Mercurial > repos > iuc > snpsift_dbnsfp_datatypes

comparison snpsift_dbnsfp.py @ 0:0c4372b93e85 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author iuc
date Thu, 22 Jan 2015 08:04:59 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:0c4372b93e85
1 """
2 SnpSift dbNSFP datatypes
3 """
4 import os,os.path,re,sys,gzip,logging
5 import traceback
6 import galaxy.datatypes.data
7 from galaxy.datatypes.data import Text
8 from galaxy.datatypes.metadata import MetadataElement
9
10 log = logging.getLogger(__name__)
11
12 class SnpSiftDbNSFP( Text ):
13 """Class describing a dbNSFP database prepared fpr use by SnpSift dbnsfp """
14 MetadataElement( name='reference_name', default='dbSNFP' , desc='Reference Name', readonly=True, visible=True, set_in_upload=True, no_value='dbSNFP' )
15 MetadataElement( name="bgzip", default=None, desc="dbNSFP bgzip", readonly=True, visible=True, no_value=None )
16 MetadataElement( name="index", default=None, desc="Tabix Index File", readonly=True, visible=True, no_value=None)
17 MetadataElement( name="annotation", default=[], desc="Annotation Names", readonly=True, visible=True, no_value=[] )
18 file_ext = "snpsiftdbnsfp"
19 composite_type = 'auto_primary_file'
20 allow_datatype_change = False
21 """
22 ## The dbNSFP file is a tabular file with 1 header line
23 ## The first 4 columns are required to be: chrom pos ref alt
24 ## These match columns 1,2,4,5 of the VCF file
25 ## SnpSift requires the file to be block-gzipped and the indexed with samtools tabix
26 ## Example:
27 ## Compress using block-gzip algorithm
28 bgzip dbNSFP2.3.txt
29 ## Create tabix index
30 tabix -s 1 -b 2 -e 2 dbNSFP2.3.txt.gz
31 """
32 def __init__( self, **kwd ):
33 Text.__init__( self, **kwd )
34 self.add_composite_file( '%s.grp', description = 'Group File', substitute_name_with_metadata = 'reference_name', is_binary = False )
35 self.add_composite_file( '%s.ti', description = '', substitute_name_with_metadata = 'reference_name', is_binary = False )
36 def init_meta( self, dataset, copy_from=None ):
37 Text.init_meta( self, dataset, copy_from=copy_from )
38 def generate_primary_file( self, dataset = None ):
39 """
40 This is called only at upload to write the html file
41 cannot rename the datasets here - they come with the default unfortunately
42 """
43 regenerate_primary_file( self, dataset)
44 def regenerate_primary_file(self,dataset):
45 """
46 cannot do this until we are setting metadata
47 """
48 annotations = "dbNSFP Annotations: %s\n" % ','.join(dataset.metadata.annotation)
49 f = open(dataset.file_name,'a')
50 if dataset.metadata.bgzip:
51 bn = dataset.metadata.bgzip
52 f.write(bn)
53 f.write('\n')
54 f.write(annotations)
55 f.close()
56 def set_meta( self, dataset, overwrite=True, **kwd ):
57 try:
58 efp = dataset.extra_files_path
59 if os.path.exists(efp):
60 flist = os.listdir(efp)
61 for i,fname in enumerate(flist):
62 if fname.endswith('.gz'):
63 dataset.metadata.bgzip = fname
64 try:
65 fh = gzip.open(os.path.join(efp,fname),'r')
66 buf = fh.read(5000)
67 lines = buf.splitlines()
68 headers = lines[0].split('\t')
69 dataset.metadata.annotation = headers[4:]
70 except Exception,e:
71 log.warn("set_meta fname: %s %s" % (fname,str(e)))
72 traceback.print_stack(file=sys.stderr)
73 finally:
74 fh.close()
75 if fname.endswith('.tbi'):
76 dataset.metadata.index = fname
77 self.regenerate_primary_file(dataset)
78 except Exception,e:
79 log.warn("set_meta fname: %s %s" % (dataset.file_name if dataset and dataset.file_name else 'Unkwown',str(e)))
80 traceback.print_stack(file=sys.stderr)
81
82 if __name__ == '__main__':
83 import doctest
84 doctest.testmod(sys.modules[__name__])
85