def parseScan(input="test.fasta", zip=True):
"""
dump[motif_name][Sequence][LOC][strand]=[start,end]
"""
basename = input.split(".")[0]
Motif_lst = loadMotifs2list("test.db")
CSV = {}
Motif_dic = {}
for entry in Motif_lst:
(motif_name, Sequence) = (entry[0], entry[2])
result = loadScanned("%s/Scan/%s.zip" % (basename, Sequence))
seq_dict = ScanParser(entry, result, CSV)
# TODO
nestDictUpdate(Motif_dic, [motif_name, Sequence], seq_dict)
if zip:
file = ZipFile("%s_csv.zip" % basename, "w", ZIP_DEFLATED)
for LOC in CSV.keys():
file.writestr(LOC + ".csv", "\n".join(CSV[LOC]))
file.close()
else:
for LOC in CSV.keys():
writeCSV(LOC, "\n".join(CSV[LOC]))
zf = ZipFile("%s.zpkl" % basename, "w", ZIP_DEFLATED)
zf.writestr("Motif_dic.pkl", cPickle.dumps(Motif_dic))
zf.close()
def SearchCARE(input="test.fasta"):
"""
在序列中搜索顺式调控元件motif
"""
basename = input.split(".")[0]
CARE = CAREdb("test.db")
Motif_lst = loadMotifs2list("test.db")
scanned_path = "%s/Scan" % basename
if not os.path.exists(scanned_path):
os.makedirs(scanned_path)
scanned = checkScanned("%s/Scan/" % basename)
for entry in Motif_lst:
(motif_name, Description, Sequence) = entry
Description = Description.replace(",", ";")
print motif_name, Sequence
if Sequence in scanned:
print "Skipping"
continue
ScanMotif(Sequence, input)
parseScan(input=input)
