Related Experiment Video
Updated: Jun 9, 2025

07:35
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
Published on: October 13, 2023
1.6K
Automatic Detection and Extraction of Key Resources from Tables in Biomedical Papers.
Ibrahim Burak Ozyurt1, Anita Bandrowski1
1FDI Lab, University of California, San Diego, 9500 Gilman Drive, M/C 0608, La Jolla, CA 92093-0608, USA.
Biorxiv : the Preprint Server for Biology
|October 28, 2024
Summary
Researchers developed automated tools to extract key resource tables from BioRxiv preprints. This improves the findability of essential research materials like antibodies and cell lines across the biomedical literature.
Area of Science:
- Biomedical Informatics
- Computational Biology
- Scientific Publishing
Background:
- Tables are crucial for identifying research resources and reagents.
- STAR*Methods tables enhance resource findability but are limited in scope.
- Automating table extraction from preprints can broaden resource discoverability.
Purpose of the Study:
- To develop automated methods for extracting and structuring key resource tables from BioRxiv preprints.
- To improve the findability of research resources in the broader biomedical literature.
Main Methods:
- Utilized multimodal pipelines with machine learning for page identification.
- Employed Table Transformer models for table detection and structure recognition.
- Developed a novel language model for row over-segmentation to enhance text extraction.
Main Results:
- Achieved a Grid Table Similarity (GriTS) score of approximately 0.90, a significant improvement from 0.12.
- Successfully automated the extraction of key resource tables from PDF preprints.
Conclusions:
- The developed automated tools enable effective extraction of research resource tables from BioRxiv.
- This advancement facilitates improved findability of critical scientific inputs across a larger corpus of literature.
More Related Videos
Related Concept Videos
Protein Networks
3.9K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
3.9K
Western Blotting
15.1K
Western blotting is an analytical technique for protein identification. It has various applications in immunology and medicine, including detecting diseases like bovine spongiform encephalopathy, mad cow disease, and human and feline immunodeficiency virus from biological samples.
The technique begins with separating proteins from the sample using sodium dodecyl sulfate-polyacrylamide gel electrophoresis (SDS-PAGE), followed by protein transfer, immunoblotting, and finally, protein detection.
The technique begins with separating proteins from the sample using sodium dodecyl sulfate-polyacrylamide gel electrophoresis (SDS-PAGE), followed by protein transfer, immunoblotting, and finally, protein detection.
15.1K

