Mercurial > repos > devteam > ucsc_custom_track

comparison build_ucsc_custom_track.py @ 2:3d87079756e1 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/main/tools/ucsc_custom_track commit 68ba77da2a1f8d6cd04dd7dc6efc5edcefcfa0c9"
author devteam
date Mon, 28 Feb 2022 20:06:04 +0000
parents 618e56c3109b
children
comparison
equal deleted inserted replaced
1:760f588e8a26 2:3d87079756e1
1 #!/usr/bin/env python 1 #!/usr/bin/env python
2 """ 2 """
3 Build a UCSC genome browser custom track file 3 Build a UCSC genome browser custom track file
4 """ 4 """
5 5
6 import sys, os 6 import sys
7 7
8 assert sys.version_info[:2] >= ( 2, 4 ) 8 FILE_TYPE_TO_TRACK_TYPE = {'bed': None, 'bedstrict': None, 'bed6': None, 'bed12': None, 'bedgraph': 'bedGraph', 'wig': 'wiggle_0'}
9 CHUNK_SIZE = 2**20 # 1 mb
9 10
10 def stop_err( msg ):
11 sys.stderr.write( msg )
12 sys.exit()
13 11
14 FILE_TYPE_TO_TRACK_TYPE = { 'bed': None, 'bedstrict': None, 'bed6': None, 'bed12': None, 'bedgraph':'bedGraph', 'wig':'wiggle_0' } 12 def get_track_line_is_interval(file_type, name, description, color, visibility):
15 CHUNK_SIZE = 2**20 #1mb
16
17 def get_track_line_is_interval( file_type, name, description, color, visibility ):
18 if file_type in FILE_TYPE_TO_TRACK_TYPE: 13 if file_type in FILE_TYPE_TO_TRACK_TYPE:
19 track_type = FILE_TYPE_TO_TRACK_TYPE[ file_type ] 14 track_type = FILE_TYPE_TO_TRACK_TYPE[file_type]
20 is_interval = False 15 is_interval = False
21 else: 16 else:
22 track_type = None 17 track_type = None
23 is_interval = True 18 is_interval = True
24 track_line = 'track ' 19 track_line = 'track '
25 if track_type: 20 if track_type:
26 track_line += 'type=%s ' % ( track_type ) 21 track_line += f"type={track_type} "
27 track_line += 'name="%s" description="%s" color=%s visibility=%s\n' % ( name, description, color, visibility ) 22 track_line += f'name="{name}" description="{description}" color={color} visibility={visibility}\n'
28 return track_line, is_interval 23 return track_line, is_interval
29 24
30 args = sys.argv[1:]
31
32 out_fname = args.pop(0)
33 out = open( out_fname, "w" )
34 25
35 num_tracks = 0 26 num_tracks = 0
36 skipped_lines = 0 27 skipped_lines = 0
37 first_invalid_line = 0 28 first_invalid_line = 0
38 while args: 29 args = sys.argv[1:]
39 # Suck in one dataset worth of arguments 30 out_fname = args.pop(0)
40 in_fname = args.pop(0) 31 with open(out_fname, "w") as out:
41 file_type = args.pop(0) 32 while args:
42 colspec = args.pop(0) 33 # Suck in one dataset worth of arguments
43 name = args.pop(0) 34 in_fname = args.pop(0)
44 description = args.pop(0) 35 file_type = args.pop(0)
45 color = args.pop(0).replace( '-', ',' ) 36 colspec = args.pop(0)
46 visibility = args.pop(0) 37 name = args.pop(0)
47 track_line, is_interval = get_track_line_is_interval( file_type, name, description, color, visibility ) 38 description = args.pop(0)
48 # Do the work 39 color = args.pop(0).replace('-', ',')
49 in_file = open( in_fname ) 40 visibility = args.pop(0)
50 out.write( track_line ) 41 track_line, is_interval = get_track_line_is_interval(file_type, name, description, color, visibility)
51 if not is_interval: 42 # Do the work
52 while True: 43 out.write(track_line)
53 chunk = in_file.read( CHUNK_SIZE ) 44 with open(in_fname) as in_file:
54 if chunk: 45 if not is_interval:
55 out.write( chunk ) 46 while True:
47 chunk = in_file.read(CHUNK_SIZE)
48 if chunk:
49 out.write(chunk)
50 else:
51 break
56 else: 52 else:
57 break 53 # Assume type is interval (don't pass this script anything else!)
58 else: 54 try:
59 # Assume type is interval (don't pass this script anything else!) 55 c, s, e, st = (int(x) - 1 for x in colspec.split(","))
60 try: 56 except ValueError:
61 c, s, e, st = [ int( x ) - 1 for x in colspec.split( "," ) ]
62 except:
63 try:
64 c, s, e = [ int( x ) - 1 for x in colspec.split( "," )[:3] ]
65 st = -1 #strand column is absent
66 except:
67 stop_err( "Columns in interval file invalid for UCSC custom track." )
68
69 i = 0
70 for i, line in enumerate( in_file ):
71 line = line.rstrip( '\r\n' )
72 if line and not line.startswith( '#' ):
73 fields = line.split( "\t" )
74 if st > 0:
75 #strand column is present
76 try: 57 try:
77 out.write( "%s\t%s\t%s\t%d\t0\t%s\n" % ( fields[c], fields[s], fields[e], i, fields[st] ) ) 58 c, s, e = (int(x) - 1 for x in colspec.split(",")[:3])
78 except: 59 st = -1 # strand column is absent
79 skipped_lines += 1 60 except Exception:
80 if not first_invalid_line: 61 sys.exit("Columns in interval file invalid for UCSC custom track.")
81 first_invalid_line = i+1
82 else:
83 try:
84 out.write( "%s\t%s\t%s\n" % ( fields[c], fields[s], fields[e] ) )
85 except:
86 skipped_lines += 1
87 if not first_invalid_line:
88 first_invalid_line = i+1
89 out.write( "\n" ) #separating newline
90 num_tracks += 1
91
92 out.close()
93 62
94 print "Generated a custom track containing %d subtracks." % num_tracks 63 i = 0
64 for i, line in enumerate(in_file):
65 line = line.rstrip('\r\n')
66 if line and not line.startswith('#'):
67 fields = line.split("\t")
68 if st > 0:
69 # strand column is present
70 try:
71 out.write(f"{fields[c]}\t{fields[s]}\t{fields[e]}\t{i}\t0\t{fields[st]}\n")
72 except Exception:
73 skipped_lines += 1
74 if not first_invalid_line:
75 first_invalid_line = i + 1
76 else:
77 try:
78 out.write(f"{fields[c]}\t{fields[s]}\t{fields[e]}\n")
79 except Exception:
80 skipped_lines += 1
81 if not first_invalid_line:
82 first_invalid_line = i + 1
83 out.write("\n") # separating newline
84 num_tracks += 1
85
86 print(f"Generated a custom track containing {num_tracks} subtracks.")
95 if skipped_lines: 87 if skipped_lines:
96 print "Skipped %d invalid lines starting at #%d" % ( skipped_lines, first_invalid_line ) 88 print(f"Skipped {skipped_lines} invalid lines starting at #{first_invalid_line}")
97
98
99