Mercurial > repos > louise > export_to_fastq

comparison export_to_fastq/README @ 0:97792524cc9c default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Migrated tool version 0.1 from old tool shed archive to new tool shed repository
author louise
date Tue, 07 Jun 2011 17:21:49 -0400
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:97792524cc9c
1 Here is the needed class to handle Solexa Export file type.
2
3 The tool and class were written by Nicolas Delhomme (delhomme@embl.de).
4 Released under the GNU GPL: http://www.opensource.org/licenses/gpl-3.0.html
5
6 The threshold parameter was commented but it can very well be used. Just uncomment the commented code and comment the current command tag in the XML file.
7
8 If you want to apply this file as a patch, just run:
9 patch <path_to_galaxy>/lib/galaxy/datatypes/tabular.py README
10 ---
11
12 diff -r 50e249442c5a lib/galaxy/datatypes/tabular.py
13 --- a/lib/galaxy/datatypes/tabular.py Thu Apr 07 08:39:07 2011 -0400
14 +++ b/lib/galaxy/datatypes/tabular.py Tue May 24 14:16:12 2011 +0200
15 @@ -504,3 +504,95 @@
16
17 def get_track_type( self ):
18 return "FeatureTrack", {"data": "interval_index", "index": "summary_tree"}
19 +
20 +class Export( Tabular ):
21 + file_ext = 'export'
22 + def __init__(self, **kwd):
23 + """Initialize export datatype"""
24 + Tabular.__init__( self, **kwd )
25 + self.column_names = ['MACHINE', 'RUN', 'LANE', 'TILE',
26 + 'X', 'Y', 'MULTIPLEX', 'PAIRID',
27 + 'READ', 'QUALITY', 'CHROMOSOME', 'CONTIG',
28 + 'POSITION','STRAND','ALN_QUAL','CHASTITY'
29 + ]
30 +
31 + def make_html_table( self, dataset, skipchars=[] ):
32 + """Create HTML table, used for displaying peek"""
33 + out = ['<table cellspacing="0" cellpadding="3">']
34 + try:
35 + # Generate column header
36 + out.append( '<tr>' )
37 + for i, name in enumerate( self.column_names ):
38 + out.append( '<th>%s.%s</th>' % ( str( i+1 ), name ) )
39 + # This data type requires at least 16 columns in the data
40 + if dataset.metadata.columns - len( self.column_names ) > 0:
41 + for i in range( len( self.column_names ), dataset.metadata.columns ):
42 + out.append( '<th>%s</th>' % str( i+1 ) )
43 + out.append( '</tr>' )
44 + out.append( self.make_html_peek_rows( dataset, skipchars=skipchars ) )
45 + out.append( '</table>' )
46 + out = "".join( out )
47 + except Exception, exc:
48 + out = "Can't create peek %s" % exc
49 + return out
50 +
51 + def set_meta( self, dataset, overwrite = True, **kwd ):
52 +
53 + #we'll arbitrarily only use the first 100 data lines in the export file to calculate tabular attributes (column types)
54 + #optional metadata values set in Tabular class will be 'None'
55 + Tabular.set_meta( self, dataset, overwrite = overwrite, max_data_lines = 100 )
56 +
57 + def sniff( self, filename ):
58 + """
59 + Determines whether the file is in Export format
60 +
61 + A file in Export format consists of lines of tab-separated data.
62 + It does not have any header
63 +
64 + Rules for sniffing as True:
65 + There must be 16 columns of data on each line
66 + Columns 2 to 8 must be numbers
67 + Column 16 should be either Y or N
68 + We will only check that up to the first 5 alignments are correctly formatted.
69 +
70 + """
71 + try:
72 + fh = open( filename )
73 + count = 0
74 + while True:
75 + line = fh.readline()
76 + line = line.strip()
77 + if not line:
78 + break #EOF
79 + if line:
80 + if line[0] != '@':
81 + linePieces = line.split('\t')
82 + if len(linePieces) != 22:
83 + return False
84 + try:
85 + check = int(linePieces[1])
86 + check = int(linePieces[2])
87 + check = int(linePieces[3])
88 + check = int(linePieces[4])
89 + check = int(linePieces[5])
90 + check = int(linePieces[6])
91 + check = int(linePieces[7])
92 + assert linePieces[21] in [ 'Y', 'N' ]
93 + except ValueError:
94 + return False
95 + count += 1
96 + if count == 5:
97 + return True
98 + fh.close()
99 + if count < 5 and count > 0:
100 + return True
101 + except:
102 + pass
103 + return False
104 +
105 +class BarcodeSet( Tabular ):
106 + file_ext = 'bs'
107 + column_names = ['SAMPLE', 'BARCODE']
108 +
109 + def sniff( self, filename ):
110 + return False
111
112