Chemistry Text Mining Suite

Naming allows the user to generate IUPAC names and traditional names from structures, or CAS registry numbers via Web service. Radicals, natural products, and peptide sequences are also supported.

Various types of chemical names can be converted to structures with Naming, including IUPAC names, systematic names, common names, drug commercial names, and CAS names. CAS registry number is also supported via Web service.

To accommodate the fast growing scientific literature in Asian languages, ChemAxon has released Chinese Name to Structure (CN2S) conversion since version 5.12. Japanese support is now available with version 6.3.

The core application is Document to Structure. Not only supporting all types of documents, it also applies text OCR and image OSR technologies to extract information from non-searchable PDF documents (e.g. chemical patents). Once structures are extracted, the location of each structure is also returned. All these features make D2S an excellent choice for text mining and patent analysis

For companies with a large collection of internal documents, Document to Database can access their document repository system, index all chemical information, and provide structure and metadata search functionalities. For those who use SharePoint for document management, similar functions are available in JChem for SharePoint.

We have set up chemicalize, a free public website tool to extract chemical information from webpages and documents. After processing, all structures from submitted webpages or documents can be interactively displayed and summarized for download. Please note that all information extracted will be public.