def findSequences(text):
""" find dna in text and return as a list of tuples: (start, end, seq)
>>> list(findSequences(" actg catgtgtg catgtgc tgactg crap crap crap tga "))
[(1, 30, 'actgcatgtgtgcatgtgctgactg')]
"""
for row in pubDnaFind.nucleotideOccurrences(text):
if row.seq == "": # can only happen if seq is a restriction site
continue
yield row.start, row.end, row.seq
def findSequences(text):
""" find dna in text and return as a list of tuples: (start, end, seq)
>>> list(findSequences(" actg catgtgtg catgtgc tgactg crap crap crap tga "))
[(1, 30, 'actgcatgtgtgcatgtgctgactg')]
"""
for row in pubDnaFind.nucleotideOccurrences(text):
if row.seq=="": # can only happen if seq is a restriction site
continue
yield row.start, row.end, row.seq
def annotateFile(self, articleData, fileData):
""" interface for pubRun to get annotation lines for text """
# find organisms in text
dbs = set()
text = fileData.content
dbString = ",".join( set(findDbs(text)))
# find dna in text and add organisms
for row in pubDnaFind.nucleotideOccurrences(text):
if row.seq=="": # can only happen if seq is a restriction site
continue
row = [str(x) for x in row]
row.append(dbString)
yield row
def annotateFile(self, articleData, fileData):
""" interface for pubRun to get annotation lines for text """
# find organisms in text
dbs = set()
text = fileData.content
dbString = ",".join(set(findDbs(text)))
# find dna in text and add organisms
for row in pubDnaFind.nucleotideOccurrences(text):
if row.seq == "": # can only happen if seq is a restriction site
continue
row = [str(x) for x in row]
row.append(dbString)
yield row
