datastew/CITATION.cff at main · SCAI-BIO/datastew · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
cff-version: 1.2.0
title: datastew
type: software
message: If you use this software, please cite it as below.
license: Apache-2.0
language: en
authors:
  - given-names: Tim
    family-names: Adams
    email: tim.adams@scai.fraunhofer.de
    affiliation: Fraunhofer Institute for Algorithms and Scientific Computing SCAI
    orcid: https://orcid.org/0000-0002-2823-0102
  - given-names: Mehmet Can
    family-names: Ay
    email: mehmet.ay@scai.fraunhofer.de
    affiliation: Fraunhofer Institute for Algorithms and Scientific Computing SCAI
    orcid: https://orcid.org/0000-0002-2977-7695
repository-code: https://github.com/SCAI-BIO/datastew
repository-artifact: https://pypi.org/project/datastew
abstract: >
  Datastew is a Python library for intelligent data harmonization using
  Large Language Model (LLM) vector embeddings.
keywords:
  - data harmonization
  - data stewardship
  - large language models
  - LLM

preferred-citation:
  type: article
  authors:
    - family-names: Salimi
      given-names: Yasamin
    - family-names: Adams
      given-names: Tim
    - family-names: Ay
      given-names: Mehmet Can
    - family-names: Balabin
      given-names: Helena
    - family-names: Jacobs
      given-names: Marc
    - family-names: Hofmann-Apitius
      given-names: Martin
  title: Evaluating language model embeddings for Parkinson’s disease cohort harmonization using a novel manually curated variable mapping schema
  journal: Scientific Reports
  year: 2025
  doi: 10.1038/s41598-025-06447-2

references:
  - type: conference-paper
    title: INDEX — the Intelligent Data Steward Toolbox
    doi: 10.24406/publica-4577
  - type: poster
    title: INDEX — the Intelligent Data Steward Toolbox
    doi: 10.4126/FRL01-006472846