CEAR: Automatic construction of a knowledge graph of chemical entities and roles from scientific literature

TL;DR

This paper presents CEAR, a method that combines ontological data and large language models to automatically extract chemical entities and roles from scientific literature, creating a comprehensive knowledge graph to enhance existing resources.

Contribution

The paper introduces a novel approach that integrates ontological knowledge with LLMs to automatically construct a chemical knowledge graph from scientific texts.

Findings

High precision and recall in identifying chemical entities and roles

Successful extraction from 8,000 ChemRxiv articles

Extension of existing chemical ontologies with literature-derived data

Abstract

Ontologies are formal representations of knowledge in specific domains that provide a structured framework for organizing and understanding complex information. Creating ontologies, however, is a complex and time-consuming endeavor. ChEBI is a well-known ontology in the field of chemistry, which provides a comprehensive resource for defining chemical entities and their properties. However, it covers only a small fraction of the rapidly growing knowledge in chemistry and does not provide references to the scientific literature. To address this, we propose a methodology that involves augmenting existing annotated text corpora with knowledge from Chebi and fine-tuning a large language model (LLM) to recognize chemical entities and their roles in scientific text. Our experiments demonstrate the effectiveness of our approach. By combining ontological knowledge and the language understanding capabilities of LLMs, we achieve high precision and recall rates in identifying both the chemical entities and roles in scientific literature. Furthermore, we extract them from a set of 8,000 ChemRxiv articles, and apply a second LLM to create a knowledge graph (KG) of chemical entities and roles (CEAR), which provides complementary information to ChEBI, and can help to extend it.