summaryrefslogtreecommitdiff
path: root/Code/make_target_tf_agris.py
diff options
context:
space:
mode:
authorHui Lan <lanhui@zjnu.edu.cn>2019-12-04 19:03:19 +0800
committerHui Lan <lanhui@zjnu.edu.cn>2019-12-04 19:03:19 +0800
commit97fdefab064f63642fa3ece05b807d29b459df31 (patch)
treea058530023224f3e35b1783996f3530c80c04bc5 /Code/make_target_tf_agris.py
brain: add python and R code to local repository.
Diffstat (limited to 'Code/make_target_tf_agris.py')
-rw-r--r--Code/make_target_tf_agris.py39
1 files changed, 39 insertions, 0 deletions
diff --git a/Code/make_target_tf_agris.py b/Code/make_target_tf_agris.py
new file mode 100644
index 0000000..c96c8fa
--- /dev/null
+++ b/Code/make_target_tf_agris.py
@@ -0,0 +1,39 @@
+# Make target_tf from AtRegNet.txt
+# Usage: python make_target_tf_agris.py > ../Data/information/target_tf_agris.txt
+
+fname = '../Data/information/AtRegNet.txt'
+
+sample_id = 'C0000000000001'
+
+f = open(fname)
+lines = f.readlines()
+f.close()
+
+d = {}
+count = 2
+duplicate = 0
+for line in lines[1:]:
+ line = line.strip()
+ lst = line.split('\t')
+ if len(lst) >= 5:
+ tf0 = lst[1].upper().strip()
+ target0 = lst[4].upper().strip()
+ tf_lst = tf0.split('/')
+ target_lst = target0.split('/')
+ for tf in tf_lst:
+ for target in target_lst:
+ if tf.startswith('AT') and target.startswith('AT'):
+ k = target + '.' + tf
+ if k in d:
+ #print('Warning at line %d ' % (count))
+ duplicate += 1
+ else:
+ d[k] = [target, tf, sample_id]
+ count += 1
+
+
+print('pairs %d' % len(d))
+print('duplicate %d' % (duplicate))
+for k in sorted(d.keys()):
+ print('\t'.join(d[k]))
+