Related Experiment Video
Updated: May 23, 2025

12:13
Rapid Identification of Chemical Genetic Interactions in Saccharomyces cerevisiae
Published on: April 5, 2015
10.3K
Yeast Knowledge Graphs Database for Exploring Saccharomyces Cerevisiae and Schizosaccharomyces Pombe
Mani R Kumar1, Karthick Raja Arulprakasam1, An-Nikol Kutevska1
1School of Biological Sciences, Nanyang Technological University, 60 Nanyang Drive, Singapore 637551 Singapore.
Journal of Molecular Biology
|March 8, 2025
Summary
This study introduces an AI pipeline to extract gene function data from scientific papers, creating searchable knowledge graphs for yeast species. This facilitates efficient biological data discovery and analysis.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- Biomedical literature is rich in gene and protein function data but difficult to access and analyze.
- Extracting specific biological insights from vast datasets presents significant challenges.
Purpose of the Study:
- To develop a high-throughput pipeline using artificial intelligence (AI) to automate gene function information extraction.
- To create searchable online knowledge graphs for Saccharomyces cerevisiae and Schizosaccharomyces pombe.
Main Methods:
- Leveraged OpenAI's Generative Pre-Trained Transformer Model (GPT) for automated data extraction.
- Applied the pipeline to analyze 84,427 publications for S. cerevisiae and 6,452 for S. pombe.
- Integrated extracted data into comprehensive, searchable online Knowledge Graph databases.
Main Results:
- Identified 3,432,749 gene-protein relationships for S. cerevisiae.
- Identified 421,198 gene-protein relationships for S. pombe.
- Developed accessible online resources: yeast.connectome.tools and spombe.connectome.tools.
Conclusions:
- AI-driven bioinformatics pipelines can efficiently extract and analyze complex biological data.
- The developed knowledge graphs provide extensive access to yeast interactions and pathways.
- This approach offers a scalable model for gene function analysis in other biological systems.

