v1.2.1

README.md

@@ -154,8 +154,8 @@ mafft --auto rice6.9.5.liban.rexdb.cls.pep.INT_TPase.faa > rice6.9.5.liban.rexdb
 ```
 Note: the domain names between rexdb and gydb are different: PROT (rexdb) = AP (gydb), RH (rexdb) = RNaseH (gydb). You should use the actual domain name.
 
-### extracting TE sequences from genome for TEsorter ###
-Here are examples to extract TE sequences from outputs of wide-used softwares.
+### Extracting TE sequences from genome for TEsorter ###
+Here are examples to extract TE sequences from outputs of wide-used softwares, when you have only genome sequences.
 
 1. extract all TE sequences from [RepeatMasker](http://www.repeatmasker.org/RMDownload.html) output:
 ```

bin/LTR_retriever.py

@@ -82,7 +82,8 @@ def get_full_seqs(self, fout=sys.stdout):
 		d_seqs = seq2dict(self.genome)
 		for rc in self.intact_list():
 			ltr_seq = d_seqs[rc.chr].seq[rc.start-1:rc.end]
-			print >> fout, '>{}\n{}'.format(rc.LTR_loc, ltr_seq)
+			ltr_cls = '{}/{}'.format(rc.TE_type, rc.SuperFamily)
+			print >> fout, '>{}#{}\n{}'.format(rc.LTR_loc, ltr_cls, ltr_seq)
 	def re_scn(self): # remove redundant
 		idmap = self.seqIdmap
 		lrt_set = set([])

bin/RepeatMasker.py

@@ -24,7 +24,9 @@ def __init__(self, line):
 		convert = [int, float, float, float,
 				   str, int, int, str, str,
 				   str, str, str, int, str, str ]
-		assert len(temp) == len(title) or (len(temp)-1 == len(title) and temp[-1] == "*")
+		assert len(temp) == len(title) or (len(temp)-1 == len(title) and temp[-1] == "*") or (len(temp) == len(title)-1)
+#		try: assert len(temp) == len(title) or (len(temp)-1 == len(title) and temp[-1] == "*")
+#		except AssertionError: print >> sys.stderr, temp, '\n', title
 		self.__dict__ = {key: func(value) for key,value,func in zip(title, temp, convert)}
 		self.query_left = int(self.query_left.strip('()'))
 		self.repeat_begin = int(self.repeat_begin.strip('()'))
@@ -70,6 +72,7 @@ def get_seq(self, seqRecord):
 		id = '{}:{}..{}|{}#{}'.format(self.query_id, self.query_begin, self.query_end, self.repeat_family, self.super_class)
 		teRecord = seqRecord[self.query_begin-1:self.query_end]
 		teRecord.id = id
+		teRecord.description = id
 		return teRecord
 
 class RMOutParser():