Mercurial > repos > iuc > circos

annotate process-cytogenetic-bands.py @ 4:184dfd9e113d draft

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-iuc/tree/master/tools/circos commit f5db2969e8602eff32ec799d237875b911578fe5"
author iuc
date Thu, 09 Jan 2020 10:03:02 -0500
parents 014a21767ac4
children c4bde687c846
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
2
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
1 #!/usr/bin/env python
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
2 import sys
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
3
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
4 # band hs1 p36.32 p36.32 2200000 5100000 gpos25
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
5 # band hs1 p36.31 p36.31 5100000 6900000 gneg
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
6 # band hs1 p36.23 p36.23 6900000 8800000 gpos25
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
7 COLS = (
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
8 "chrom",
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
9 "chromStart",
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
10 "chromEnd",
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
11 "name",
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
12 "score",
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
13 "strand",
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
14 "thickStart",
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
15 "thickEnd",
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
16 "itemRgb",
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
17 )
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
18
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
19 colormap = {}
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
20 # Process optional cytogenetic bands
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
21 # band
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
22 # ID
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
23 # parentChr
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
24 # parentChr
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
25 # START
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
26 # END COLOR
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
27 with open(sys.argv[1], "r") as handle:
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
28 for line in handle:
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
29 if line.startswith("#"):
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
30 continue
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
31
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
32 lineData = dict(zip(COLS, line.split()))
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
33 color = lineData.get("itemRgb", "gpos50")
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
34
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
35 if color not in colormap:
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
36 # Color MUST be an RGB triplet
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
37 if color.count(",") != 2:
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
38 continue
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
39 tmp = color.replace(",", "")
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
40 # Try interpreting it, without `,`s as an integer. If it fails this
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
41 # test there are non-numerical values and they might try and send
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
42 # us an `eval()` or a colour name. We do not currently support
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
43 # colour names just in case.
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
44 try:
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
45 int(tmp)
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
46 except ValueError:
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
47 # Does not look like an int
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
48 continue
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
49
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
50 colormap[color] = "gx-karyotype-%s" % len(colormap.keys())
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
51
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
52 sys.stderr.write(
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
53 "{colorName} = {color}\n".format(colorName=colormap[color], color=color)
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
54 )
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
55
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
56 sys.stdout.write(
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
57 "band {chrom} {name} {name} {chromStart} {chromEnd} {color}\n".format(
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
58 # Can access name because requiring >bed3
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
59 name=lineData["name"],
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
60 chrom=lineData["chrom"],
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
61 chromStart=lineData["chromStart"],
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
62 chromEnd=lineData["chromEnd"],
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
63 # 255,0,0 is a valid colour specifier
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
64 color=colormap[color],
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
65 )
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
66 )
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
67
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
68
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
69 # chrom - The name of the chromosome (e.g. chr3, chrY, chr2_random) or scaffold (e.g. scaffold10671).
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
70 # chromStart - The starting position of the feature in the chromosome or scaffold. The first base in a chromosome is numbered 0.
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
71 # 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.
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
72 # 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.
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
73 # 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:
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
74 # strand - Defines the strand - either '+' or '-'.
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
75 # 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.
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
76 # thickEnd - The ending position at which the feature is drawn thickly (for example, the stop codon in gene displays).
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
77 # 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.
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
78 # blockCount - The number of blocks (exons) in the BED line.
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
79 # blockSizes - A comma-separated list of the block sizes. The number of items in this list should correspond to blockCount.
014a21767ac4 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/circos commit 076837a2e9c2b6ececcea4aa286ea7a412387a96"
iuc
parents:
diff changeset
80 # blockStarts - A comma-separated list of block starts. All of the blockStart positions should be calculated relative to chromStart. The number of items in this list should correspond to blockCount.