textToKnowledgeGraph: Generation of Molecular Interaction Knowledge Graphs Using Large Language Models for...

Area of Science:

• Bioinformatics
• Computational Biology
• Natural Language Processing

Background:

• Knowledge graphs (KGs) are vital for biological data analysis but manual construction from literature is resource-intensive.
• Existing text-mining tools struggle with contextual understanding and inferring complex biological relationships.
• Large Language Models (LLMs) offer enhanced contextual knowledge for more accurate information extraction.

Purpose of the Study:

• To develop an automated method for extracting biological interactions from unstructured text.
• To represent extracted relationships in the structured Biological Expression Language (BEL) format.
• To overcome limitations of traditional text-mining approaches in capturing complex biological context.

Main Methods:

• Utilized Large Language Models (LLMs) for advanced text understanding and relationship extraction.
• Developed the open-source Python package textToKnowledgeGraph for automated BEL extraction.
• Integrated an interactive application within Cytoscape Web for simplified extraction and exploration.

Main Results:

• Successfully extracted biological interactions from scientific articles into BEL format.
• Created an open-source tool and an interactive application for knowledge graph construction.
• Generated a reviewed dataset to facilitate future advancements in automated biological knowledge extraction.

Conclusions:

• LLM-powered textToKnowledgeGraph effectively automates the extraction of biological relationships.
• The developed tool and dataset lower barriers to creating structured biological knowledge graphs.
• This approach enhances the accessibility and utility of biological literature for computational analysis.