linuskohl

#!/usr/bin/perl
#
# Author:         Linus Kohl
# E-Mail:         [email protected]
# Org:            MunichResearch
#
use strict;
use UMLS::Interface;
use UMLS::Similarity::lch;
use UMLS::Similarity::path;

linuskohl

linuskohl

Id,Text
0,It has recently been shown that Craf is essential for Kras G12D-induced NSCLC.
1,"The Bcl-2 inhibitor ABT-737 induces regression of solid tumors  and its derivatives are in the early clinical phase as cancer therapeutics; however, it targets Bcl-2, Bcl-XL, and Bcl-w, but not Mcl-1, which induces resistance against apoptotic cell death triggered by ABT-737."
2,Previous studies demonstrated that the decrease level of 5 hmC in tumors was due to the reduced expression of TET1/2/3 and IDH2 genes or tumor derived IDH1 and IDH2 mutations.
3,"More recently, IDH mutations and resultant 2-hydroxyglutarate (2HG) production in leukemia cells were reported to induce global DNA hypermethylation through impaired TET2 catalytic function."
4,Recent in vitro studies using shRNA-based approaches have suggested a role for TET2 in regulating myeloid differentiation and in regulating stem/progenitor cell proliferation.
5,"Recently, it was reported that expression of IDH1R132H suppresses TET2 activity and the mutations of

linuskohl

import io
import os
import string
import csv
import xml
import re
import unicodedata
import itertools
import requests
from functools import partial

linuskohl

# Load similarities
cui_similarities = pd.read_csv("cui_pairings_out.csv", header=None, names=["cui_0","cui_1","lch","path","wup"])

# Build index for faster access
cui_similarities_reverse = cui_similarities.copy()
cui_similarities_reverse.rename(columns={"cui_0": "cui_1", "cui_1": "cui_0"}, inplace=True)
cui_table = pd.concat([cui_similarities, cui_similarities_reverse], sort=False)
cui_table.set_index(["cui_0","cui_1"], inplace=True)
cui_table = cui_table.sort_index(level='cui_1')
cui_table = cui_table.sort_index()

linuskohl

# Create evaluation DataFrame containing BIOSSES pairings and additional information for evaluation
evaluation = pd.DataFrame(biosses_meta.loc[:,['Text1', 'Text2', 'Avg', 'Var']])
# Add CUI information
evaluation['Text1_CUIs'] = evaluation['Text1'].apply(lambda x: biosses_texts.loc[x,'UMLS_CUIs'])
evaluation['Text2_CUIs'] = evaluation['Text2'].apply(lambda x: biosses_texts.loc[x,'UMLS_CUIs'])
# Add UMLS terms
evaluation['Text1_UMLS_TERMS'] = evaluation['Text1'].apply(lambda x: biosses_texts.loc[x,'UMLS_Terms'])
evaluation['Text2_UMLS_TERMS'] = evaluation['Text2'].apply(lambda x: biosses_texts.loc[x,'UMLS_Terms'])
# Add texts for evaluation purposes
evaluation['Text1'] = evaluation['Text1'].apply(lambda x: biosses_texts.loc[x,'Text'])

linuskohl

[
    {
        "identifier": "sg1153",
        "title": "The Rose Lover",
        "subjects": [
            "adult man",
            "walking, hiking (recreation)",
            "peeping, voyeur",
            "flowers: rose",
            "couple of lovers",