0 votes

Normalization and Matching of Chemical Compound Names

Martin Golebiewski¹, Jasmin Šarić², Henriette Engelken¹, Meik Bittkowski¹, Ulrike Wittig¹, Wolfgang Müller¹ & Isabel Rojas¹

Correspondence: (Login to view email address)

1. EML Research gGmbH, Heidelberg, Germany
2. EML Research gGmbH, Heidelberg, Germany (present address: Boehringer Ingelheim Pharma GmbH & Co. KG, Biberach, Germany)

PPT (2.3 MB) PDF (463 KB)

Document Type:

Poster

Date:

Received 04 June 2009 16:05 UTC; Posted 05 June 2009

Subjects:

Chemistry, Bioinformatics

Tags:

• text mining
• bioinformatics
• chemistry
• biocuration
• Data integration
• Biochemistry
• Cheminformatics

Abstract:

The identification of a chemical compound solely based on its name requires comprehensive chemical knowledge and often extensive searches in chemical databases. However, it is crucial for the integration of biochemical data extracted from the literature, since many publications exclusively describe a compound by its name. We have developed an application which matches synonymic names of chemical compounds and thereby facilitates the bundling of corresponding data referring to the same compound.

The tool that we have developed is based on natural language processing (NLP) methods and applies rules to systematically normalize chemical compound names. Matching of synonymous names is achieved by comparison of the normalized name forms. It is capable of normalizing a given name of a chemical compound and matching it against names in (bio-)chemical databases (e.g. SABIO-RK, ChEBI or PubChem), even when there is no exact name-to-name-match. The tool is also able to match a complete list of compound names against these databases which makes it useful for the automatic annotation of chemical data.

This normalization and matching of various synonyms of a chemical compound constitutes a platform for the unambiguous identification of compounds described in the literature or in databases.

Collection:

3rd International Biocuration Conference

Presented at:

3rd International Biocuration Conference, 16 April 2009

Discussion

Votes:

0 votes

(Login to vote)

Comments:

0 comments

(Login to post a comment)

Share:

(Login to share with a colleague)

Additional information

License:

This document is licensed to the public under the Creative Commons Attribution 3.0 License

How to cite this document:

Golebiewski, Martin, Šarić, Jasmin, Engelken, Henriette, Bittkowski, Meik, Wittig, Ulrike, Müller, Wolfgang, and Rojas, Isabel. Normalization and Matching of Chemical Compound Names. Available from Nature Precedings <http://dx.doi.org/10.1038/npre.2009.3322.1> (2009)

Version info:

Other versions of this document in Nature Precedings

None.

Other versions of this document elsewhere on the web

None known.

Submit a new version link