ICANNOTATOR

ICANNOTATOR enables extraction of chemically relevant entities from unstructured text sources. It recognizes and extracts systematic names, and trivial and trade names, as well as standard identifiers such as InChI's or CAS Registry Numbers.

ICANNOTATOR is our high performance named entity recognition engine containing over 32 million Chemistry terms specifically designed for chemical text mining and semantic enrichment. No matter if you have native Chinese, Japanese, Korean or Russian documents; the program is capable of extracting chemical names, fragments or substance classes. Furthermore it can tag other chemical related terms like polymers and materials as well as biochemical concepts like gene and protein names.

Mining for Chemistry: Your tailor-made solution

Thanks to the modular software concept, InfoChem is able to offer highly customized solutions for the extraction of chemical content from legacy data, patents and company internal repositories. In a Mining for Chemistry project we identify the most relevant data sources and define with the customer specific objectives. Additionally, we can evaluate and accomplish integration of the generated content into existing chemical information systems or help setting up a new infrastructure. We place great emphasis on high quality and strict chemical validation, obtained applying cutting edge chemoinformatics tools for the verification of the generated data.

CONTACT US

FOR MORE INFORMATION

Contact us

We also offer additional modules for ICANNOTATOR:

Extensions - enabling extraction of different entities in multiple languages.

Images Workup - 30 years skills and expertise in the field of structure and reaction handling enable us to offer high performant processes for the generation of structure and reaction databases from images and ChemDraw files.

Database Building - If you need to generate high quality structure and/or reaction databases contact us!
We offer manual and automatic abstraction of chemical data from any kind of literature and build structure and reaction databases for your individual needs.