cleanup after solo_ltr and trf; correct solo_ltr numbering (b69bdbc2) · Commits · Matej Lexa / nested

nested/core/solo_ltrs.py

+13 −1

Original line number	Original line	Diff line number	Diff line
	@@ -41,6 +41,7 @@ class SoloLtrs(object):

	def create_ltr_multifasta(self, tes, seq):		def create_ltr_multifasta(self, tes, seq):
	offset = len(self.ltr_lengths.keys())		offset = len(self.ltr_lengths.keys())
			num = 1
	with open("{}_ltrs.fa".format(self.seqId), 'a+') as file:		with open("{}_ltrs.fa".format(self.seqId), 'a+') as file:
	for i in range(len(self.ltr_lengths.keys()), len(self.ltr_lengths.keys()) + len(tes)):		for i in range(len(self.ltr_lengths.keys()), len(self.ltr_lengths.keys()) + len(tes)):
	if (intervals.length(tes[i - offset].ltr_left_location) < 100		if (intervals.length(tes[i - offset].ltr_left_location) < 100
	@@ -48,9 +49,10 @@ class SoloLtrs(object):
	or math.isnan(tes[i - offset].tsr_right[0])):		or math.isnan(tes[i - offset].tsr_right[0])):
	continue		continue

	file.write(">ltr_" + str(i) + "\n")		file.write(">ltr_" + str(num) + "\n")
	file.write(str(seq[tes[i - offset].ltr_left_location[0]:tes[i - offset].ltr_left_location[1] + 1]) + "\n")		file.write(str(seq[tes[i - offset].ltr_left_location[0]:tes[i - offset].ltr_left_location[1] + 1]) + "\n")
	self.ltr_lengths["ltr_" + str(i)] = len(str(seq[tes[i - offset].ltr_left_location[0]:tes[i - offset].ltr_left_location[1] + 1]))		self.ltr_lengths["ltr_" + str(i)] = len(str(seq[tes[i - offset].ltr_left_location[0]:tes[i - offset].ltr_left_location[1] + 1]))
			num += 1

	def run_blastn(self):		def run_blastn(self):
	args = dict(config['blastx']['args'])		args = dict(config['blastx']['args'])
	@@ -114,6 +116,7 @@ class SoloLtrs(object):
	result.difference(intersections.keys())		result.difference(intersections.keys())
	result.add(real_best)		result.add(real_best)

			# refactor this
	def cleanup(self):		def cleanup(self):
	if os.path.isfile("{}.nhr".format(self.ltrs_fasta_path)):		if os.path.isfile("{}.nhr".format(self.ltrs_fasta_path)):
	os.remove("{}.nhr".format(self.ltrs_fasta_path))		os.remove("{}.nhr".format(self.ltrs_fasta_path))
	@@ -121,4 +124,13 @@ class SoloLtrs(object):
	os.remove("{}.nin".format(self.ltrs_fasta_path))		os.remove("{}.nin".format(self.ltrs_fasta_path))
	if os.path.isfile("{}.nsq".format(self.ltrs_fasta_path)):		if os.path.isfile("{}.nsq".format(self.ltrs_fasta_path)):
	os.remove("{}.nsq".format(self.ltrs_fasta_path))		os.remove("{}.nsq".format(self.ltrs_fasta_path))
			if os.path.isfile("{}.ndb".format(self.ltrs_fasta_path)):
			os.remove("{}.ndb".format(self.ltrs_fasta_path))
			if os.path.isfile("{}.not".format(self.ltrs_fasta_path)):
			os.remove("{}.not".format(self.ltrs_fasta_path))
			if os.path.isfile("{}.ntf".format(self.ltrs_fasta_path)):
			os.remove("{}.ntf".format(self.ltrs_fasta_path))
			if os.path.isfile("{}.nto".format(self.ltrs_fasta_path)):
			os.remove("{}.nto".format(self.ltrs_fasta_path))

nested/core/tandem_repeat.py

+9 −0

Original line number	Original line	Diff line number	Diff line
	@@ -74,6 +74,9 @@ def get_candidates(seqid):
	split = entry.split(' ')		split = entry.split(' ')
	candidates.append(TandemRepeat([int(split[0]), int(split[1])], int(split[2]), float(split[3]),		candidates.append(TandemRepeat([int(split[0]), int(split[1])], int(split[2]), float(split[3]),
	int(split[5]), int(split[6]), int(split[7]), float(split[12]), split[-1]))		int(split[5]), int(split[6]), int(split[7]), float(split[12]), split[-1]))

			cleanup()

	return candidates		return candidates

	def filter_candidates(candidates):		def filter_candidates(candidates):
	@@ -101,5 +104,11 @@ def filter_candidates(candidates):
	repeats.append(candidate)		repeats.append(candidate)
	return repeats		return repeats

			def cleanup():
			if os.path.isfile("{}.fa.2.5.7.80.10.50.2000.dat".format(seqid)):
			os.remove("{}.fa.2.5.7.80.10.50.2000.dat".format(seqid))
			if os.path.isfile("{}.fa.2.5.7.80.10.50.2000.mask".format(seqid)):
			os.remove("{}.fa.2.5.7.80.10.50.2000.mask".format(seqid))