Limits...
Extending the "web of drug identity" with knowledge extracted from United States product labels.

Hassanzadeh O, Zhu Q, Freimuth R, Boyce R - AMIA Jt Summits Transl Sci Proc (2013)

Bottom Line: To help address this issue we created LinkedSPLs, a Linked Data resource that extends the "web of drug identity" using information extracted from SPLs.These mappings were created using three approaches: InChI chemical structure descriptors comparison, exact string matching based on the chemical name, and automatic (unsupervised) linkage identification.Comparison of the approaches found that, while these three approaches are complementary, the automatic approach performs well in terms of precision and recall.

View Article: PubMed Central - PubMed

Affiliation: IBM Research, Yorktown Heights, NY.

ABSTRACT
Structured Product Labels (SPLs) contain information about drugs that can be valuable to clinical and translational research, especially if it can be linked to other sources that provide data about drug targets, chemical properties, interactions, and biological pathways. Unfortunately, SPLs currently provide coarsely-structured drug information and lack the detailed annotation that is required to support computational use cases. To help address this issue we created LinkedSPLs, a Linked Data resource that extends the "web of drug identity" using information extracted from SPLs. In this paper we describe the mapping that LinkedSPLs provides between SPL active ingredients and DrugBank chemical entities. These mappings were created using three approaches: InChI chemical structure descriptors comparison, exact string matching based on the chemical name, and automatic (unsupervised) linkage identification. Comparison of the approaches found that, while these three approaches are complementary, the automatic approach performs well in terms of precision and recall.

No MeSH data available.


An overview of the three mapping methods
© Copyright Policy
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3814463&req=5

f1-amia_tbi_2013_064: An overview of the three mapping methods

Mentions: The SPL for all FDA-approved prescription and OTC drugs were downloaded from the NLM’s DailyMed resource20. Custom scripts were written that load the content of each SPL into a relational database. The active moieties and products present in each SPL were mapped to RxNorm unique identifiers (RxCUIs) through RxNorm ingredient strings and this mapping was added to the database. The relational database was mapped to an RDF knowledge base using a relational to RDF mapper21. The mapping from the relational database to RDF was derived semi-automatically and enhanced based on our design goals, and a final RDF dataset was generated which is hosted on a Virtuoso RDF server (http://virtuoso.openlinksw.com/) that provides SPARQL endpointa. We then tested three approaches to mapping the SPL active ingredients present in LinkedSPLs to DrugBank drugs (Figure 1). All experiments attempted to map active ingredients present in drug products with SPLs in DailyMed as of August 30, 2012 for which we could find preferred terms in the March 2012 version of the FDA UNII table. This helped to avoid attempting to map drugs that were very recently released to the market and thus, might not be listed in DrugBank.


Extending the "web of drug identity" with knowledge extracted from United States product labels.

Hassanzadeh O, Zhu Q, Freimuth R, Boyce R - AMIA Jt Summits Transl Sci Proc (2013)

An overview of the three mapping methods
© Copyright Policy
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3814463&req=5

f1-amia_tbi_2013_064: An overview of the three mapping methods
Mentions: The SPL for all FDA-approved prescription and OTC drugs were downloaded from the NLM’s DailyMed resource20. Custom scripts were written that load the content of each SPL into a relational database. The active moieties and products present in each SPL were mapped to RxNorm unique identifiers (RxCUIs) through RxNorm ingredient strings and this mapping was added to the database. The relational database was mapped to an RDF knowledge base using a relational to RDF mapper21. The mapping from the relational database to RDF was derived semi-automatically and enhanced based on our design goals, and a final RDF dataset was generated which is hosted on a Virtuoso RDF server (http://virtuoso.openlinksw.com/) that provides SPARQL endpointa. We then tested three approaches to mapping the SPL active ingredients present in LinkedSPLs to DrugBank drugs (Figure 1). All experiments attempted to map active ingredients present in drug products with SPLs in DailyMed as of August 30, 2012 for which we could find preferred terms in the March 2012 version of the FDA UNII table. This helped to avoid attempting to map drugs that were very recently released to the market and thus, might not be listed in DrugBank.

Bottom Line: To help address this issue we created LinkedSPLs, a Linked Data resource that extends the "web of drug identity" using information extracted from SPLs.These mappings were created using three approaches: InChI chemical structure descriptors comparison, exact string matching based on the chemical name, and automatic (unsupervised) linkage identification.Comparison of the approaches found that, while these three approaches are complementary, the automatic approach performs well in terms of precision and recall.

View Article: PubMed Central - PubMed

Affiliation: IBM Research, Yorktown Heights, NY.

ABSTRACT
Structured Product Labels (SPLs) contain information about drugs that can be valuable to clinical and translational research, especially if it can be linked to other sources that provide data about drug targets, chemical properties, interactions, and biological pathways. Unfortunately, SPLs currently provide coarsely-structured drug information and lack the detailed annotation that is required to support computational use cases. To help address this issue we created LinkedSPLs, a Linked Data resource that extends the "web of drug identity" using information extracted from SPLs. In this paper we describe the mapping that LinkedSPLs provides between SPL active ingredients and DrugBank chemical entities. These mappings were created using three approaches: InChI chemical structure descriptors comparison, exact string matching based on the chemical name, and automatic (unsupervised) linkage identification. Comparison of the approaches found that, while these three approaches are complementary, the automatic approach performs well in terms of precision and recall.

No MeSH data available.