def test_loadBiocFile_dir():
scriptDir = os.path.dirname(__file__)
dataPath = os.path.join(scriptDir, 'data')
corpus = kindred.load(dataFormat='biocxml', path=dataPath)
assert isinstance(corpus, kindred.Corpus)
assert len(corpus.documents) == 1
doc = corpus.documents[0]
assert isinstance(doc, kindred.Document)
entities = doc.entities
relations = doc.relations
sourceEntityIDsToEntity = {
entity.sourceEntityID: entity
for entity in entities
}
assertEntity(entities[0],
expectedType='disease',
expectedText='colorectal cancer',
expectedPos=[(4, 21)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='APC',
expectedPos=[(49, 52)],
expectedSourceEntityID="T2")
assert relations == [
kindred.Relation(
'causes',
[sourceEntityIDsToEntity["T1"], sourceEntityIDsToEntity["T2"]],
['obj', 'subj'])
], "(%s) not as expected" % relations
def test_loadEmptyDirectory():
with TempDir() as tempDir:
for dataformat in ['standoff', 'simpletag', 'json', 'biocxml']:
with pytest.raises(RuntimeError) as excinfo:
corpus = kindred.load(dataformat, tempDir)
expectedError = 'No documents loaded from directory (%s). Are you sure this directory contains the corpus (format: %s)' % (
tempDir.rstrip('/'), dataformat)
assert excinfo.value.args == (expectedError, )
def test_saveStandoffFile():
text = "The colorectal cancer was caused by mutations in APC"
e1 = kindred.Entity(entityType="disease",
text="colorectal cancer",
position=[(4, 21)],
sourceEntityID="T1")
e2 = kindred.Entity(entityType="gene",
text="APC",
position=[(49, 52)],
sourceEntityID="T2")
rel = kindred.Relation(relationType="causes",
entities=[e1, e2],
argNames=['obj', 'subj'])
doc = kindred.Document(text, [e1, e2], [rel])
corpus = kindred.Corpus()
corpus.addDocument(doc)
with TempDir() as tempDir:
kindred.save(corpus, 'standoff', tempDir)
for filename in os.listdir(tempDir):
if filename.endswith('.a2'):
checkRelationAnnotations(os.path.join(tempDir, filename))
loadedCorpus = kindred.load('standoff', tempDir)
assert isinstance(loadedCorpus, kindred.Corpus)
assert len(loadedCorpus.documents) == 1
loadedDoc = loadedCorpus.documents[0]
assert isinstance(loadedDoc, kindred.Document)
entities = loadedDoc.entities
relations = loadedDoc.relations
sourceEntityIDToEntity = {
entity.sourceEntityID: entity
for entity in entities
}
assertEntity(entities[0],
expectedType='disease',
expectedText='colorectal cancer',
expectedPos=[(4, 21)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='APC',
expectedPos=[(49, 52)],
expectedSourceEntityID="T2")
assert relations == [
kindred.Relation(
'causes',
[sourceEntityIDToEntity["T1"], sourceEntityIDToEntity["T2"]],
['obj', 'subj'],
sourceRelationID='R1')
], "(%s) not as expected" % relations
def test_saveBB3Data():
corpus = kindred.bionlpst.load('2016-BB3-event-train')
assert isinstance(corpus, kindred.Corpus)
with TempDir() as tempDir:
kindred.save(corpus, 'standoff', tempDir)
for filename in os.listdir(tempDir):
if filename.endswith('.a2'):
checkRelationAnnotations(os.path.join(tempDir, filename))
loadedCorpus = kindred.load('standoff', tempDir)
assert len(corpus.documents) == len(loadedCorpus.documents)
def test_saveStandoffFile_fromSimpleTag_triple():
text = '<drug id="T1">Erlotinib</drug>, a <gene id="T2">EGFR</gene> inhibitor is commonly used for <disease id="T3">NSCLC</disease> patients. <relation type="druginfo" drug="T1" gene="T2" disease="T3" />'
corpus = kindred.Corpus(text, loadFromSimpleTag=True)
with TempDir() as tempDir:
kindred.save(corpus, 'standoff', tempDir)
for filename in os.listdir(tempDir):
if filename.endswith('.a2'):
checkRelationAnnotations(os.path.join(tempDir, filename))
loadedCorpus = kindred.load('standoff', tempDir)
assert isinstance(loadedCorpus, kindred.Corpus)
assert len(loadedCorpus.documents) == 1
loadedDoc = loadedCorpus.documents[0]
assert isinstance(loadedDoc, kindred.Document)
entities = loadedDoc.entities
relations = loadedDoc.relations
sourceEntityIDToEntity = {
entity.sourceEntityID: entity
for entity in entities
}
assertEntity(entities[0],
expectedType='drug',
expectedText='Erlotinib',
expectedPos=[(0, 9)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='EGFR',
expectedPos=[(13, 17)],
expectedSourceEntityID="T2")
assertEntity(entities[2],
expectedType='disease',
expectedText='NSCLC',
expectedPos=[(49, 54)],
expectedSourceEntityID="T3")
assert relations == [
kindred.Relation('druginfo', [
sourceEntityIDToEntity["T3"], sourceEntityIDToEntity["T1"],
sourceEntityIDToEntity["T2"]
], ['disease', 'drug', 'gene'],
sourceRelationID='R1')
], "(%s) not as expected" % relations
def test_saveStandoffFile_fromSimpleTag_binary():
text = 'The <disease id="T1">colorectal cancer</disease> was caused by mutations in <gene id="T2">APC</gene><relation type="causes" subj="T2" obj="T1" />'
corpus = kindred.Corpus(text, loadFromSimpleTag=True)
with TempDir() as tempDir:
kindred.save(corpus, 'standoff', tempDir)
for filename in os.listdir(tempDir):
if filename.endswith('.a2'):
checkRelationAnnotations(os.path.join(tempDir, filename))
loadedCorpus = kindred.load('standoff', tempDir)
assert isinstance(loadedCorpus, kindred.Corpus)
assert len(loadedCorpus.documents) == 1
loadedDoc = loadedCorpus.documents[0]
assert isinstance(loadedDoc, kindred.Document)
entities = loadedDoc.entities
relations = loadedDoc.relations
sourceEntityIDToEntity = {
entity.sourceEntityID: entity
for entity in entities
}
assertEntity(entities[0],
expectedType='disease',
expectedText='colorectal cancer',
expectedPos=[(4, 21)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='APC',
expectedPos=[(49, 52)],
expectedSourceEntityID="T2")
print([r.sourceRelationID for r in relations])
assert relations == [
kindred.Relation(
'causes',
[sourceEntityIDToEntity["T1"], sourceEntityIDToEntity["T2"]],
['obj', 'subj'],
sourceRelationID='R1')
], "(%s) not as expected" % relations
def test_savePubAnnotationFile_fromSimpleTag():
text = 'The <disease id="T1">colorectal cancer</disease> was caused by mutations in <gene id="T2">APC</gene><relation type="causes" subj="T2" obj="T1" />'
corpus = kindred.Corpus(text, loadFromSimpleTag=True)
with TempDir() as tempDir:
tempFile = os.path.join(tempDir, 'corpus.json')
kindred.save(corpus, 'pubannotation', tempFile)
loadedCorpus = kindred.load('pubannotation', tempFile)
assert isinstance(loadedCorpus, kindred.Corpus)
assert len(loadedCorpus.documents) == 1
loadedDoc = loadedCorpus.documents[0]
assert isinstance(loadedDoc, kindred.Document)
entities = loadedDoc.entities
relations = loadedDoc.relations
sourceEntityIDToEntity = {
entity.sourceEntityID: entity
for entity in entities
}
assertEntity(entities[0],
expectedType='disease',
expectedText='colorectal cancer',
expectedPos=[(4, 21)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='APC',
expectedPos=[(49, 52)],
expectedSourceEntityID="T2")
print([r.sourceRelationID for r in relations])
assert relations == [
kindred.Relation(
'causes',
[sourceEntityIDToEntity["T1"], sourceEntityIDToEntity["T2"]],
['subj', 'obj'],
sourceRelationID='R1')
], "(%s) not as expected" % relations
def test_loadStandoffFile_triple():
scriptDir = os.path.dirname(__file__)
txtPath = os.path.join(scriptDir, 'data_triple', 'example.txt')
corpus = kindred.load('standoff', txtPath)
assert isinstance(corpus, kindred.Corpus)
assert len(corpus.documents) == 1
doc = corpus.documents[0]
assert isinstance(doc, kindred.Document)
entities = doc.entities
relations = doc.relations
sourceEntityIDsToEntity = {
entity.sourceEntityID: entity
for entity in entities
}
assertEntity(entities[0],
expectedType='drug',
expectedText='Erlotinib',
expectedPos=[(0, 9)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='EGFR',
expectedPos=[(13, 17)],
expectedSourceEntityID="T2")
assertEntity(entities[2],
expectedType='disease',
expectedText='NSCLC',
expectedPos=[(49, 54)],
expectedSourceEntityID="T3")
assert relations == [
kindred.Relation('druginfo', [
sourceEntityIDsToEntity["T3"], sourceEntityIDsToEntity["T1"],
sourceEntityIDsToEntity["T2"]
], ['disease', 'drug', 'gene'],
sourceRelationID='R0')
], "(%s) not as expected" % relations
def load(taskName, ignoreEntities=[]):
"""
Download and load the corresponding corpus from the BioNLP Shared Task
:param taskName: The name of the shared task to download (e.g. 'BioNLP-ST-2016_BB-event_train'). Use kindred.bionlpst.listTasks() to get a list of valid options
:param ignoreEntities: A list of any entities that should be ignored during loading
:type taskName: str
:type ignoreEntities: list of str
:return: The loaded corpus
:rtype: kindred.Corpus
"""
global taskOptions
tempDir = tempfile.mkdtemp()
assert taskName in taskOptions.keys(), "%s not a valid option in %s" % (
taskName, taskOptions.keys())
url, expectedFile, expectedSHA256 = taskOptions[taskName]
filesToDownload = [(url, expectedFile, expectedSHA256)]
expectedDir = expectedFile.replace('.zip', '')
try:
kindred.utils._downloadFiles(filesToDownload, tempDir)
except:
exc_info = sys.exc_info()
shutil.rmtree(tempDir)
six.reraise(*exc_info)
mainDir = kindred.utils._findDir(expectedDir, tempDir)
corpus = kindred.load(dataFormat='standoff',
path=mainDir,
ignoreEntities=ignoreEntities)
shutil.rmtree(tempDir)
return corpus
def test_saveStandoffFile_SeparateSentences():
texts = [
'The <disease id="T1">colorectal cancer</disease> was caused by mutations in <gene id="T2">APC</gene><relation type="causes" subj="T2" obj="T1" />',
'<disease id="T1">Li-Fraumeni</disease> was caused by mutations in <gene id="T2">P53</gene><relation type="causes" subj="T2" obj="T1" />'
]
corpus = kindred.Corpus()
for t in texts:
doc = kindred.Document(t, loadFromSimpleTag=True)
corpus.addDocument(doc)
with TempDir() as tempDir:
kindred.save(corpus, 'standoff', tempDir)
for filename in os.listdir(tempDir):
if filename.endswith('.a2'):
checkRelationAnnotations(os.path.join(tempDir, filename))
loadedCorpus = kindred.load('standoff', tempDir)
assert isinstance(loadedCorpus, kindred.Corpus)
assert len(loadedCorpus.documents) == 2
data = loadedCorpus.documents[0]
assert isinstance(data, kindred.Document)
entities = data.entities
relations = data.relations
sourceEntityIDToEntity = {
entity.sourceEntityID: entity
for entity in entities
}
assertEntity(entities[0],
expectedType='disease',
expectedText='colorectal cancer',
expectedPos=[(4, 21)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='APC',
expectedPos=[(49, 52)],
expectedSourceEntityID="T2")
assert relations == [
kindred.Relation(
'causes',
[sourceEntityIDToEntity["T1"], sourceEntityIDToEntity["T2"]],
['obj', 'subj'])
], "(%s) not as expected" % relations
data = loadedCorpus.documents[1]
assert isinstance(data, kindred.Document)
entities = data.entities
relations = data.relations
sourceEntityIDToEntity = {
entity.sourceEntityID: entity
for entity in entities
}
assertEntity(entities[0],
expectedType='disease',
expectedText='Li-Fraumeni',
expectedPos=[(0, 11)],
expectedSourceEntityID="T1")
assertEntity(entities[1],
expectedType='gene',
expectedText='P53',
expectedPos=[(39, 42)],
expectedSourceEntityID="T2")
assert relations == [
kindred.Relation(
'causes',
[sourceEntityIDToEntity["T1"], sourceEntityIDToEntity["T2"]],
['obj', 'subj'])
], "(%s) not as expected" % relations
def get_rels():
c.execute("SELECT * FROM relationships")
return c.fetchall()
def get_rels_clean():
c.execute("SELECT gene, disease, relation FROM relationships")
return c.fetchall()
# Kindred
# 5 classes
trainCorpus = kindred.load(dataFormat='json', path='relation/db/1')
devCorpus = kindred.load(dataFormat='json', path='ner-dump')
predictionCorpus = devCorpus.clone()
classifier = kindred.RelationClassifier()
classifier.train(trainCorpus)
classifier.predict(predictionCorpus)
f1score = kindred.evaluate(devCorpus, predictionCorpus, metric='f1score')
print("5 CLASSES ---------------------")
for i in predictionCorpus.documents:
for j in (i.relations):
rel = Relationships(j.entities[0].text, j.entities[1].text,
j.relationType, i.text)
parser = argparse.ArgumentParser(
description='Create PR curves using a train and test set')
parser.add_argument('--train',
required=True,
type=str,
help='Directory containing stand-off training test')
parser.add_argument('--test',
required=True,
type=str,
help='Directory containing stand-off testing test')
args = parser.parse_args()
print("threshold\tprecision\trecall")
for threshold in np.arange(0, 1.01, 0.01):
trainCorpus = kindred.load('standoff', args.train)
testCorpus = kindred.load('standoff', args.test)
predCorpus = testCorpus.clone()
predCorpus.removeRelations()
parser = kindred.Parser(model='en_core_sci_sm')
parser.parse(trainCorpus)
parser.parse(testCorpus)
parser.parse(predCorpus)
classifier = kindred.RelationClassifier(
classifierType='LogisticRegression',
threshold=threshold,
acceptedEntityTypes=[('Chemical', 'Mutation')])
classifier.train(trainCorpus)
import kindred
import argparse
import os
import csv
with open('5_types_lp.csv', mode='w') as csv_file:
fieldnames = ['iteration_num', 'svm', 'decision_trees', 'neural_net']
writer = csv.DictWriter(csv_file, fieldnames=fieldnames)
writer.writeheader()
Corpus = kindred.load(dataFormat='json', path='db/5types')
# avg_svm = 0
# avg_dct = 0
# avg_nn = 0
count = 0
iter_num = 200
print("-------------5 CLASSES------------")
while count < iter_num:
print("------", count, "------")
trainCorpus, devCorpus = Corpus.split(trainFraction=0.9)
predictionCorpus = devCorpus.clone()
predictionCorpus.removeRelations()
classifier = kindred.RelationClassifier()
headers = [
'pmid', 'title', 'journal', 'journal_short', 'year', 'month', 'day',
'section', 'subsection', 'chemical_mesh_id', 'chemical_pharmgkb_id',
'chemical_drugbank_id', 'chemical_text', 'chemical_normalized',
'chemical_position', 'variant_id', 'variant_type', 'variant_text',
'variant_normalized', 'variant_position', 'gene_ids', 'gene_names',
'score', 'sentence', 'formatted_sentence'
]
with open(args.outKB, 'w') as outF:
outF.write("\t".join(headers) + "\n")
for mode, trainingData in zip(modes, trainingFiles):
print("Creating classifier for %s" % mode)
predictedCount = 0
trainCorpus = kindred.load('biocxml', trainingData)
corpus = kindred.load('biocxml', args.inBioC)
for doc in trainCorpus.documents:
for relation in doc.relations:
relation.relationType = 'ChemicalMutation'
for doc in corpus.documents:
if mode == 'star_allele':
doc.entities = [
e for e in doc.entities
if not (e.entityType == 'Mutation'
and not e.text.strip().startswith('*'))
]
elif mode == 'rs':
doc.entities = [
import kindred
import argparse
import os
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='Use annotated sentences to build a Kindred classifer and apply to unannotated sentences')
parser.add_argument('--dataToBuildModel',required=True,type=str,help='Sentences with relations')
parser.add_argument('--dataToApplyModel',required=True,type=str,help='Sentences without annotated relations to make predictions on')
parser.add_argument('--outDir',required=True,type=str,help='Directory to store output')
args = parser.parse_args()
print("Loading corpora...")
trainCorpus = kindred.load('standoff',args.dataToBuildModel)
predictionCorpus = kindred.load('standoff',args.dataToApplyModel)
print("Building classifier...")
classifier = kindred.RelationClassifier()
classifier.train(trainCorpus)
print("Applying classifier...")
classifier.predict(predictionCorpus)
if not os.path.isdir(args.outDir):
os.makedirs(args.outDir)
print("Saving results to directory...")
kindred.save(predictionCorpus,'standoff',args.outDir)
print("\nPredicted relations:")
for relation in predictionCorpus.getRelations():
print("%s\t%s" % (relation.entities[0].text,relation.entities[1].text))
'Driver': 0.80,
'Oncogene': 0.76,
'Tumor_Suppressor': 0.92
}
else:
thresholds = {'Driver': 0.5, 'Oncogene': 0.5, 'Tumor_Suppressor': 0.5}
for relationType, outModel in zip(
['Driver', 'Oncogene', 'Tumor_Suppressor'], [
args.outModel_Driver, args.outModel_Oncogene,
args.outModel_TumorSuppressor
]):
print("Building %s model" % relationType)
print(" Loading training")
goldDir = 'gold'
trainCorpus = kindred.load('standoff', args.inTrain)
for doc in trainCorpus.documents:
doc.relations = [
r for r in doc.relations if r.relationType == relationType
]
print(" Doing training")
features = "entityTypes,unigramsBetweenEntities,bigrams,dependencyPathEdges,dependencyPathEdgesNearEntities".split(
',')
threshold = thresholds[relationType]
classifier = kindred.RelationClassifier(
classifierType='LogisticRegression',
threshold=threshold,
features=features,
acceptedEntityTypes=[('cancer', 'gene')])
with open(args.variantStopwords) as f:
variantStopwords = set(line.strip().lower() for line in f)
stopwords = {'dopamine', 'insulin', 'caffeine', 'nicotine', 'choline'}
print("Loading sentences...")
corpus = kindred.Corpus()
filenames = sorted(os.listdir(args.sentenceData))
if args.fileCount:
filenames = random.sample(filenames, args.fileCount)
for i, filename in enumerate(filenames):
print(i, filename)
tmpCorpus = kindred.load('biocxml',
os.path.join(args.sentenceData, filename))
if args.filterTerms:
tmpCorpus.documents = [
doc for doc in tmpCorpus.documents
if any(filterTerm in doc.text.lower()
for filterTerm in filterTerms)
]
tmpCorpus.documents = [
doc for doc in tmpCorpus.documents
if not any(stopword in doc.text.lower() for stopword in stopwords)
]
filtered = []
for doc in tmpCorpus.documents:
if args.mode == 'star_allele':
doc.entities = [
