Annotation of biological samples data to standard ontologies with support from large language models

The semantic integration of biological data is hindered by the vast heterogeneity of data sources and their limited semantic formalization. A crucial step in this process is mapping data elements to ontological concepts, which typically involves substantial manual effort. Large Language Models (LLMs...

Full description

Saved in:
Bibliographic Details
Main Authors: Andrea Riquelme-García, Juan Mulero-Hernández, Jesualdo Tomás Fernández-Breis
Format: Article
Language:English
Published: Elsevier 2025-01-01
Series:Computational and Structural Biotechnology Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2001037025001837
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849688733300817920
author Andrea Riquelme-García
Juan Mulero-Hernández
Jesualdo Tomás Fernández-Breis
author_facet Andrea Riquelme-García
Juan Mulero-Hernández
Jesualdo Tomás Fernández-Breis
author_sort Andrea Riquelme-García
collection DOAJ
description The semantic integration of biological data is hindered by the vast heterogeneity of data sources and their limited semantic formalization. A crucial step in this process is mapping data elements to ontological concepts, which typically involves substantial manual effort. Large Language Models (LLMs) have demonstrated potential in automating complex language-related tasks and may offer a solution to streamline biological data annotation. This study investigates the utility of LLMs—specifically various base and fine-tuned GPT models—for the automatic assignment of ontological identifiers to biological sample labels. We evaluated model performance in annotating labels to four widely used ontologies: the Cell Line Ontology (CLO), Cell Ontology (CL), Uber-anatomy Ontology (UBERON), and BRENDA Tissue Ontology (BTO). Our dataset was compiled from publicly available, high-quality databases containing biologically relevant sequence information, which suffers from inconsistent annotation practices, complicating integrative analyses. Model outputs were compared against annotations generated by text2term, a state-of-the-art annotation tool. The fine-tuned GPT model outperformed both the base models and text2term in annotating cell lines and cell types, particularly for the CL and UBERON ontologies, achieving a precision of 47–64% and a recall of 88–97%. In contrast, base models exhibited significantly lower performance. These results suggest that fine-tuned LLMs can accelerate and improve the accuracy of biological data annotation. Nonetheless, our evaluation highlights persistent challenges, including variable precision across ontology categories and the continued need for expert curation to ensure annotation validity.
format Article
id doaj-art-bd00bad2e2564212a0980ab7e45c19dd
institution DOAJ
issn 2001-0370
language English
publishDate 2025-01-01
publisher Elsevier
record_format Article
series Computational and Structural Biotechnology Journal
spelling doaj-art-bd00bad2e2564212a0980ab7e45c19dd2025-08-20T03:21:51ZengElsevierComputational and Structural Biotechnology Journal2001-03702025-01-01272155216710.1016/j.csbj.2025.05.020Annotation of biological samples data to standard ontologies with support from large language modelsAndrea Riquelme-García0Juan Mulero-Hernández1Jesualdo Tomás Fernández-Breis2Departamento de Informática y Sistemas, Universidad de Murcia, CEIR Campus Mare Nostrum, IMIB-Pascual Parrilla, Murcia, 30100, SpainDepartamento de Informática y Sistemas, Universidad de Murcia, CEIR Campus Mare Nostrum, IMIB-Pascual Parrilla, Murcia, 30100, SpainCorresponding author.; Departamento de Informática y Sistemas, Universidad de Murcia, CEIR Campus Mare Nostrum, IMIB-Pascual Parrilla, Murcia, 30100, SpainThe semantic integration of biological data is hindered by the vast heterogeneity of data sources and their limited semantic formalization. A crucial step in this process is mapping data elements to ontological concepts, which typically involves substantial manual effort. Large Language Models (LLMs) have demonstrated potential in automating complex language-related tasks and may offer a solution to streamline biological data annotation. This study investigates the utility of LLMs—specifically various base and fine-tuned GPT models—for the automatic assignment of ontological identifiers to biological sample labels. We evaluated model performance in annotating labels to four widely used ontologies: the Cell Line Ontology (CLO), Cell Ontology (CL), Uber-anatomy Ontology (UBERON), and BRENDA Tissue Ontology (BTO). Our dataset was compiled from publicly available, high-quality databases containing biologically relevant sequence information, which suffers from inconsistent annotation practices, complicating integrative analyses. Model outputs were compared against annotations generated by text2term, a state-of-the-art annotation tool. The fine-tuned GPT model outperformed both the base models and text2term in annotating cell lines and cell types, particularly for the CL and UBERON ontologies, achieving a precision of 47–64% and a recall of 88–97%. In contrast, base models exhibited significantly lower performance. These results suggest that fine-tuned LLMs can accelerate and improve the accuracy of biological data annotation. Nonetheless, our evaluation highlights persistent challenges, including variable precision across ontology categories and the continued need for expert curation to ensure annotation validity.http://www.sciencedirect.com/science/article/pii/S2001037025001837BioinformaticsGenerative AILarge language modelsData interoperabilityBiological samples
spellingShingle Andrea Riquelme-García
Juan Mulero-Hernández
Jesualdo Tomás Fernández-Breis
Annotation of biological samples data to standard ontologies with support from large language models
Computational and Structural Biotechnology Journal
Bioinformatics
Generative AI
Large language models
Data interoperability
Biological samples
title Annotation of biological samples data to standard ontologies with support from large language models
title_full Annotation of biological samples data to standard ontologies with support from large language models
title_fullStr Annotation of biological samples data to standard ontologies with support from large language models
title_full_unstemmed Annotation of biological samples data to standard ontologies with support from large language models
title_short Annotation of biological samples data to standard ontologies with support from large language models
title_sort annotation of biological samples data to standard ontologies with support from large language models
topic Bioinformatics
Generative AI
Large language models
Data interoperability
Biological samples
url http://www.sciencedirect.com/science/article/pii/S2001037025001837
work_keys_str_mv AT andreariquelmegarcia annotationofbiologicalsamplesdatatostandardontologieswithsupportfromlargelanguagemodels
AT juanmulerohernandez annotationofbiologicalsamplesdatatostandardontologieswithsupportfromlargelanguagemodels
AT jesualdotomasfernandezbreis annotationofbiologicalsamplesdatatostandardontologieswithsupportfromlargelanguagemodels