Named entity recognition of pharmacokinetic parameters in the scientific literature.

Autor: Gonzalez Hernandez F; Department of Computer Science, University College London, London, UK. ferran.hernandez.17@ucl.ac.uk., Nguyen Q; Institute of Health Informatics, University College London, London, UK., Smith VC; Institute of Health Informatics, University College London, London, UK., Cordero JA; Blanquerna School of Health Sciences, Ramon Llull University, Barcelona, Spain., Ballester MR; Blanquerna School of Health Sciences, Ramon Llull University, Barcelona, Spain.; Institut de Recerca Sant Pau Barcelona, Barcelona, Spain., Duran M; Blanquerna School of Health Sciences, Ramon Llull University, Barcelona, Spain., Solé A; Blanquerna School of Health Sciences, Ramon Llull University, Barcelona, Spain., Chotsiri P; Mahidol Oxford Tropical Medicine Research Unit, Faculty of Tropical Medicine, Mahidol University, Bangkok, Thailand., Wattanakul T; Mahidol Oxford Tropical Medicine Research Unit, Faculty of Tropical Medicine, Mahidol University, Bangkok, Thailand., Mundin G; Department of Computer Science, University College London, London, UK., Lilaonitkul W; Global Business School for Health, University College London, London, UK., Standing JF; Great Ormond Street Institute for Child Health, University College London, London, UK.; Department of Pharmacy, Great Ormond Street Hospital for Children, London, UK., Kloprogge F; Institute for Global Health, University College London, London, UK. f.kloprogge@ucl.ac.uk.
Jazyk: angličtina
Zdroj: Scientific reports [Sci Rep] 2024 Oct 08; Vol. 14 (1), pp. 23485. Date of Electronic Publication: 2024 Oct 08.
DOI: 10.1038/s41598-024-73338-3
Abstrakt: The development of accurate predictions for a new drug's absorption, distribution, metabolism, and excretion profiles in the early stages of drug development is crucial due to high candidate failure rates. The absence of comprehensive, standardised, and updated pharmacokinetic (PK) repositories limits pre-clinical predictions and often requires searching through the scientific literature for PK parameter estimates from similar compounds. While text mining offers promising advancements in automatic PK parameter extraction, accurate Named Entity Recognition (NER) of PK terms remains a bottleneck due to limited resources. This work addresses this gap by introducing novel corpora and language models specifically designed for effective NER of PK parameters. Leveraging active learning approaches, we developed an annotated corpus containing over 4000 entity mentions found across the PK literature on PubMed. To identify the most effective model for PK NER, we fine-tuned and evaluated different NER architectures on our corpus. Fine-tuning BioBERT exhibited the best results, achieving a strict F 1 score of 90.37% in recognising PK parameter mentions, significantly outperforming heuristic approaches and models trained on existing corpora. To accelerate the development of end-to-end PK information extraction pipelines and improve pre-clinical PK predictions, the PK NER models and the labelled corpus were released open source at https://github.com/PKPDAI/PKNER .
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: