Mercurial > repos > bgruening > upload_testing

diff homer.py @ 54:675d25a0b9d4

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author bgruening
date Mon, 12 Aug 2013 08:16:21 -0400
parents
children e9cd105a8856
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/homer.py	Mon Aug 12 08:16:21 2013 -0400
@@ -0,0 +1,76 @@
+"""
+HOMER special datatypes
+"""
+
+from galaxy.datatypes.data import get_file_peek
+from galaxy.datatypes.data import Text, Data
+from galaxy.datatypes.metadata import MetadataElement
+from galaxy.datatypes.images import Html
+
+
+class TagDirectory(object):
+    """Base class for HOMER's Tag Directory datatype."""
+
+    file_ext = 'homer_tagdir'
+    composite_type = 'auto_primary_file'
+    allow_datatype_change = False
+
+    def __init__(self, **kwd):
+        Text.__init__( self, **kwd )
+        #self.add_composite_file('tagInfo.txt', description = 'basic configuration information', mimetype = 'text/html') # Contains basic configuration information
+        self.add_composite_file('tagLengthDistribution.txt', description = 'histogram of read lengths used for alignment', mimetype = 'text/html') # File contains a histogram of read lengths used for alignment.
+        self.add_composite_file('tagCountDistribution.txt', description = 'histogram of clonal read depth, showing the number of reads per unique position', mimetype = 'text/html') # File contains a histogram of clonal read depth, showing the number of reads per unique position.
+        self.add_composite_file('tagAutocorrelation.txt', description = 'distribution of distances between adjacent reads in the genome', mimetype = 'text/html') # The autocorrelation routine creates a distribution of distances between adjacent reads in the genome.
+        self.add_composite_file('tagFreq.txt', description = "nucleotide and dinucleotide frequencies as a function of distance from the 5' end of all reads", mimetype = 'text/html', optional=True) # Calculates the nucleotide and dinucleotide frequencies as a function of distance from the 5' end of all reads.
+        self.add_composite_file('tagFreqUniq.txt', description = "nucleotide and dinucleotide frequencies as a function of distance from the 5' end of all reads (counted only once)", mimetype = 'text/html', optional=True) # Same as tagFreq.txt, however individual genomic positions are only counted once.
+        self.add_composite_file('tagGCcontent.txt', description = 'Distribution of fragment GC%-content', mimetype = 'text/html', optional=True) # Distribution of fragment GC%-content.
+        self.add_composite_file('genomeGCcontent.txt', description = 'Distribution of fragment GC%-content at each location in the genome', mimetype = 'text/html', optional=True) # Distribution of fragment GC%-content at each location in the genome.
+
+    def generate_primary_file( self, dataset = None ):
+        rval = ['<html><head><title>HOMER database files</title></head><ul>']
+        for composite_name, composite_file in self.get_composite_files( dataset = dataset ).iteritems():
+            opt_text = ''
+            if composite_file.optional:
+                opt_text = ' (optional)'
+            rval.append( '<li><a href="%s">%s</a>%s' % ( composite_name, composite_name, opt_text ) )
+        rval.append( '</ul></html>' )
+        return "\n".join( rval )
+
+    def display_data(self, trans, data, preview=False, filename=None,
+                     to_ext=None, size=None, offset=None, **kwd):
+        """Apparently an old display method, but still gets called.
+
+        This allows us to format the data shown in the central pane via the "eye" icon.
+        """
+        return "This is a HOMER database."
+
+    def set_peek( self, dataset, is_multi_byte=False ):
+        """Set the peek and blurb text."""
+        if not dataset.dataset.purged:
+            dataset.peek  = "HOMER database (multiple files)"
+            dataset.blurb = "HOMER database (multiple files)"
+        else:
+            dataset.peek = 'file does not exist'
+            dataset.blurb = 'file purged from disk'
+
+    def display_peek( self, dataset ):
+        """Create HTML content, used for displaying peek."""
+        try:
+            return dataset.peek
+        except:
+            return "HOMER database (multiple files)"
+
+    def get_mime(self):
+        """Returns the mime type of the datatype (pretend it is text for peek)"""
+        return 'text/plain'
+
+    def merge(split_files, output_file):
+        """Merge HOMER databases (not implemented)."""
+        raise NotImplementedError("Merging HOMER databases is not supported")
+
+    def split( cls, input_datasets, subdir_generator_function, split_params):
+        """Split a HOMER database (not implemented)."""
+        if split_params is None:
+            return None
+        raise NotImplementedError("Can't split HOMER databases")
+