Mercurial > repos > iuc > circos
comparison unified-histogram.py @ 0:ef5f8bbf7730 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit a41493893bdcbe330434db9c5851719012b62fa8
author | iuc |
---|---|
date | Wed, 09 Aug 2017 09:52:52 -0400 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:ef5f8bbf7730 |
---|---|
1 #!/usr/bin/env python | |
2 import logging | |
3 import sys | |
4 | |
5 import wiggle | |
6 from BCBio import GFF | |
7 | |
8 logging.basicConfig(level=logging.INFO) | |
9 log = logging.getLogger() | |
10 | |
11 | |
12 MODE = sys.argv[1] | |
13 | |
14 # Pair up (file, extension) pairs from sys.argv | |
15 files = zip(sys.argv[2:][0::2], sys.argv[2:][1::2]) | |
16 | |
17 # Our output data structure. This could be much more efficient. | |
18 data = {} | |
19 | |
20 | |
21 def bed(idx, path): | |
22 # chrom - The name of the chromosome (e.g. chr3, chrY, chr2_random) or scaffold (e.g. scaffold10671). | |
23 # chromStart - The starting position of the feature in the chromosome or scaffold. The first base in a chromosome is numbered 0. | |
24 # chromEnd - The ending position of the feature in the chromosome or scaffold. The chromEnd base is not included in the display of the feature. For example, the first 100 bases of a chromosome are defined as chromStart=0, chromEnd=100, and span the bases numbered 0-99. | |
25 # name - Defines the name of the BED line. This label is displayed to the left of the BED line in the Genome Browser window when the track is open to full display mode or directly to the left of the item in pack mode. | |
26 # score - A score between 0 and 1000. If the track line useScore attribute is set to 1 for this annotation data set, the score value will determine the level of gray in which this feature is displayed (higher numbers = darker gray). This table shows the Genome Browser's translation of BED score values into shades of gray: | |
27 # strand - Defines the strand - either '+' or '-'. | |
28 # thickStart - The starting position at which the feature is drawn thickly (for example, the start codon in gene displays). When there is no thick part, thickStart and thickEnd are usually set to the chromStart position. | |
29 # thickEnd - The ending position at which the feature is drawn thickly (for example, the stop codon in gene displays). | |
30 # itemRgb - An RGB value of the form R,G,B (e.g. 255,0,0). If the track line itemRgb attribute is set to "On", this RBG value will determine the display color of the data contained in this BED line. NOTE: It is recommended that a simple color scheme (eight colors or less) be used with this attribute to avoid overwhelming the color resources of the Genome Browser and your Internet browser. | |
31 | |
32 with open(path, 'r') as handle: | |
33 for line in handle: | |
34 lineData = line.strip().split() | |
35 chrom = lineData[0] | |
36 chromStart = lineData[1] | |
37 chromEnd = lineData[2] | |
38 | |
39 if chrom not in data: | |
40 data[chrom] = {} | |
41 | |
42 for i in range(chromStart, chromEnd): | |
43 if i not in data[chrom]: | |
44 data[chrom][i] = {} | |
45 | |
46 data[chrom][i][idx] = lineData[5] | |
47 | |
48 | |
49 # Handlers | |
50 def gff3(idx, path): | |
51 for record in GFF.parse(path): | |
52 if len(record.features) == 0: | |
53 continue | |
54 | |
55 if record.id not in data: | |
56 data[record.id] = {} | |
57 | |
58 for feature in record.features: | |
59 if 'score' in feature.qualifiers: | |
60 for i in range(feature.location.start, feature.location.end): | |
61 if i not in data[record.id]: | |
62 data[record.id][i] = {} | |
63 | |
64 data[record.id][i][idx] = feature.qualifiers['score'][0] | |
65 | |
66 | |
67 def wig(idx, path): | |
68 walker = wiggle.Wiggle() | |
69 with open(path, 'r') as handle: | |
70 for region, position, value in walker.walk(handle): | |
71 if region not in data: | |
72 data[region] = {} | |
73 | |
74 if position not in data[region]: | |
75 data[region][position] = {} | |
76 | |
77 data[region][position][idx] = value | |
78 | |
79 | |
80 if __name__ == '__main__': | |
81 mode_tiles_possible = True | |
82 | |
83 for idx, (file_path, file_type) in enumerate(files): | |
84 log.info("Processing %s.%s", file_path, file_type) | |
85 | |
86 if file_type in globals(): | |
87 func = globals()[file_type] | |
88 func(idx, file_path) | |
89 | |
90 if file_type == 'wig': | |
91 mode_tiles_possible = False | |
92 | |
93 if MODE == 'tile' and not mode_tiles_possible: | |
94 raise Exception("You requested a 'tile' plot with wig data, which is impossible") | |
95 | |
96 # Max number of files | |
97 max_idx = range(len(files)) | |
98 | |
99 serialized_values = None | |
100 region_start, region_end = (None, None) | |
101 | |
102 for genome in data: | |
103 for position in sorted(data[genome]): | |
104 values = [ | |
105 '' if x not in data[genome][position] else data[genome][position][x] | |
106 for x in max_idx | |
107 ] | |
108 if serialized_values is None: | |
109 serialized_values = values | |
110 if region_start is None: | |
111 region_start = position | |
112 region_end = position | |
113 | |
114 if values == serialized_values: | |
115 region_end = position | |
116 else: | |
117 if MODE == 'histogram': | |
118 # histogram | |
119 # hs4 0 1999999 5.0000,3.0000,1.0000,19.0000 | |
120 sys.stdout.write(' '.join( | |
121 (genome, str(region_start), str(region_end), ','.join(map(str, values))) | |
122 ) + '\n') | |
123 elif MODE == 'heatmap': | |
124 # heatmap | |
125 # hs1 2000000 3999999 0.0000 id=hs4 | |
126 # hs1 4000000 5999999 2.0000 id=hs1 | |
127 # hs1 4000000 5999999 0.0000 id=hs2 | |
128 # hs1 4000000 5999999 0.0000 id=hs3 | |
129 # hs1 4000000 5999999 0.0000 id=hs4 | |
130 # hs1 6000000 7999999 4.0000 id=hs2 | |
131 for x in max_idx: | |
132 if x in data[genome][position]: | |
133 sys.stdout.write(' '.join( | |
134 (genome, str(region_start), str(region_end), data[genome][position][x], 'id=hm%s' % x) | |
135 ) + '\n') | |
136 else: | |
137 sys.stdout.write(' '.join( | |
138 (genome, str(region_start), str(region_end), 0.0, 'id=hm%s' % x) | |
139 ) + '\n') | |
140 elif MODE == 'line': | |
141 # multiple=False | |
142 sys.stdout.write(' '.join( | |
143 (genome, str(region_start), str(region_end), data[genome][position][0]) | |
144 ) + '\n') | |
145 elif MODE == 'scatter': | |
146 # multiple=False | |
147 sys.stdout.write(' '.join( | |
148 (genome, str(region_start), str(region_end), data[genome][position][0]) | |
149 ) + '\n') | |
150 | |
151 # Update start of next array | |
152 region_start = position | |
153 region_end = position | |
154 # And update with new array | |
155 serialized_values = values |