diff options
| author | Hui Lan <lanhui@zjnu.edu.cn> | 2019-12-04 19:03:19 +0800 |
|---|---|---|
| committer | Hui Lan <lanhui@zjnu.edu.cn> | 2019-12-04 19:03:19 +0800 |
| commit | 97fdefab064f63642fa3ece05b807d29b459df31 (patch) | |
| tree | a058530023224f3e35b1783996f3530c80c04bc5 /Code/make_parameter_dapseq2.py | |
brain: add python and R code to local repository.
Diffstat (limited to 'Code/make_parameter_dapseq2.py')
| -rw-r--r-- | Code/make_parameter_dapseq2.py | 57 |
1 files changed, 57 insertions, 0 deletions
diff --git a/Code/make_parameter_dapseq2.py b/Code/make_parameter_dapseq2.py new file mode 100644 index 0000000..946ab6f --- /dev/null +++ b/Code/make_parameter_dapseq2.py @@ -0,0 +1,57 @@ +import sys, glob, os, operator
+from geneid2name import make_gene_name_AGI_map_dict
+
+DAPSEQ_DIR = '../Data/C/Mapped/dapseq/peaks'
+
+GENE_ID_TO_GENE_NAME = '../Data/information/AGI-to-gene-names_v2.txt'
+
+
+def make_dapseq_dictionary(dirname):
+
+ d = {}
+
+ files = glob.glob(os.path.join(dirname, '*/*/*/*.narrowPeak'))
+
+ for f in files:
+ lst = f.split('/')
+ tf_name = lst[-3]
+ if not tf_name in d:
+ d[tf_name] = f
+ else:
+ print('ERROR: transcription factor name not unique.')
+ sys.exit()
+
+ return d
+
+
+d = make_dapseq_dictionary(DAPSEQ_DIR)
+agi2name_dict = make_gene_name_AGI_map_dict(GENE_ID_TO_GENE_NAME)
+
+
+count = 1
+for k, v in sorted(d.items(), key=operator.itemgetter(0)):
+ cid = 'C0002%09d' % (count)
+ count += 1
+ print('@%s' % (cid))
+ g = k.split('_')[0]
+ g = g.upper()
+
+
+ if g.startswith('AT'):
+ print('PROTEIN_ID:%s' % (g))
+ elif g in agi2name_dict and g != agi2name_dict[g]:
+ print('PROTEIN_ID:%s' % (agi2name_dict[g]))
+ else:
+ print('PROTEIN_ID:%s' % (g))
+
+ if g.startswith('AT') and g in agi2name_dict and g != agi2name_dict[g]:
+ print('PROTEIN_NAME:%s' % (agi2name_dict[g]))
+ else:
+ print('PROTEIN_NAME:%s' % (g))
+
+ print('DATA_NAME:%s' % (k))
+ print('DATA_FORMAT:%s' % ('narrowPeak'))
+ print('DESCRIPTION:dapseq')
+ print('LOCATION:%s' % (v))
+ print('NOTE:')
+ print('')
|