A molecular search engine! ChemxSeer
Thanks to the Alpha Doggs from Network World for this one! It’s not molecular as in a tiny search engine, its a search engine that searches for molecules on the Internet - like CO2, for instance. ChemxSeer can even tell the difference between the “He” in helium or as a pronoun.
It may take a Ph.D in Chemistry to even understand what ChemxSeer is capable of, but here goes:
ChemxSeer is an integrated digital library and database allowing for intelligent search of documents in the chemistry domain. Currently, they have designed and implemented the following:
- Chemical Entity Search: This tool identifies chemical formulae and chemical names, disambiguates the terms from other general terms, and tags them. Novel similarity scores, ranking functions and search methods are used to enable searching for chemical entities.
- TableSeer: This tool automatically identifies tables in digital documents and extracts the contents in the cells of the tables. The contents are stored in a queryable table in a database. TableSeer extracts table metadata, and uses a ranking function to search for tables relevant to user queries.
- Databases: Their data repository contains experimental data obtained from various sources. They can process, store and link data in multiple formats, e.g., Excel, XML, Gaussian, and Charmm. A metadata ad-on can help annotate the data and link multiple datasets.
The metadata is then used to link the data to published articles to allow the end-user to search for relevant data. Built using a novel architecture, their digital library will also utilize focused crawling and query expansion and rewriting techniques to utilize the limited resources available at hand and to enhance the quality of the search respectively.
What??
