REPORT - Creating reports or documents often comes with chemical content. Molecules and reactions need to be added with their most important attributes. Static images make the update of the chemical content more difficult than “live” structures, where compound properties are also automatically updated.
FIND - In principal, best decisions can be made if all the available and relevant pieces of information are at our fingertips. However, chemical data exists in many places in multiple forms: It might come from scientific literature, internal reports or patents, stored in systematic or traditional names, various structure formats and images or even identifiers defined in-house.
Chemaxon’s chemical text mining technology offers an automated solution to extract all of the chemical data from various unstructured sources and build an integrated and structured knowledge base from it.
Conversion and Search
Recognition and conversion of chemical identifiers and names (in Chinese or Japanese too) into searchable molecular structures give the backbone of our text mining capabilities. The combination of sophisticated chemical structure search and free text search enable more effective navigation and information retrieval from large-scale document repositories.
Patent curation is a specific case of chemical data mining. Computer-assisted extraction, as well as composition, search and overlap analysis of Markush structures support new compound ideas to remain outside the patented space.
Our text mining solution offers a wide choice to work with the content of your documents, patents and articles within your preferred environment. Our technology can be accessed from desktop or web-based applications and also as an integrated piece in your enterprise software infrastructure. Our chemistry add-on for Microsoft Office enables users to edit structures in-place with dynamic calculation of their phys-chem properties. This is not only available in Excel spreadsheets, but also in Word documents and PowerPoint slides as well.
A user’s story on a successful transition into the modern era: NCK A/S, a small contract research and development org...
ChemAxon's naming technology to accelerate extraction of chemical information from unstructured data
Nowadays, most research activities generate an enormous amount of data. Some might say, an unmanageable amount. Mostl...
Founded in 1978, Questel developed the first ever online patent search service. Today, with premises in Europe, US, a...
Sprint Bioscience develops small molecule medicines, focusing on cancer and tumor metabolism. Using fragment-based me...
Chemistry-enriched patent curation - automatized chemical and semantic analysis and elaboration of large patent sets
Currently, analysis of large patent sets is a tedious and cumbersome work. In order to improve and speed up this proc...
Find the innovation within our tools
Get Connected with ChemAxon
Our solutions can be integrated into a wide variety of software environment, with thousands of features supporting scientists. We can help find the best combination for your R&D.