# drugs_file = FR("../PUBMED_DATA/drugbank2606.latest.txt",
# sep = "\t", suppress_newlines = True, encoding = "utf-8", skiplines = 0)
fda_file = FR("../FDA/FDA_DATABASE_2018_07.txt",
sep = "", suppress_newlines = True, encoding = "CP1252", skiplines = 1)
strippattern = "^\"|\"$|^ +| +$"
fda_file2 = FR("../FDA/FDA_DATABASE_2018_07.txt",
sep = "\t", suppress_newlines = True, encoding = "CP1252", skiplines = 0, strip_chars_pattern = strippattern)
# fda_dict = fda_file.as_dict(lines_askeys = True)
fda_lines = fda_file.readlines()
fda_dict = fda_file2.as_dict(lines_askeys = True)
header,drugs_dict = drugs_file.as_dict(ret_header = True)
fda_cols_retained = ["SubmissionStatusDate", "SubmissionStatus", "SponsorName", "ActiveIngredient"]
app = "FDA_"
header.append("HAS_FDA_ENTRY")
for col in fda_cols_retained:
header.append(app+col)
for key in drugs_dict.keys():
# alias = ";".join([drugs_dict[key]["COMMON_DRUGBANK_ALIAS"],
# drugs_dict[key]["MINED_ALIAS"]]) if drugs_dict[key]["MINED_ALIAS"] else drugs_dict[key]["COMMON_DRUGBANK_ALIAS"]
alias = drugs_dict[key]["COMMON_DRUGBANK_ALIAS"]
found_indexes = []
for line in fda_lines:
# if alias.lower() in line.lower():
if any([a.lower() in line.lower() for a in alias.split(";")]):
found_indexes.append(fda_lines.index(line))
from utils import File_Reader as FR
drugbank_alias_file = FR("../PUBMED_DATA/drugbank2606.latest.txt",
sep="\t",
suppress_newlines=True,
encoding="utf-8",
skiplines=0)
drugbank_dict = drugbank_alias_file.as_dict()
drugbank_names = [key for key in drugbank_dict.keys()]
drugbank_names.sort()
for k in drugbank_names:
print(k)