39 -r 3be0e0a858fe tool-data/gmap_indices.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/gmap_indices.loc.sample Tue Nov 08 13:22:34 2011 -0600 |
b |
@@ -0,0 +1,10 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of GMAPDB indexed sequences data files. You will need +#to create these data files using gmap_build and then create a gmap_indices.loc file +#similar to this one (store it in this directory) that points to +#the directories in which those files are stored. The gmap_indices.loc +#file has this format (white space characters are TAB characters): +# +#<unique_build_id> <dbkey> <display_name> <kmers> <map,map> <snp,snp> <file_base_path> +#hg18 hg18 hg18 (cmet atoi) 12,13,14,15 splicesites,introns snps /depot/data2/galaxy/gmap/hg18 +#hg19 hg19 hg19 (cmet atoi) 12,13,14,15 splicesites,introns,snps snps,dbsnp /depot/data2/galaxy/gmap/hg19 |