An integrated pharmacokinetics ontology and corpus for text mining

Abstract

BackgroundDrug pharmacokinetics parameters, drug interaction parameters, and pharmacogenetics data have been unevenly collected in different databases and published extensively in the literature. Without appropriate pharmacokinetics ontology and a well annotated pharmacokinetics corpus, it will be difficult to develop text mining tools for pharmacokinetics data collection from the literature and pharmacokinetics data integration from multiple databases.DescriptionA comprehensive pharmacokinetics ontology was constructed. It can annotate all aspects of in vitro pharmacokinetics experiments and in vivo pharmacokinetics studies. It covers all drug metabolism and transportation enzymes. Using our pharmacokinetics ontology, a PK-corpus was constructed to present four classes of pharmacokinetics abstracts: in vivo pharmacokinetics studies, in vivo pharmacogenetic studies, in vivo drug interaction studies, and in vitro drug interaction studies. A novel hierarchical three level annotation scheme was proposed and implemented to tag key terms, drug interaction sentences, and drug interaction pairs. The utility of the pharmacokinetics ontology was demonstrated by annotating three pharmacokinetics studies; and the utility of the PK-corpus was demonstrated by a drug interaction extraction text mining analysis.ConclusionsThe pharmacokinetics ontology annotates both in vitro pharmacokinetics experiments and in vivo pharmacokinetics studies. The PK-corpus is a highly valuable resource for the text mining of pharmacokinetics parameters and drug interactions.

Translational Biomedical Informatics and Pharmacometrics Approaches in the Drug Interactions Research

“…Although many corpora are available, only a few focus on the topic of DDIs . The DDI Corpus 2011 and 2013 were built as reference standards for 2011 and 2013 DDI Extraction Challenges, respectively .…”

“…In addition, the authors further categorized interactions into “increase” and “decrease” classes. The final corpus, called PK corpus, was developed in our group. It was constructed to present four classes of PK abstracts: (1) in vivo PK studies ( n = 56); (2) in vivo pharmacogenetic studies ( n = 57); (3) in vivo DDI studies ( n = 218); and (4) in vitro DDI studies ( n = 210).…”

An analysis on the entity annotations in biological corpora

“…The CellFinder corpus 2 was developed in the scope of the CellFinder database (http://cellfinder.de/) and includes annotations for six entity types (anatomical parts, cell lines, cell types, species and cell components) for 10 full text documents in the stem cell research field. This corpus has been mainly used for the evaluation of named-entity recognition approaches for the above entity types in Neves et al 2,56 .…”

“…When annotating semantic information, a schema is usually composed of some entities (e.g., genes, proteins), and optionally, relationships (e.g., protein-protein interactions, gene-disease relationships). The number of documents may vary from a couple of full text documents 1,2 , to hundreds of abstracts 3 or thousands of sentences 4 .…”

An analysis on the entity annotations in biological corpora

“…Concerning drugs, there are two corpora that do not appear in the article: (a) PK Corpus and PF DDI Corpus 2  with approx. 600 abstracts about clinical pharmacokinetics and pharmacogenetics, in-vitro and in-vivo drug-drug interactions.…”