Elsevier MDL and TEMIS, a provider of Text Mining solutions have announced that they have co-developed the Chemical Entity Relationship Skill Cartridge, a new software application that identifies and extracts chemical information from text documents.
The software identifies chemical compound names, chemical classes and molecular formulae in text documents and translates extracted information into the chemist's language: the chemical structure. Features include: Classification and relevance weighting--identified chemical terms are assigned to specific chemical concepts according to semantic categories such as regular chemical name, chemical class name, trivial name, etc.; name-to-structure translation--an elaborated name-to-structure translation service enables the user to automatically match textual information with proprietary chemical libraries; and unique identification--for each identified structure, a unique fingerprint is provided for de-duplication purposes.
The Chemical Entity Relationship Skill Cartridge integrates the Chemical Name Recognition software developed and used by Elsevier MDL to identify chemical names and extract reaction schemes from scientific literature and patents. This Chemical Name Recognition software has proven its robustness and high-quality extraction capabilities for more than two years in the production of the MDL Patent Chemistry Database backfile. Under the terms of the agreement, TEMIS is the exclusive channel of the Chemical Entity Relationship Skill Cartridge.
(www.elsevier.com; www.mdl.com; www.temis.com)