"""
Count drug occurences from input file. Format of said file should be checked.
"""
from utils import File_Reader as FR
from utils import File_Maker as FM
file = FR("../PUBMED_DATA/pubmedNdrugs.latest.txt",
sep='\t',
suppress_newlines=True,
skiplines=0,
encoding="utf-8")
counter = {}
for line in file.iter():
drug = line[3]
drug = drug.split(";")[0]
if drug:
if drug not in counter:
counter[drug] = 1
else:
counter[drug] += 1
print(counter)
print(len(counter))
s = sorted(counter.items(), key=lambda x: x[1])[::-1]
print(s)
'''
Cleaning of the fda database.
Specifically extra trailling spaces and tabs.
'''
from utils import File_Reader as FR
from utils import File_Maker as FM
charstrip = "^[ ]+|[ ]+$"
fda_file = FR("../FDA/FDA_DRUG_DATABASE_cured.txt",
encoding="utf-16",
sep="\t",
strip_chars_pattern=charstrip)
fda = []
for f in fda_file.iter():
fda.append(f[:5])
print(fda)
file = FM("../FDA/FDA_DRUG_DATABASE_cured_cleaned",
data_stream=fda,
extension=".txt")
file.save()
# with open("../FDA/FDA_DRUG_DATABASE_cured_cleaned.latest.txt", 'w', encoding = 'utf-8') as fp:
# for i in fda:
# fp.write("\t".join(i)+'\n')
# Search drugbank for alternative aliases from CIR and Pubchem
alternative_alias_file = FR("../DRUG_LISTS/pcp_cir_newalias.latest.txt",
sep="\t",
suppress_newlines=True,
encoding="utf-8")
drugbank_db_file = FR("../DRUGBANK/drugbank_extracted_identifiers.latest.txt",
skiplines=1,
suppress_newlines=True,
encoding="utf-8")
drugbank = drugbank_db_file.readlines()
count = 0
for new in alternative_alias_file.iter():
key = new[0]
# print(key)
if new[1] or new[2]:
a = ''
if new[1]:
a = new[1].lower().split(";")
b = ''
if new[2]:
b = new[2].lower().split(";")
aliases = []
if a:
aliases.extend(a)
if b:
"""
return re.sub(pattern, '', string)
# Load files and data
print("reading files")
pmid = []
drugs_data = []
drug_data_file = FR("../PUBMED_DATA/pubmedNdrugs_2.txt",
sep='\t',
suppress_newlines=True,
skiplines=0,
encoding="utf-16")
for line in drug_data_file.iter():
pmid.append(line[0])
a = line[1]
if a != "NA" or a != "":
drugs_data.append(a)
# Parse xml file.
print("parsing xml")
tree = ET.parse('../DRUGBANK/drugbank_db.xml')
root = tree.getroot()
# a = [elem for elem in root.findall(get_xpath("by_PMID", keyword = "26242220"))]
# a = [elem for elem in root.findall("./drug[name='Lepirudin']")]
res = []
print("search")
drug_file = FR("../DRUG_LISTS/original_drug_list_2606.txt",
sep="",
suppress_newlines=True,
encoding="utf-8")
modifications_file = FR(
"../DRUG_LISTS/old_pubmed_with_drugs.latest.manually.annotated.txt",
sep="\t",
suppress_newlines=True,
encoding="utf-8",
strip_chars_pattern="^\"|\"$",
skiplines=1)
drugs = []
for line in drug_file.iter():
drugs.append(line)
for line in modifications_file.iter():
current_Drugs = line[3].split("|")
New_alias_identifier = line[5]
Drug_manually_found_in_0drug_titles = line[6]
Alias_to_delete = line[7]
while '' in current_Drugs:
current_Drugs.pop(current_Drugs.index(''))
if Alias_to_delete in drugs and Alias_to_delete:
drugs.pop(drugs.index(Alias_to_delete))
else: