From 97fdefab064f63642fa3ece05b807d29b459df31 Mon Sep 17 00:00:00 2001 From: Hui Lan Date: Wed, 4 Dec 2019 19:03:19 +0800 Subject: brain: add python and R code to local repository. --- Code/make_parameter_dapseq2.py | 57 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 57 insertions(+) create mode 100644 Code/make_parameter_dapseq2.py (limited to 'Code/make_parameter_dapseq2.py') 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('') -- cgit v1.2.1