def main():
# Use file defined by BIOC_IN as default if no other provided
bioc_in = BIOC_IN
if len(sys.argv) >= 2:
bioc_in = sys.argv[1]
# A BioCReader object is put in place to hold the example BioC XML
# document
bioc_reader = BioCReader(bioc_in, dtd_valid_file=DTD_FILE)
# A BioCWRiter object is prepared to write out the annotated data
bioc_writer = BioCWriter(BIOC_OUT)
# The NLTK porter stemmer is used for stemming
stemmer = PorterStemmer()
# The example input file given above (by BIOC_IN) is fed into
# a BioCReader object; validation is done by the BioC DTD
bioc_reader.read()
# Pass over basic data
bioc_writer.collection = bioc_reader.collection
# Get documents to manipulate
documents = bioc_writer.collection.documents
# Go through each document
annotation_id = 0
for document in documents:
# Go through each passage of the document
for passage in document:
# Stem all the tokens found
stems = [stemmer.stem(token) for
token in wordpunct_tokenize(passage.text)]
# Add an anotation showing the stemmed version, in the
# given order
for stem in stems:
annotation_id += 1
# For each token an annotation is created, providing
# the surface form of a 'stemmed token'.
# (The annotations are collectively added following
# a document passage with a <text> tag.)
bioc_annotation = BioCAnnotation()
bioc_annotation.text = stem
bioc_annotation.id = str(annotation_id)
bioc_annotation.put_infon('surface form',
'stemmed token')
passage.add_annotation(bioc_annotation)
# Print file to screen w/o trailing newline
# (Can be redirected into a file, e. g output_bioc.xml)
sys.stdout.write(str(bioc_writer))
# Write to disk
bioc_writer.write()
def test_should_get_gene_names_normalised(self, list_dict, expected_genes):
# Arrange
sut = BiocAnnotationGenes()
bioc_doc = BioCDocument()
bioc_passage = BioCPassage()
bioc_doc.add_passage(bioc_passage)
for dict in list_dict:
annotation = BioCAnnotation()
annotation.infons = dict
bioc_passage.add_annotation(annotation)
# act
actual = sut.get_gene_names_normalised(bioc_doc)
# assert
self.assertEqual(set(expected_genes), actual)
def brat2bioc_entity(bratentity: BratEntity) -> BioCAnnotation:
ann = BioCAnnotation()
ann.id = bratentity.id
ann.text = bratentity.text
ann.infons['type'] = bratentity.type
for span in bratentity.locations:
ann.add_location(BioCLocation(span.begin, span.end - span.begin))
return ann
def to_bioc(self):
entity_bioc = BioCAnnotation()
entity_bioc.infons['type'] = self.type
entity_bioc.text = self.text
entity_bioc.id = str(self.id)
location = BioCLocation(self.start, len(self.text))
entity_bioc.add_location(location)
return entity_bioc
def __parse_annotation(self, tree):
annotation = BioCAnnotation()
annotation.id = tree.attrib['id']
annotation.infons = self.__parse_infons(tree)
annotation.text = tree.findtext('text')
for child in tree.findall('location'):
annotation.add_location(
BioCLocation(int(child.attrib['offset']), int(child.attrib['length'])))
return annotation
def test_should_get_gene_names_to_normalised_dict(
self, list_gene_dict_in_passage, expected_dict):
# Arrange
sut = BiocAnnotationGenes()
bioc_doc = BioCDocument()
for list_gene_dict in list_gene_dict_in_passage:
bioc_passage = BioCPassage()
bioc_doc.add_passage(bioc_passage)
for dict in list_gene_dict:
annotation = BioCAnnotation()
annotation.text = dict["text"]
annotation.infons = dict
bioc_passage.add_annotation(annotation)
# act
actual = sut.get_gene_names_to_normalised_dict(bioc_doc)
# assert
self.assertEqual(expected_dict, actual)
def main():
# Use file defined by BIOC_IN as default if no other provided
bioc_in = BIOC_IN
if len(sys.argv) >= 2:
bioc_in = sys.argv[1]
# A BioCReader object is put in place to hold the example BioC XML
# document
bioc_reader = BioCReader(bioc_in, dtd_valid_file=DTD_FILE)
# A BioCWRiter object is prepared to write out the annotated data
bioc_writer = BioCWriter(BIOC_OUT)
# The NLTK porter stemmer is used for stemming
stemmer = PorterStemmer()
# The example input file given above (by BIOC_IN) is fed into
# a BioCReader object; validation is done by the BioC DTD
bioc_reader.read()
# Pass over basic data
bioc_writer.collection = bioc_reader.collection
# Get documents to manipulate
documents = bioc_writer.collection.documents
# Go through each document
annotation_id = 0
for document in documents:
# Go through each passage of the document
for passage in document:
# Stem all the tokens found
stems = [
stemmer.stem(token)
for token in wordpunct_tokenize(passage.text)
]
# Add an anotation showing the stemmed version, in the
# given order
for stem in stems:
annotation_id += 1
# For each token an annotation is created, providing
# the surface form of a 'stemmed token'.
# (The annotations are collectively added following
# a document passage with a <text> tag.)
bioc_annotation = BioCAnnotation()
bioc_annotation.text = stem
bioc_annotation.id = str(annotation_id)
bioc_annotation.put_infon('surface form', 'stemmed token')
passage.add_annotation(bioc_annotation)
# Print file to screen w/o trailing newline
# (Can be redirected into a file, e. g output_bioc.xml)
sys.stdout.write(str(bioc_writer))
# Write to disk
bioc_writer.write()
def add_annotation(triple, annotation_id):
# initialize annotation element
bioc_annotation = BioCAnnotation()
# MeSH term in a tag <text> ... </text> (origininal term, searched case insensitive)
bioc_annotation.text = triple[2]
# generate XML structure for the annotation and add infon
bioc_annotation.id = str(annotation_id)
bioc_annotation.put_infon('type', 'MeSH term')
# add location element
bioc_location = BioCLocation()
# add length of MeSH term
bioc_location.length = str(triple[1])
# add start position (offset)
bioc_location.offset = str(triple[0])
bioc_annotation.add_location(bioc_location)
return bioc_annotation
def add_annotation(triple, annotation_id):
# initialize annotation element
bioc_annotation = BioCAnnotation()
# MeSH term in a tag <text> ... </text> (origininal term, searched case insensitive)
bioc_annotation.text = triple[2]
# generate XML structure for the annotation and add infon
bioc_annotation.id = str(annotation_id)
bioc_annotation.put_infon('type', 'MeSH term')
# add location element
bioc_location = BioCLocation()
# add length of MeSH term
bioc_location.length = str(triple[1])
# add start position (offset)
bioc_location.offset = str(triple[0])
bioc_annotation.add_location(bioc_location)
return bioc_annotation
def __read_annotation(self, start_elem):
ann = BioCAnnotation()
ann.id = start_elem.get('id')
while self.__has_next():
event, elem = self.__next_event()
if event == 'start':
pass
elif event == 'end':
if elem.tag == 'text':
ann.text = elem.text
elif elem.tag == 'infon':
ann.infons[elem.get('key')] = elem.text
elif elem.tag == 'location':
ann.add_location(BioCLocation(int(elem.get('offset')), int(elem.get('length'))))
elif elem.tag == 'annotation':
return ann
raise RuntimeError("should not reach here") # pragma: no cover
def bioconcepts2pubtator_annotations(tag, index):
"""Bioconcepts to Annotations
Specifically for bioconcepts2pubtator and converts each annotation
into an annotation object that BioC can parse.
Keyword Arguments:
tag -- the annotation line that was parsed into an array
index -- the id of each document specific annotation
"""
annt = BioCAnnotation()
annt.id = str(index)
annt.infons["type"] = tag["type"]
# If the annotation type is a Gene,Species, Mutation, SNP
# Write out relevant tag
tag_type = tag['type'] or ''
tag_id = tag['tag_id']
if tag_type == "Gene":
annt.infons["NCBI Gene"] = tag_id
elif tag_type == "Species":
annt.infons["NCBI Species"] = tag_id
elif "Mutation" in tag_type:
annt.infons["tmVar"] = tag_id
elif "SNP" in tag_type:
annt.infons["tmVar"] = tag_id
else:
# If there is no MESH ID for an annotation
if tag_id:
# check to see if there are multiple mesh tags
if "|" in tag_id:
# Write out each MESH id as own tag
for tag_num, ids in enumerate(tag_id.split("|")):
# Some ids dont have the MESH:#### form so added case to that
if ":" not in ids:
annt.infons["MESH {}".format(tag_num)] = tag_id
else:
term_type, term_id = ids.split(":")
annt.infons["{} {}".format(term_type, tag_num)] = term_id
else:
# Some ids dont have the MESH:#### form so added case to that
if ":" in tag_id:
term_type, term_id = tag_id.split(":")
annt.infons[term_type] = term_id
else:
annt.infons["MESH"] = tag_id
else:
annt.infons["MESH"] = "Unknown"
location = BioCLocation()
location.offset = str(tag["start"])
location.length = str(len(tag["term"]))
annt.locations.append(location)
annt.text = tag["term"]
return annt
