def LF_DEBUG(c):
"""
This label function is for debugging purposes. Feel free to ignore.
keyword arguments:
c - The candidate object to be labeled
"""
print(c)
print()
print("Left Tokens")
print(list(get_left_tokens(c[0], window=5)))
print()
print("Right Tokens")
print(list(get_right_tokens(c[0])))
print()
print("Between Tokens")
print(list(get_between_tokens(c)))
print()
print("Tagged Text")
print(get_tagged_text(c))
print(re.search(r'{{B}} .* is a .* {{A}}', get_tagged_text(c)))
print()
print("Get between Text")
print(get_text_between(c))
print(len(get_text_between(c)))
print()
print("Parent Text")
print(c.get_parent())
print()
return 0
def LF_abbreviation(c):
"""
IF {{B}}} {{A}} or vice versa then not a valid relationship
"""
if len(get_text_between(c)) < 3:
return -1
return 0
def LF_GiG_REGULATION(c):
if LF_GiG_UPREGULATES(c) or LF_GiG_DOWNREGULATES(c):
return -1
elif re.search(ltp(regulation_identifiers), get_text_between(c), flags=re.I):
return -1
else:
return 0
def LF_GiG_ASSOCIATION(c):
if re.search(ltp(association_identifiers), " ".join(get_right_tokens(c[0], window=2)), flags=re.I):
return -1
elif re.search(ltp(association_identifiers), " ".join(get_right_tokens(c[1], window=2)), flags=re.I):
return -1
elif re.search(ltp(association_identifiers), get_text_between(c), flags=re.I):
return -1
else:
return 0
def LF_GiG_DOWNREGULATES(c):
if re.search(ltp(downregulates_identifiers), " ".join(get_right_tokens(c[0], window=2)), flags=re.I):
return -1
elif re.search(ltp(downregulates_identifiers), " ".join(get_right_tokens(c[1], window=2)), flags=re.I):
return -1
elif re.search(ltp(downregulates_identifiers), get_text_between(c), flags=re.I):
return -1
else:
return 0
def LF_GiG_COMPOUND_IDENTIFICATIONS(c):
if re.search(ltp(compound_indications), " ".join(get_right_tokens(c[0], window=2)), flags=re.I):
return -1
elif re.search(ltp(compound_indications), " ".join(get_right_tokens(c[1], window=2)), flags=re.I):
return -1
elif re.search(ltp(compound_indications), get_text_between(c), flags=re.I):
return -1
else:
return 0
def LF_CG_WEAK_BINDING(c):
"""
This label function is designed to look for phrases
that could imply a compound binding to a gene/protein
"""
if re.search(ltp(weak_binding_indications), get_text_between(c), flags=re.I):
return 1
else:
return 0
def LF_CD_TREATS(c):
if re.search(ltp(treat_indication), get_text_between(c), flags=re.I):
return 1
elif re.search(ltp(treat_indication), " ".join(get_left_tokens(c[0], window=5)), flags=re.I):
return 1
elif re.search(ltp(treat_indication), " ".join(get_right_tokens(c[0], window=5)), flags=re.I):
return 1
else:
return 0
def LF_CG_UPREGULATES(c):
"""
This label function is designed to look for phrases
that implies a compound increaseing activity of a gene/protein
"""
if re.search(ltp(upregulates), get_text_between(c), flags=re.I):
return 1
elif upregulates.intersection(get_left_tokens(c[1], window=2)):
return 1
else:
return 0
def LF_CG_DOWNREGULATES(c):
"""
This label function is designed to look for phrases
that could implies a compound decreasing the activity of a gene/protein
"""
if re.search(ltp(downregulates), get_text_between(c), flags=re.I):
return 1
elif downregulates.intersection(get_right_tokens(c[1], window=2)):
return 1
else:
return 0
def LF_GiG_BINDING_IDENTIFICATIONS(c):
gene1_tokens = list(get_left_tokens(c[0], window=5)) + list(get_right_tokens(c[0], window=5))
gene2_tokens = list(get_left_tokens(c[0], window=5)) + list(get_right_tokens(c[0], window=5))
if re.search(ltp(binding_identifiers), " ".join(gene1_tokens), flags=re.I):
return 1
elif re.search(ltp(binding_identifiers), " ".join(gene2_tokens), flags=re.I):
return 1
elif re.search(ltp(binding_identifiers), get_text_between(c), flags=re.I):
return 1
else:
return 0
def LF_CD_PALLIATES(c):
"""
This label function is designed to look for phrases
that could imply a compound binding to a gene/protein
"""
if re.search(ltp(palliates_indication), get_text_between(c), flags=re.I):
return 1
elif re.search(ltp(palliates_indication), " ".join(get_left_tokens(c[0], window=5)), flags=re.I):
return 1
elif re.search(ltp(palliates_indication), " ".join(get_right_tokens(c[0], window=5)), flags=re.I):
return 1
else:
return 0
def LF_CD_WEAKLY_TREATS(c):
"""
This label function is designed to look for phrases
that imply a compound binding to a gene/protein
"""
if re.search(ltp(weak_treatment_indications), get_text_between(c), flags=re.I):
return 1
elif re.search(ltp(weak_treatment_indications), " ".join(get_left_tokens(c[0], window=5)), flags=re.I):
return 1
elif re.search(ltp(weak_treatment_indications), " ".join(get_right_tokens(c[0], window=5)), flags=re.I):
return 1
else:
return 0
def LF_DEBUG(C):
print "Left Tokens"
print get_left_tokens(c, window=3)
print
print "Right Tokens"
print get_right_tokens(c)
print
print "Between Tokens"
print get_between_tokens(c)
print
print "Tagged Text"
print get_tagged_text(c)
print re.search(r'{{B}} .* is a .* {{A}}', get_tagged_text(c))
print
print "Get between Text"
print get_text_between(c)
print len(get_text_between(c))
print
print "Parent Text"
print c.get_parent()
print
return 0
def LF_CD_COMPOUND_INDICATION(c):
"""
This label function is designed to look for phrases
that implies a compound increaseing activity of a gene/protein
"""
if re.search(ltp(compound_indications), get_text_between(c), flags=re.I):
return 1
elif re.search(ltp(compound_indications), " ".join(get_left_tokens(c[0], window=5)), flags=re.I):
return 1
elif re.search(ltp(compound_indications), " ".join(get_right_tokens(c[0], window=5)), flags=re.I):
return 1
else:
return 0
def LF_DG_GENETIC_ABNORMALITIES(c):
"""
This LF searches for key phraes that indicate a genetic abnormality
"""
left_window = " ".join(get_left_tokens(c[0], window=10)) + " ".join(get_left_tokens(c[1], window=10))
right_window = " ".join(get_right_tokens(c[0], window=10)) + " ".join(get_right_tokens(c[1], window=10))
if re.search(ltp(genetic_abnormalities), get_text_between(c), flags=re.I):
return 1
elif re.search(ltp(genetic_abnormalities), left_window, flags=re.I):
return 1
elif re.search(ltp(genetic_abnormalities), right_window, flags=re.I):
return 1
return 0
def LF_DG_WEAK_ASSOCIATION(c):
"""
This label function is design to search for phrases that indicate a
weak association between the disease and gene
"""
if re.search(ltp(weak_association), get_text_between(c), flags=re.I):
return -1
elif re.search(ltp(weak_association) + r".*({{B}}|{{A}})",
get_tagged_text(c),
flags=re.I):
return -1
elif re.search(r"({{B}}|{{A}}).*" + ltp(weak_association),
get_tagged_text(c),
flags=re.I):
return -1
else:
return 0
def LF_DG_NO_ASSOCIATION(c):
"""
This LF is designed to test if there is a key phrase that suggests
a d-g pair is no an association.
"""
if re.search(ltp(no_direct_association), get_text_between(c), flags=re.I):
return -1
elif re.search(ltp(no_direct_association) + r".*({{B}}|{{A}})",
get_tagged_text(c),
flags=re.I):
return -1
elif re.search(r"({{B}}|{{A}}).*" + ltp(no_direct_association),
get_tagged_text(c),
flags=re.I):
return -1
else:
return 0
def _get_search_func(self, c):
"""
Enumerate the token search space for pattern matching
:param c:
:return:
"""
if self.search == "sentence":
return c.get_parent().__dict__[self.attrib]
elif self.search == "between":
return get_text_between(c).strip().split()
elif self.search == "left":
# use left-most Span
span = c[0] if c[0].char_start < c[1].char_start else c[1]
return get_left_tokens(span, window=self.window, attrib=self.attrib)
elif self.search == "right":
# use right-most Span
span = c[0] if c[0].char_start > c[1].char_start else c[1]
return get_right_tokens(span, window=self.window, attrib=self.attrib)
def LF_DaG_NO_ASSOCIATION(c):
"""
This LF is designed to test if there is a key phrase that suggests
a d-g pair is no an association.
"""
left_window = " ".join(get_left_tokens(c[0], window=10)) + " ".join(get_left_tokens(c[1], window=10))
right_window = " ".join(get_right_tokens(c[0], window=10)) + " ".join(get_right_tokens(c[1], window=10))
if LF_DG_METHOD_DESC(c) or LF_DG_TITLE(c):
return 0
elif re.search(ltp(no_direct_association), get_text_between(c), flags=re.I):
return -1
elif re.search(ltp(no_direct_association), left_window, flags=re.I):
return -1
elif re.search(ltp(no_direct_association), right_window, flags=re.I):
return -1
else:
return 0
def LF_DaG_WEAK_ASSOCIATION(c):
"""
This label function is design to search for phrases that indicate a
weak association between the disease and gene
"""
left_window = " ".join(get_left_tokens(c[0], window=10)) + " ".join(get_left_tokens(c[1], window=10))
right_window = " ".join(get_right_tokens(c[0], window=10)) + " ".join(get_right_tokens(c[1], window=10))
if LF_DG_METHOD_DESC(c) or LF_DG_TITLE(c):
return 0
elif re.search(ltp(weak_association), get_text_between(c), flags=re.I):
return 1
elif re.search(ltp(weak_association), left_window, flags=re.I):
return 1
elif re.search(ltp(weak_association), right_window, flags=re.I):
return 1
else:
return 0
def _get_search_func(self, c):
"""
Enumerate the token search space for pattern matching
:param c:
:return:
"""
if self.search == "sentence":
return c.get_parent().__dict__[self.attrib]
elif self.search == "between":
return get_text_between(c).strip().split()
elif self.search == "left":
# use left-most Span
span = c[0] if c[0].char_start < c[1].char_start else c[1]
return get_left_tokens(span, window=self.window, attrib=self.attrib)
elif self.search == "right":
# use right-most Span
span = c[0] if c[0].char_start > c[1].char_start else c[1]
return get_right_tokens(span, window=self.window, attrib=self.attrib)
def LF_DaG_ASSOCIATION(c):
"""
This LF is designed to test if there is a key phrase that suggests
a d-g pair is an association.
"""
left_window = " ".join(get_left_tokens(c[0], window=10)) + " ".join(get_left_tokens(c[1], window=10))
right_window = " ".join(get_right_tokens(c[0], window=10)) + " ".join(get_right_tokens(c[1], window=10))
found_negation = not re.search(r'\b(not|no)\b', left_window, flags=re.I)
if LF_DG_METHOD_DESC(c) or LF_DG_TITLE(c):
return 0
elif re.search(r'(?<!not )(?<!no )' + ltp(direct_association), get_text_between(c), flags=re.I) and found_negation:
return 1
elif re.search(r'(?<!not )(?<!no )' + ltp(direct_association), left_window, flags=re.I) and found_negation:
return 1
elif re.search(r'(?<!not )(?<!no )' + ltp(direct_association), right_window, flags=re.I) and found_negation:
return 1
else:
return 0
def LF_CtD_WEAKLY_TREATS(c):
"""
This label function is designed to look for phrases
that have a weak implication towards a compound treating a disease
"""
if re.search(ltp(weak_treatment_indications),
get_text_between(c),
flags=re.I):
return 1
elif re.search(ltp(weak_treatment_indications),
" ".join(get_left_tokens(c[0], window=5)),
flags=re.I):
return 1
elif re.search(ltp(weak_treatment_indications),
" ".join(get_right_tokens(c[0], window=5)),
flags=re.I):
return 1
else:
return 0
def LF_DaG_ASSOCIATION(c):
"""
This LF is designed to test if there is a key phrase that suggests
a d-g pair is an association.
"""
if LF_DG_METHOD_DESC(c) or LF_DG_TITLE(c):
return 0
elif re.search(r'(?<!not )(?<!no )' + ltp(direct_association),
get_text_between(c),
flags=re.I):
return 1
elif re.search(r'(?<!not )(?<!no )' + ltp(direct_association) +
r".*({{B}}|{{A}})",
get_tagged_text(c),
flags=re.I):
return 1
elif re.search(r"({{B}}|{{A}}).*(?<!not )(?<!no )" +
ltp(direct_association),
get_tagged_text(c),
flags=re.I):
return 1
else:
return 0
def LF_DG_CONTEXT_SWITCH(c):
if re.search(ltp(context_change_keywords), get_text_between(c), flags=re.I):
return -1
return 0
def LF_GiG_DIAGNOSIS_IDENTIFIERS(c):
if re.search(ltp(diagnosis_indication), get_text_between(c), flags=re.I):
return -1
else:
return 0
def LF_NO_ASSOCIATION(c):
"""
This LF is designed to test if there is a key phrase that suggests
a d-g pair is no an association.
"""
return -1 if re.search(ltp(direct_assocation_complement), get_text_between(candidate), re.I) return 0