Deep learning-enabled natural language processing to identify directional pharmacokinetic drug-drug interactions.

Drug Interactions Natural Language Processing Data Mining / methods Deep Learning Language
Directionality Drug-drug interactions Natural language processing Pharmacokinetic Transformer language model

Journal

BMC bioinformatics
ISSN: 1471-2105
Titre abrégé: BMC Bioinformatics
Pays: England
ID NLM: 100965194

Informations de publication

Date de publication:
01 Nov 2023
Historique:
received: 20 03 2023
accepted: 04 10 2023
medline: 3 11 2023
pubmed: 2 11 2023
entrez: 2 11 2023
Statut: epublish

Résumé

During drug development, it is essential to gather information about the change of clinical exposure of a drug (object) due to the pharmacokinetic (PK) drug-drug interactions (DDIs) with another drug (precipitant). While many natural language processing (NLP) methods for DDI have been published, most were designed to evaluate if (and what kind of) DDI relationships exist in the text, without identifying the direction of DDI (object vs. precipitant drug). Here we present a method for the automatic identification of the directionality of a PK DDI from literature or drug labels. We reannotated the Text Analysis Conference (TAC) DDI track 2019 corpus for identifying the direction of a PK DDI and evaluated the performance of a fine-tuned BioBERT model on this task by following the training and validation steps prespecified by TAC. This initial attempt showed the model achieved an F-score of 0.82 in identifying sentences as containing PK DDI and an F-score of 0.97 in identifying object versus precipitant drugs in those sentences. Despite a growing list of NLP methods for DDI extraction, most of them use a common set of corpora to perform general purpose tasks (e.g., classifying a sentence into one of several fixed DDI categories). There is a lack of coordination between the drug development and biomedical informatics method development community to develop corpora and methods to perform specific tasks (e.g., extract clinical exposure changes due to PK DDI). We hope that our effort can encourage such a coordination so that more "fit for purpose" NLP methods could be developed and used to facilitate the drug development process.

Sections du résumé

BACKGROUND BACKGROUND
During drug development, it is essential to gather information about the change of clinical exposure of a drug (object) due to the pharmacokinetic (PK) drug-drug interactions (DDIs) with another drug (precipitant). While many natural language processing (NLP) methods for DDI have been published, most were designed to evaluate if (and what kind of) DDI relationships exist in the text, without identifying the direction of DDI (object vs. precipitant drug). Here we present a method for the automatic identification of the directionality of a PK DDI from literature or drug labels.
METHODS METHODS
We reannotated the Text Analysis Conference (TAC) DDI track 2019 corpus for identifying the direction of a PK DDI and evaluated the performance of a fine-tuned BioBERT model on this task by following the training and validation steps prespecified by TAC.
RESULTS RESULTS
This initial attempt showed the model achieved an F-score of 0.82 in identifying sentences as containing PK DDI and an F-score of 0.97 in identifying object versus precipitant drugs in those sentences.
DISCUSSION AND CONCLUSION CONCLUSIONS
Despite a growing list of NLP methods for DDI extraction, most of them use a common set of corpora to perform general purpose tasks (e.g., classifying a sentence into one of several fixed DDI categories). There is a lack of coordination between the drug development and biomedical informatics method development community to develop corpora and methods to perform specific tasks (e.g., extract clinical exposure changes due to PK DDI). We hope that our effort can encourage such a coordination so that more "fit for purpose" NLP methods could be developed and used to facilitate the drug development process.

Identifiants

DOI: 10.1186/s12859-023-05520-9 PMID: 37914988 PMC: PMC10619324
pubmed: 37914988
doi: 10.1186/s12859-023-05520-9
pii: 10.1186/s12859-023-05520-9
pmc: PMC10619324
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

413

Informations de copyright

© 2023. This is a U.S. Government work and not under copyright protection in the US; foreign copyright protection may apply.

Références

J Am Med Inform Assoc. 2011 Jul-Aug;18(4):441-8
pubmed: 21515544
J Biomed Inform. 2013 Oct;46(5):914-20
pubmed: 23906817
Bioinformatics. 2020 Feb 15;36(4):1234-1240
pubmed: 31501885
CPT Pharmacometrics Syst Pharmacol. 2018 Feb;7(2):90-102
pubmed: 29193890
J Neural Transm (Vienna). 2020 Aug;127(8):1185-1198
pubmed: 32519194
J Biomed Inform. 2020 Jun;106:103451
pubmed: 32454243
Bioinformatics. 2020 Jul 1;36(Suppl_1):i490-i498
pubmed: 32657389
J Biomed Inform. 2014 Oct;51:152-64
pubmed: 24858490
CPT Pharmacometrics Syst Pharmacol. 2019 Jun;8(6):371-379
pubmed: 31044559
N Engl J Med. 1971 Sep 2;285(10):547-58
pubmed: 4397794
Br J Clin Pharmacol. 1999 May;47(5):545-52
pubmed: 10336579

Auteurs

Joel Zirkle (J)

Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA.

Xiaomei Han (X)

Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA.

Rebecca Racz (R)

Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA.

Mohammadreza Samieegohar (M)

Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA.

Anik Chaturbedi (A)

Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA.

John Mann (J)

Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA.

Shilpa Chakravartula (S)

Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA.

Zhihua Li (Z)

Division of Applied Regulatory Science, Office of Clinical Pharmacology, Office of Translational Sciences, Center for Drug Evaluation and Research, Food and Drug Administration, WO Bldg 64 Rm 2078, 10903 New Hampshire Ave, Silver Spring, MD, 20993, USA. Zhihua.li@fda.hhs.gov.

Articles similaires

Exploring structural diversity across the protein universe with The Encyclopedia of Domains.

Andy M Lau, Nicola Bordin, Shaun M Kandathil et al.
1.00
Databases, Protein Protein Domains Protein Folding Proteins Deep Learning

The Importance of Language and Messaging in Psychological Treatment for Functional Neurological Disorder in Children and Adolescents.

Rebecca Laptook
1.00
Humans Child Adolescent Nervous System Diseases Language

The effectiveness of language nursing intervention on mental health in children with poor language skills.

Xi Shu, Yingzi Xiao, Lingzhi Yang
1.00
Humans Male Female Mental Health Child, Preschool

ACL-DUNet: A tumor segmentation method based on multiple attention and densely connected breast ultrasound images.

Hao Zhang, He Liang, Guo Wenjia et al.
1.00
Humans Breast Neoplasms Female Deep Learning Ultrasonography, Mammary

Classifications MeSH

questionsmedicales.fr › Phénomènes physiologiques › Phénomènes pharmacologiques et toxicologiques › Phénomènes pharmacologiques › Interactions médicamenteuses › Deep learning-enabled natural language...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Traitement du langage naturel › Deep learning-enabled natural language...
questionsmedicales.fr › Sciences de l'information › Mémorisation et recherche des informations › Fouille de données › Deep learning-enabled natural language...
questionsmedicales.fr › Sciences de l'information › Méthodologies informatiques › Algorithmes › Intelligence artificielle › Réseaux neuronaux (ordinateur) › Apprentissage profond › Deep learning-enabled natural language...
questionsmedicales.fr › Sciences de l'information › Langage › Deep learning-enabled natural language...