Advances in text mining for chemical information
21 November 2012
4:00 pm CET / 7:00 am PST / 10:00 am EST / 3:00 pm GMT / 8:30 pm IST
As scientific and patent literature expands, we need more efficient ways to find and extract information. Converting systematic chemical names to their structures is key for automatically finding novel compounds. This talk will show the benefit of directly integrating Chemaxon's name to structure and structure search with the interactive text mining platform, I2E. We will describe recent improvements made to the ChemAxon name to structure software, and how we evaluated this. The session will conclude with a demonstration of text mining over full text patents from USPTO, WIPO and EPO. Examples will include showing how chemicals can be clustered according to their roles, and how information can be linked across different parts of a patent e.g. between a definition of a compound and a table of results for that compound.