-
Notifications
You must be signed in to change notification settings - Fork 0
/
DUXBL_TLX3.py
129 lines (77 loc) · 2.9 KB
/
DUXBL_TLX3.py
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
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
import numpy as np
from os.path import join
import pandas as pd
import pybedtools as pb
#import gseapy as gp
import seaborn as sns
import matplotlib.pyplot as plt
# === User defined
import RNA_expression_processing as rn
def log2p1(x):
return np.log2(x + 1)
SAVE = False
ntop=100
# === Load file
path = 'tracks/MARGE/relativeRP/DUXBL/'
#~ TLX3_regulated_TF2DNA.csv
df = pd.read_table(path+'TLX3_regulated_TF2DNA.csv')
#df = pd.read_table(path+'RAG_TLX_TAP_relativeRP_mm10mm9.txt')
# -- transform
#dfs = df.sort_values('TLX_rel_RP', axis=0, ascending=False)
#dfs.drop_duplicates(subset='gene_name', inplace=True)
#dfs.index=dfs['gene_name']
#~ A = 'TLX_rel_RP'
#~ if SAVE:
#~ from matplotlib.backends.backend_pdf import PdfPages
#~ pp = PdfPages(path+str(ntop)+'_RegPoten_TLX3.pdf')
#~ for B in ['RAG_rel_RP']: # ['RAG_rel_RP', 'TAP_rel_RP']:
#~ cols = ['gene_name', A, B]
#~ dfp = dfs[cols]
#~ # classes
#~ Ac = A+'c'
#~ Bc = B+'c'
#~ classe = [A+'c', B+'c']
#~ rn.scatter(dfp, Ac, Bc, classes=classe, n_top=5, geneList=[], ttl=A+'/'+B, names_term='Gene')
#~ if SAVE:
#~ plt.savefig(pp, format='pdf')
#~ top, up, dn, gs = rn.express(dfp, Ac, Bc, classes=classe, n_top=ntop, geneList=[], ttl=A+'/'+B)
#~ if SAVE:
#~ top.to_csv(path+'Top'+str(ntop)+'_'+A+'_vs_'+B+'.csv')
#~ plt.savefig(pp, format='pdf')
## Expression analysis
# === Load expression table
tbl = pd.read_table(join('tracks', 'TLX3vsRAG-results_genes.txt'), index_col=0)
tbl = tbl[(tbl.padj < 0.05)].dropna()
tbl = tbl.dropna()
# === Load gene names
names = pd.read_table("tracks/annot_tracks/references/mm9/mm9_EnsemblTransc_GeneNames.txt",
index_col=0,
header=0,
names=['GeneID', 'TransID', 'Gene_name'])
names = names.drop('TransID', axis=1).drop_duplicates()
names = names.loc[tbl.index]
assert names.shape[0] == tbl.shape[0]
tbl=names.join(tbl, how ='right')
tbn = tbl[['Gene_name', 'TLX3.1_1','TLX3.1_5','TLX3.1_P','R2.RAG1W.RAG1','RAGS.RAGZ','RAGZ', 'padj']]
## === Expresion analysis
classes = ['TLX3','TLX3','TLX3','RAG','RAG','RAG']
import RNA_expression_processing as rn
gl = list(df['gene_symbol'])
gl.insert(0,'TCF3')
#~ print(gl)
topN, upN, dnN, gsN = rn.express(tbn, 'TLX3', 'RAG',
classes=classes,
geneList=gl,
ttl='ALL genes',
n_top=120,
sort=True)
if SAVE:
plt.savefig(pp, format='pdf')
rn.scatter(tbn, 'TLX3', 'RAG', classes=classes, n_top=10, geneList=gl, ttl='ALL genes')
#~ rn.scatter(tbn, 'TLX3', 'RAG', classes=classes, n_top=5, geneList=[], ttl='ALL genes')
#~ rn.volcano(tbn, 'TLX3', 'RAG', classes=classes, n_top=5, geneList=[], ttl='ALL genes')
#~ if SAVE:
#~ dfs.head(500)['gene_name'].to_csv('topRPtlx3.txt')
if SAVE:
pp.close()
plt.show()