Mercurial > repos > bgruening > upload_testing

comparison 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
comparison
equal deleted inserted replaced
53:a281b5931ffb 54:675d25a0b9d4
1 """
2 HOMER special datatypes
3 """
4
5 from galaxy.datatypes.data import get_file_peek
6 from galaxy.datatypes.data import Text, Data
7 from galaxy.datatypes.metadata import MetadataElement
8 from galaxy.datatypes.images import Html
9
10
11 class TagDirectory(object):
12 """Base class for HOMER's Tag Directory datatype."""
13
14 file_ext = 'homer_tagdir'
15 composite_type = 'auto_primary_file'
16 allow_datatype_change = False
17
18 def __init__(self, **kwd):
19 Text.__init__( self, **kwd )
20 #self.add_composite_file('tagInfo.txt', description = 'basic configuration information', mimetype = 'text/html') # Contains basic configuration information
21 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.
22 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.
23 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.
24 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.
25 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.
26 self.add_composite_file('tagGCcontent.txt', description = 'Distribution of fragment GC%-content', mimetype = 'text/html', optional=True) # Distribution of fragment GC%-content.
27 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.
28
29 def generate_primary_file( self, dataset = None ):
30 rval = ['<html><head><title>HOMER database files</title></head><ul>']
31 for composite_name, composite_file in self.get_composite_files( dataset = dataset ).iteritems():
32 opt_text = ''
33 if composite_file.optional:
34 opt_text = ' (optional)'
35 rval.append( '<li><a href="%s">%s</a>%s' % ( composite_name, composite_name, opt_text ) )
36 rval.append( '</ul></html>' )
37 return "\n".join( rval )
38
39 def display_data(self, trans, data, preview=False, filename=None,
40 to_ext=None, size=None, offset=None, **kwd):
41 """Apparently an old display method, but still gets called.
42
43 This allows us to format the data shown in the central pane via the "eye" icon.
44 """
45 return "This is a HOMER database."
46
47 def set_peek( self, dataset, is_multi_byte=False ):
48 """Set the peek and blurb text."""
49 if not dataset.dataset.purged:
50 dataset.peek = "HOMER database (multiple files)"
51 dataset.blurb = "HOMER database (multiple files)"
52 else:
53 dataset.peek = 'file does not exist'
54 dataset.blurb = 'file purged from disk'
55
56 def display_peek( self, dataset ):
57 """Create HTML content, used for displaying peek."""
58 try:
59 return dataset.peek
60 except:
61 return "HOMER database (multiple files)"
62
63 def get_mime(self):
64 """Returns the mime type of the datatype (pretend it is text for peek)"""
65 return 'text/plain'
66
67 def merge(split_files, output_file):
68 """Merge HOMER databases (not implemented)."""
69 raise NotImplementedError("Merging HOMER databases is not supported")
70
71 def split( cls, input_datasets, subdir_generator_function, split_params):
72 """Split a HOMER database (not implemented)."""
73 if split_params is None:
74 return None
75 raise NotImplementedError("Can't split HOMER databases")
76