Mercurial > repos > yating-l > hubarchivecreator

comparison Bed.py @ 0:3e0c61b52a06 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/Yating-L/hub-archive-creator commit a77635b40ebd29baafb3bea57f8cbfb3f252e3b0-dirty
author yating-l
date Mon, 31 Oct 2016 16:36:25 -0400
parents
children 4ced8f116509
comparison
equal deleted inserted replaced
-1:000000000000 0:3e0c61b52a06
1 #!/usr/bin/python
2
3 import os
4 import tempfile
5
6 # Internal dependencies
7 from Datatype import Datatype
8 from Track import Track
9 from TrackDb import TrackDb
10 from util import subtools
11
12
13 class Bed( Datatype ):
14 def __init__( self, inputBedGeneric, data_bed_generic):
15 super(Bed, self).__init__()
16
17 self.track = None
18
19 self.inputBedGeneric = inputBedGeneric
20
21 self.sortedBedFile = tempfile.NamedTemporaryFile(suffix=".sortedBed")
22
23 self.data_bed_generic = data_bed_generic
24 self.name_bed_generic = self.data_bed_generic["name"]
25 self.priority = self.data_bed_generic["order_index"]
26 self.track_color = self.data_bed_generic["track_color"]
27 # TODO: Think about how to avoid repetition of the group_name everywhere
28 self.group_name = self.data_bed_generic["group_name"]
29
30 modified = self._checkAndFixBed()
31 # Sort processing
32 subtools.sort(self.inputBedGeneric, self.sortedBedFile.name)
33
34
35
36
37 # bedToBigBed processing
38 # TODO: Change the name of the bb, to tool + genome + possible adding if multiple + .bb
39 trackName = "".join( ( self.name_bed_generic, ".bb") )
40
41 myBigBedFilePath = os.path.join(self.myTrackFolderPath, trackName)
42 with open(myBigBedFilePath, 'w') as self.bigBedFile:
43 subtools.bedToBigBed(self.sortedBedFile.name,
44 self.chromSizesFile.name,
45 self.bigBedFile.name,
46 typeOption='bed12+1',
47 tab=True)
48
49 # Create the Track Object
50 self.createTrack(file_path=trackName,
51 track_name=trackName,
52 long_label=self.name_bed_generic, track_type='bigBed', visibility='dense',
53 priority=self.priority,
54 track_file=myBigBedFilePath,
55 track_color=self.track_color,
56 group_name=self.group_name,
57 )
58
59 # dataURL = "tracks/%s" % trackName
60 #
61 # trackDb = TrackDb(
62 # trackName=trackName,
63 # longLabel=self.name_bed_generic,
64 # shortLabel=self.getShortName(self.name_bed_generic),
65 # trackDataURL=dataURL,
66 # trackType='bigBed',
67 # visibility='dense',
68 # thickDrawItem='on',
69 # priority=self.priority,
70 # )
71 #
72 # # Return the BigBed track
73 # self.track = Track(
74 # trackFile=myBigBedFilePath,
75 # trackDb=trackDb,
76 # )
77
78 print("- Bed %s created" % self.name_bed_generic)
79 if (len(modified) != 0):
80 print("The lines that were removed: " + str(len(modified)))
81 #print("- %s created in %s" % (trackName, myBigBedFilePath))
82
83 # TODO: bed verifier, check if there are invalid strands: "."
84 def _checkAndFixBed(self):
85 """
86 Call _checkAndFixBed, check the integrity of bed file,
87 if the strand is not "+" or "-" truncate that line and report to users
88 create column and move the score column to
89 """
90 # Store the lines that have been removed
91 removedLines = []
92 # Remove the lines with invalid strand
93 temp_bed = tempfile.NamedTemporaryFile(bufsize=0, suffix=".bed", delete=False)
94 with open(temp_bed.name, 'w') as tmp:
95 with open(self.inputBedGeneric, 'r') as f:
96 lines = f.readlines()
97 for line in lines:
98 fields = line.split()
99 strand = fields[5]
100 score = fields[4]
101 fields[4] = '1000'
102 fields.append(score)
103 if (strand == '+' or strand == '-'):
104 tmp.write('\t'.join(map(str, fields)))
105 tmp.write("\n")
106 else:
107 removedLines.append(line)
108 self.inputBedGeneric = temp_bed.name
109
110 return removedLines