Named entity recognition of pharmacokinetic parameters in the scientific literature
Open accessAbstract
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 $$F_{1}$$ 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.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Traditional NLP pipelines for automated extraction require task-specific training data and do not generalize to the diverse parameter types in QSP modeling.
“Traditional NLP pipelines for automated extraction require task‐specific training data [11, 12, 13] and do not generalize to the diverse parameter types in QSP modeling.”
From Structured Schemas for Provenance‐Rich, <scp>LLM</scp> ‐Assisted <scp>QSP</scp> Model Calibration (2026) · cites this paper as [13]
The citation is attached to the training-data clause. The Methodology (Corpus construction) says effective NER models for new entity types often require many annotated samples, supporting the need for task-specific data in machine-learning pipelines. But the Methodology (Models) also describes a rule-based pipeline built from expert-written rules, so the paper does not establish that all traditional NLP pipelines require training data. The separate claim about generalizing to QSP parameter types is not addressed by this source. (LLM, conf=0.82)
Experimental — accuracy not yet measuredTraditional NLP pipelines for automated extraction require task-specific training data and do not generalize to the diverse parameter types in QSP modeling.
“Traditional NLP pipelines for automated extraction require task-specific training data11,12,13 and do not generalize to the diverse parameter types in QSP modeling.”
From Structured Schemas for Provenance-Rich, LLM-Assisted QSP Model Calibration (2026) · cites this paper as [13]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741 · see citing works
BioBERT: a pre-trained biomedical language representation model for biomedical text mining
Lee, J., Yoon, W., Kim, S., Kim, D., Kim, S., So, C. H., & Kang, J. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btz682 · Cited by 7,218 · see citing works
Innovation in the pharmaceutical industry: New estimates of R&D costs
DiMasi, J. A., Grabowski, H. G., & Hansen, R. W. (2016) · Journal of Health Economics · doi:10.1016/j.jhealeco.2016.01.012 · Cited by 3,359 · see citing works
HuggingFace's Transformers: State-of-the-art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2019) · arXiv · doi:10.48550/arxiv.1910.03771 · Cited by 3,347 · see citing works
Estimation of clinical trial success rates and related parameters
Wong, C. H., Siah, K. W., & Lo, A. W. (2019) · Biostatistics · doi:10.1093/biostatistics/kxx069 · Cited by 1,585 · see citing works
Agreement, the F-Measure, and Reliability in Information Retrieval
Hripcsak, G. M. (2005) · Journal of the American Medical Informatics Association · doi:10.1197/jamia.m1733 · Cited by 949 · see citing works
ScispaCy: Fast and Robust Models for Biomedical Natural Language Processing
Neumann, M., King, D., Beltagy, I., & Ammar, W. (2019) · BioNLP Workshop and Shared Task (BioNLP) · doi:10.18653/v1/w19-5034 · Cited by 772 · see citing works
Morgan, P., Van Der Graaf, P. H., Arrowsmith, J., Feltner, D. E., Drummond, K. S., Wegner, C. D., & Street, S. D. A. (2012) · Drug Discovery Today · doi:10.1016/j.drudis.2011.12.020 · Cited by 692 · see citing works
Obach, R. S., Lombardo, F., & Waters, N. J. (2008) · Drug Metabolism and Disposition · doi:10.1124/dmd.108.020479 · Cited by 461 · see citing works
Deep Active Learning for Named Entity Recognition
Shen, Y., Yun, H., Lipton, Z. C., Kronrod, Y., & Anandkumar, A. (2017) · Workshop on Representation Learning for NLP (RepL4NLP) · doi:10.18653/v1/w17-2630 · Cited by 389 · see citing works
How much does it cost to research and develop a new drug? A systematic review and assessment
Schlander (2021) · PharmacoEconomics · doi:10.1007/s40273-021-01065-y · Cited by 360 · see citing works
Siddhant, A., & Lipton, Z. C. (2018) · Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1318 · Cited by 239 · see citing works
Multi-criteria-based active learning for named entity recognition
Shen, D., Zhang, J., Su, J., et al. (2004) · Annual Meeting of the Association for Computational Linguistics (ACL) · doi:10.3115/1218955.1219030 · Cited by 234 · see citing works
Extraction of Pharmacokinetic Evidence of Drug–Drug Interactions from the Literature
Kolchinsky, A., Lourenço, A. M. G., Wu, H., Li, L., & Rocha, L. M. (2015) · PLoS ONE · doi:10.1371/journal.pone.0122199 · Cited by 222 · see citing works
Lombardo, F., Berellini, G., & Obach, R. S. (2018) · Drug Metabolism and Disposition · doi:10.1124/dmd.118.082966 · Cited by 176 · see citing works
HunFlair: an easy-to-use tool for state-of-the-art biomedical named entity recognition
Weber, L., Sänger, M., Münchmeyer, J., Habibi, M., Leser, U., & Akbik, A. (2021) · Bioinformatics · doi:10.1093/bioinformatics/btab042 · Cited by 108 · see citing works
Building gold standard corpora for medical natural language processing tasks.
Deléger, L., Li, Q., Lingren, T., Kaiser, M., Molnár, K., Stoutenborough, L., Kouril, M., Marsolo, K. A., & Solti, I. (2012) · PubMed Central · Cited by 79 · see citing works
A comparative study for biomedical named entity recognition
Wang, X., Yang, C., & Guan, R. (2015) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-015-0426-6 · Cited by 66 · see citing works
PK-DB: pharmacokinetics database for individualized and stratified computational modeling
Grzegorzewski, J., Brandhorst, J., Green, K., Eleftheriadou, D., Duport, Y., Barthorscht, F., Köller, A., Ke, D. Y. J., Angelis, S. D., & König, M. (2020) · Nucleic Acids Research · doi:10.1093/nar/gkaa990 · Cited by 60 · see citing works
An integrated pharmacokinetics ontology and corpus for text mining
Wu, H., Karnik, S., Subhadarshini, A., Wang, Z. P., Philips, S., Han, X., Chiang, C., Liu, L., Boustani, M. A., Rocha, L. M., et al. (2013) · BMC Bioinformatics · doi:10.1186/1471-2105-14-35 · Cited by 55 · see citing works
New horizons in drug metabolism, pharmacokinetics and drug discovery.
Palmer, A. M. (2003) · PubMed · Cited by 44 · see citing works
Deep Active Learning for Named Entity RecognitionPreprint
Shen, Y., Yun, H., Lipton, Z. C., et al. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1707.05928 · Cited by 40 · see citing works
Extracting a Knowledge Base of Mechanisms from COVID-19 Papers
Hope, T., Amini, A., Wadden, D., van Zuylen, M., Parasa, S., Horvitz, E., Weld, D. S., Schwartz, R., & Hajishirzi, H. (2021) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2021.naacl-main.355 · Cited by 38 · see citing works
An automated approach to identify scientific publications reporting pharmacokinetic parameters
Hernandez, F. G., Carter, S. J., Iso-Sipilä, J., Goldsmith, P., Almousa, A., Gastine, S., Lilaonitkul, W., Kloprogge, F., & Standing, J. (2021) · Wellcome Open Research · doi:10.12688/wellcomeopenres.16718.1 · Cited by 18 · see citing works
Self-citationMarkup: A Web-Based Annotation Tool Powered by Active Learning
Dobbie, S., Strafford, H., Pickrell, W. O., et al. (2021) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.598916 · Cited by 11 · see citing works
PK-DB: PharmacoKinetics DataBase for Individualized and Stratified Computational ModelingPreprint
Grzegorzewski, J., Brandhorst, J., Eleftheriadou, D., et al. (2019) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/760884 · Cited by 7 · see citing works
Extracting a Knowledge Base of Mechanisms from COVID-19 PapersPreprint
Hope, T., Amini, A., Wadden, D., van Zuylen, M., Parasa, S., Horvitz, E., Weld, D. S., Schwartz, R., & Hajishirzi, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.03824 · Cited by 6 · see citing works
Pharmacokinetic Named Entity Recognition Benchmark
Hernandez, F. G. (2024) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.4646970 · Cited by 2 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805
Flagged first, then by citations
Research works printed but not linked: 2
- [8]Hernandez, F.G. Structuring the Unstructured: Unlocking pharmacokinetic data from journals with Natural Language Processing. PhD thesis, UCL (University College London), (2022).
- [20]Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. Attention is all you need. In Advances in neural information processing systems, pp 5998–6008, (2017).
Cited by
Sorted by citations
Structured Schemas for Provenance-Rich, LLM-Assisted QSP Model Calibration
Eliason, J., & Popel, A. S. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.05.709623
“LLMs can identify relevant litera-56 ture given mechanistic context, read scientific text, and extract information into structured tem-57 plates 14,15,16,17,18 .”
Structured Schemas for Provenance‐Rich, <scp>LLM</scp> ‐Assisted <scp>QSP</scp> Model Calibration
Eliason, J., & Popel, A. S. (2026) · CPT: Pharmacometrics & Systems Pharmacology · doi:10.1002/psp4.70306
- Authors
- Gonzalez Hernandez, F., Nguyen, Q., Smith, V. C., Cordero, J. A., Ballester, M. R., Duran, M., Solé, A., Chotsiri, P., Wattanakul, T., Mundin, G., Lilaonitkul, W., Standing, J. F., & Kloprogge, F.
- Affiliations
- University College London (GB)
- Universitat Ramon Llull (ES)
- Mahidol University (TH)
- Great Ormond Street Hospital (GB)
- Corresponding author
- Kloprogge, Frank
- ORCID
- Venue
- Scientific Reports
- Published
- 2024-10-08
- Volume
- 14
- Issue
- 1
- Pages
- 23485-23485
- ISSN
- 2045-2322 (ISSN-L)
- PMC
- PMC11461509
- OpenAlex
- W4403217785
- Cited by
- 8
- References
- 29
- Citations by year
- 2026: 3 · 2025: 5
- FWCI
- 1.09
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Scientific Reports (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- UCL Graduate Research Scholarship
- UKRI UCL CDT in AI-enabled Healthcare Systems
- Wellcome Trust (214464)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Biomedical Text Mining and Ontologies
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Computational Theory and Mathematics › Computational Drug Discovery Methods
- Keywords
- named entity recognition, pharmacokinetic parameters, annotated corpus, BioBERT, text mining, information extraction, drug development, PubMed
- MeSH terms
- Humans, Natural Language Processing, Pharmacokinetics, Data Mining
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
