Automating Data Extraction From Scientific Literature and General PDF Files Using Large Language Models and KNIME : An Application in Toxicology
WIREs Computational Molecular Science · 2025-09 · 15 (5)
DOI: 10.1002/wcms.70047 ↗At a glance
Journal article in WIREs Computational Molecular Science, published online on 2025-09-18. Written by José Teófilo Moreira‐Filho and 12 co-authors. Cited 10 times so far (Crossref); 74 references. The full text is freely available (open access, CC BY 4.0).
Abstract (original language)
The large and steadily increasing volume of scientific publications presents a challenge in accessing and utilizing data due to their unstructured nature. Toxicology, in particular, depends on structured data from diverse study types for study evaluation, weight‐of‐evidence chemical assessments, and validation of new approach methodologies (NAMs). Manual data extraction is time and labor‐intensive. This work presents an automated data extraction workflow using large language models (LLMs) within the KNIME platform. The workflow integrates document parsing tools with LLMs to extract variables from scientific publications and general PDF files. Two execution modes are available: text mode and image mode. Text mode applies tools for extracting text and tables, while image mode uses multimodal LLMs to process non‐linear layouts and graphical content. The workflow achieves 81.14% accuracy in text mode for scientific publications and up to 98.54% in image mode for general PDF files. The KNIME platform ensures accessibility through a user‐friendly interface, allowing non‐experts to use advanced data extraction methods. This automated approach facilitates toxicological research by improving the retrieval of structured data. By democratizing access to LLM‐powered workflows, this approach paves the way for significant advancements in knowledge synthesis to support biomedical research. This article is categorized under: Data Science > Artificial Intelligence/Machine Learning Data Science > Computer Algorithms and Programming Data Science > Databases and Expert Systems
Cite
APA
Moreira‐Filho, J. T., Ranganath, D., Tieghi, R. S., Patton, R., Sutherland, V., Schmitt, C., Rooney, A. A., Fostel, J., Walker, V. R., Saddler, T., Reif, D., Mansouri, K., & Kleinstreuer, N. (2025). Automating Data Extraction From Scientific Literature and General PDF Files Using Large Language Models and KNIME : An Application in Toxicology. WIREs Computational Molecular Science, 15(5). https://doi.org/10.1002/wcms.70047
Vancouver
Moreira‐Filho JT, Ranganath D, Tieghi RS, Patton R, Sutherland V, Schmitt C, et al. Automating Data Extraction From Scientific Literature and General PDF Files Using Large Language Models and KNIME : An Application in Toxicology. WIREs Computational Molecular Science. 2025;15(5). doi:10.1002/wcms.70047
BibTeX
@article{MoreiraFilho2025,
author = {Moreira‐Filho, José Teófilo and Ranganath, Dhruv and Tieghi, Ricardo S. and Patton, Robert and Sutherland, Vicki and Schmitt, Charles and Rooney, Andrew A. and Fostel, Jennifer and Walker, Vickie R. and Saddler, Trey and Reif, David and Mansouri, Kamel and Kleinstreuer, Nicole},
title = {Automating Data Extraction From Scientific Literature and General PDF Files Using Large Language Models and KNIME : An Application in Toxicology},
journal = {WIREs Computational Molecular Science},
year = {2025},
volume = {15},
number = {5},
doi = {10.1002/wcms.70047}
}
EUVIMED