-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathOverlap_counting
More file actions
75 lines (59 loc) · 3.59 KB
/
Overlap_counting
File metadata and controls
75 lines (59 loc) · 3.59 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
import pandas as pd
import os
import sys
# To run, simply type: python Overlap_counting.py LZ_intersect LZ_output P_intersect P_output D_intersect D_output
#Read in the input files and desired paths for result (output) files
LZ_intersect = sys.argv[1]
LZ_output = sys.argv[2]
P_intersect = sys.argv[3]
P_output = sys.argv[4]
D_intersect = sys.argv[5]
D_output = sys.argv[6]
#LZ
data = pd.read_csv(LZ_intersect,
sep = '\t',
names = ['chr', 'start', 'end', 'dataset', 'overlap'])
data['window'] = [x + '_' + str(y) + '_' + str(z) for x,y,z in zip(list(data['chr']), list(data['start']), list(data['end']))]
df = data.pivot(columns = 'dataset', values = 'overlap', index = 'window')
total_DMC1 = len(df.loc[df['DMC1'] > 0].index)
total_SPO11 = len(df.loc[df['SPO11'] > 0].index)
total_PRDM9 = len(df.loc[df['PRDM9'] > 0].index)
total_dREG = len(df.loc[df['dREG'] > 0].index)
DMC1_dREG_overlap = len((df.loc[(df['DMC1'] > 0) & (df['dREG'] > 0)].index))
PRDM9_dREG_overlap = len((df.loc[(df['PRDM9'] > 0) & (df['dREG'] > 0)].index))
SPO11_dREG_overlap = len((df.loc[(df['SPO11'] > 0) & (df['dREG'] > 0)].index))
output = pd.DataFrame(columns = ['Total_DMC1', 'Total_SPO11', 'Total_PRDM9', 'Total_dREG', 'DMC1_dREG_overlap', 'SPO11_dREG_overlap', 'PRDM9_dREG_overlap'])
output.loc[0] = [total_DMC1, total_SPO11, total_PRDM9, total_dREG, DMC1_dREG_overlap, SPO11_dREG_overlap, PRDM9_dREG_overlap]
output.to_csv(LZ_output, index = False)
#P
data = pd.read_csv(P_intersect,
sep = '\t',
names = ['chr', 'start', 'end', 'dataset', 'overlap'])
data['window'] = [x + '_' + str(y) + '_' + str(z) for x,y,z in zip(list(data['chr']), list(data['start']), list(data['end']))]
df = data.pivot(columns = 'dataset', values = 'overlap', index = 'window')
total_DMC1 = len(df.loc[df['DMC1'] > 0].index)
total_SPO11 = len(df.loc[df['SPO11'] > 0].index)
total_PRDM9 = len(df.loc[df['PRDM9'] > 0].index)
total_dREG = len(df.loc[df['dREG'] > 0].index)
DMC1_dREG_overlap = len((df.loc[(df['DMC1'] > 0) & (df['dREG'] > 0)].index))
PRDM9_dREG_overlap = len((df.loc[(df['PRDM9'] > 0) & (df['dREG'] > 0)].index))
SPO11_dREG_overlap = len((df.loc[(df['SPO11'] > 0) & (df['dREG'] > 0)].index))
output = pd.DataFrame(columns = ['Total_DMC1', 'Total_SPO11', 'Total_PRDM9', 'Total_dREG', 'DMC1_dREG_overlap', 'SPO11_dREG_overlap', 'PRDM9_dREG_overlap'])
output.loc[0] = [total_DMC1, total_SPO11, total_PRDM9, total_dREG, DMC1_dREG_overlap, SPO11_dREG_overlap, PRDM9_dREG_overlap]
output.to_csv(P_output, index = False)
#D
data = pd.read_csv(D_intersect,
sep = '\t',
names = ['chr', 'start', 'end', 'dataset', 'overlap'])
data['window'] = [x + '_' + str(y) + '_' + str(z) for x,y,z in zip(list(data['chr']), list(data['start']), list(data['end']))]
df = data.pivot(columns = 'dataset', values = 'overlap', index = 'window')
total_DMC1 = len(df.loc[df['DMC1'] > 0].index)
total_SPO11 = len(df.loc[df['SPO11'] > 0].index)
total_PRDM9 = len(df.loc[df['PRDM9'] > 0].index)
total_dREG = len(df.loc[df['dREG'] > 0].index)
DMC1_dREG_overlap = len((df.loc[(df['DMC1'] > 0) & (df['dREG'] > 0)].index))
PRDM9_dREG_overlap = len((df.loc[(df['PRDM9'] > 0) & (df['dREG'] > 0)].index))
SPO11_dREG_overlap = len((df.loc[(df['SPO11'] > 0) & (df['dREG'] > 0)].index))
output = pd.DataFrame(columns = ['Total_DMC1', 'Total_SPO11', 'Total_PRDM9', 'Total_dREG', 'DMC1_dREG_overlap', 'SPO11_dREG_overlap', 'PRDM9_dREG_overlap'])
output.loc[0] = [total_DMC1, total_SPO11, total_PRDM9, total_dREG, DMC1_dREG_overlap, SPO11_dREG_overlap, PRDM9_dREG_overlap]
output.to_csv(D_output, index = False)