def _prepare_domains(self, dom_list):
"""Select domain subsequences from the entire protein sequences."""
def prepare_domains(fasta_dic, dom_list, pfam_scan, out_folder):
out_file_dic = {}
for acc in dom_list:
out_file_dic[acc] = open("%s/%s.fa" % (out_folder, acc), "w")
f = open(pfam_scan)
f.readline()
for line in f:
split = line.split()
rbp = split[0]
start = int(split[3])
stop = int(split[4])
acc = split[5].split('.')[0]
if acc in out_file_dic.keys():
out_file_dic[acc].write(
">%s:%i-%i\n%s\n" %
(rbp, start, stop, fasta_dic[rbp][start:stop]))
f.close()
for acc in dom_list:
out_file_dic[acc].close()
mkdir(self._dom_fold)
fasta = fasta_utils.import_fasta(self.fasta)
prepare_domains(fasta, dom_list, self.pfam_scan, self._dom_fold)
def _prepare_domains(self, dom_list):
"""Select domain subsequences from the entire protein sequences."""
def prepare_domains(fasta_dic, dom_list, pfam_scan, out_folder):
out_file_dic = {}
for acc in dom_list:
out_file_dic[acc] = open("%s/%s.fa" % (out_folder, acc), "w")
f = open(pfam_scan)
f.readline()
for line in f:
split = line.split()
rbp = split[0]
start = int(split[3])
stop = int(split[4])
acc = split[5].split('.')[0]
if acc in out_file_dic.keys():
out_file_dic[acc].write(
">%s:%i-%i\n%s\n" % (rbp, start, stop,
fasta_dic[rbp][start:stop]))
f.close()
for acc in dom_list:
out_file_dic[acc].close()
mkdir(self._dom_fold)
fasta = fasta_utils.import_fasta(self.fasta)
prepare_domains(fasta, dom_list, self.pfam_scan,
self._dom_fold)
def _pfam_scan(self):
"""Scan the sequences against the Pfam database."""
nf = open(self.pfam_scan, "w")
nf.write(pfam_utils.search_header())
fasta = fasta_utils.import_fasta(self.fasta)
for rbp in sorted(fasta.keys()):
seq = fasta[rbp]
text = pfam_utils.sequence_search(rbp, seq)
nf.write(text)
nf.close()
def _pfam_scan(self):
"""Scan the sequences against the Pfam database."""
nf = open(self.pfam_scan, "w")
nf.write(pfam_utils.search_header())
fasta = fasta_utils.import_fasta(self.fasta)
for rbp in sorted(fasta.keys()):
seq = fasta[rbp]
text = pfam_utils.sequence_search(rbp, seq)
nf.write(text)
nf.close()
def _pfam_scan(self):
"""Scan the sequences against the Pfam database."""
nf = open(self.pfam_scan, "w")
nf.write(pfam_utils.search_header())
fasta = fasta_utils.import_fasta(self.fasta)
if len(fasta) != 1:
sys.exit("""Fasta file must contain exactly one sequence.""")
for rbp in sorted(fasta.keys()):
seq = fasta[rbp]
text = pfam_utils.sequence_search(rbp, seq)
nf.write(text)
nf.close()
def _pfam_scan(self):
"""Scan the sequences against the Pfam database."""
nf = open(self.pfam_scan, "w")
nf.write(pfam_utils.search_header())
fasta = fasta_utils.import_fasta(self.fasta)
if len(fasta) != 1:
sys.exit("""Fasta file must contain exactly one sequence.""")
for rbp in sorted(fasta.keys()):
seq = fasta[rbp]
text = pfam_utils.sequence_search(rbp, seq)
nf.write(text)
nf.close()