Mercurial > repos > gregory-minevich > ems_variant_density_mapping

comparison EMS_VariantDensityMapping.py @ 11:27b739051d72 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author gregory-minevich
date Mon, 08 Oct 2012 16:18:22 -0400
parents 6d2dbdfa11e3
children
comparison
equal deleted inserted replaced
10:1fd9f548d105 11:27b739051d72
1 #!/usr/bin/python
2
3 import re
4 import sys
5 import optparse
6 import csv
7 from rpy import *
8
9 def main():
10 parser = optparse.OptionParser()
11 parser.add_option('-s', '--snp_vcf', dest = 'snp_vcf', action = 'store', type = 'string', default = None, help = "VCF of SNPs")
12 parser.add_option('-c', '--hist_color', dest = 'hist_color', action = 'store', type = 'string', default = "darkgray", help = "Color for 1Mb histograms")
13 parser.add_option('-y', '--ylim', dest = 'ylim', action = 'store', type = 'int', default= 100, help = "Upper limit of Y axis")
14 parser.add_option('-z', '--standardize', dest = 'standardize', default= 'false', help = "Standardize X-axis")
15 parser.add_option('-e', '--ems', dest = 'ems', default= 'false', help = "Whether EMS variants should be filtered for")
16 parser.add_option('-o', '--output', dest = 'plot_output', action = 'store', type = 'string', default = 'EMS_Variant_Density_Plot.pdf', help = "Output file name of plot")
17 (options, args) = parser.parse_args()
18
19
20 i, ii, iii, iv, v, x = parse_snp_vcf(snp_vcf = options.snp_vcf, ems=options.ems)
21 create_histograms(plot_output = options.plot_output, hist_color=options.hist_color, ylim=options.ylim, ems=options.ems, standardize=options.standardize, i = i, ii = ii, iii = iii, iv = iv, v = v, x = x)
22
23 def create_histograms(plot_output = None, hist_color=None, ylim=None, ems=None, standardize=None , i = None, ii = None, iii = None, iv = None, v = None, x = None):
24 breaks = { 'I' : 16 , 'II' : 16, 'III' : 14, 'IV' : 18, 'V' : 21, 'X' : 18 }
25
26 try:
27 r.pdf(plot_output, 8, 8)
28 if len(i) > 0:
29 plot_data(position_list = i, chr = "I", breaks = breaks["I"], hist_color=hist_color, ylim=ylim, ems=ems, standardize=standardize)
30 if len(ii) > 0:
31 plot_data(position_list = ii, chr = "II", breaks = breaks["II"], hist_color=hist_color, ylim=ylim, ems=ems, standardize=standardize)
32 if len(iii) > 0:
33 plot_data(position_list = iii, chr = "III", breaks = breaks["III"], hist_color=hist_color, ylim=ylim, ems=ems, standardize=standardize)
34 if len(iv) > 0:
35 plot_data(position_list = iv, chr = "IV", breaks = breaks["IV"], hist_color=hist_color, ylim=ylim, ems=ems, standardize=standardize)
36 if len(v) > 0:
37 plot_data(position_list = v, chr = "V", breaks = breaks["V"], hist_color=hist_color, ylim=ylim, ems=ems, standardize=standardize)
38 if len(x) > 0:
39 plot_data(position_list = x, chr = "X", breaks = breaks["X"], hist_color=hist_color, ylim=ylim, ems=ems, standardize=standardize)
40 r.dev_off()
41 except Exception as inst:
42 print inst
43 print "There was an error creating the plot pdf... Please try again"
44
45 def parse_snp_vcf(snp_vcf = None, ems=None):
46 i_file = open(snp_vcf, 'rU')
47 reader = csv.reader(i_file, delimiter = '\t', quoting = csv.QUOTE_NONE)
48
49 skip_headers(reader = reader, i_file = i_file)
50
51 i_position_list = []
52 ii_position_list = []
53 iii_position_list = []
54 iv_position_list = []
55 v_position_list = []
56 x_position_list = []
57
58 for row in reader:
59 chromosome = row[0].upper()
60 chromosome = re.sub("chr", "", chromosome, flags = re.IGNORECASE)
61 chromosome = re.sub("CHROMOSOME_", "", chromosome, flags = re.IGNORECASE)
62
63 position = row[1]
64 ref_allele = row[3]
65 alt_allele = row[4]
66
67 if (ems=='true'):
68 if (ref_allele =="G" or ref_allele =="C") and (alt_allele =="A" or alt_allele =="T"):
69 if chromosome == "I":
70 i_position_list.append(position)
71 elif chromosome == "II":
72 ii_position_list.append(position)
73 elif chromosome == "III":
74 iii_position_list.append(position)
75 elif chromosome == "IV":
76 iv_position_list.append(position)
77 elif chromosome == "V":
78 v_position_list.append(position)
79 elif chromosome == "X":
80 x_position_list.append(position)
81 elif (ems=='false'):
82 if chromosome == "I":
83 i_position_list.append(position)
84 elif chromosome == "II":
85 ii_position_list.append(position)
86 elif chromosome == "III":
87 iii_position_list.append(position)
88 elif chromosome == "IV":
89 iv_position_list.append(position)
90 elif chromosome == "V":
91 v_position_list.append(position)
92 elif chromosome == "X":
93 x_position_list.append(position)
94
95 return i_position_list, ii_position_list, iii_position_list, iv_position_list, v_position_list, x_position_list
96
97 def skip_headers(reader = None, i_file = None):
98 # count headers
99 comment = 0
100 while reader.next()[0].startswith('#'):
101 comment = comment + 1
102
103 # skip headers
104 i_file.seek(0)
105 for i in range(0, comment):
106 reader.next()
107
108 def plot_data(position_list = None, chr = None, breaks = None, hist_color=None, ylim = None, ems=None, standardize=None):
109 positions = ",".join(map(str, map(lambda x: float(x) / 1000000, position_list)))
110 positions = "c(" + positions + ")"
111
112 if (standardize=='true'):
113 r("hist(" + positions + ", xlim=c(0,21), ylim=c(0, %d "%ylim +"),col='"+ hist_color + "', breaks = seq(0, as.integer( ' " + str(breaks) + " '), by=1), main = 'LG " + chr + "', ylab = 'Frequency Of SNPs', xlab = 'Location (Mb)')")
114 r("hist(" + positions + ", xlim=c(0,21), add=TRUE, ylim=c(0, %d "%ylim +"), col=rgb(1, 0, 0, 1), breaks = seq(0, as.integer( ' " + str(breaks) + " '), by=.5), main = 'Chr " + chr + "', ylab = 'Number Of SNPs', xlab = 'Location (Mb)')")
115 r("axis(1, at=seq(0, 21, by=1), labels=FALSE, tcl=-0.5)")
116 r("axis(1, at=seq(0, 21, by=0.5), labels=FALSE, tcl=-0.25)")
117 elif (standardize=='false'):
118 r("hist(" + positions + ", xlim=c(0,as.integer( ' " + str(breaks) + " ')), ylim=c(0, %d "%ylim +"),col='"+ hist_color + "', breaks = seq(0, as.integer( ' " + str(breaks) + " '), by=1), main = 'LG " + chr + "', ylab = 'Frequency Of SNPs', xlab = 'Location (Mb)')")
119 r("hist(" + positions + ", xlim=c(0,as.integer( ' " + str(breaks) + " ')), add=TRUE, ylim=c(0, %d "%ylim +"), col=rgb(1, 0, 0, 1), breaks = seq(0, as.integer( ' " + str(breaks) + " '), by=.5), main = 'Chr " + chr + "', ylab = 'Number Of SNPs', xlab = 'Location (Mb)')")
120 r("axis(1, at=seq(0, as.integer( ' " + str(breaks) + " '), by=1), labels=FALSE, tcl=-0.5)")
121 r("axis(1, at=seq(0, as.integer( ' " + str(breaks) + " '), by=0.5), labels=FALSE, tcl=-0.25)")
122
123
124
125 if __name__ == "__main__":
126 main()