Chemical database, data mining

Data mining in chemistry focuses on the extraction and evaluation of information in chemical data sets. In contrast to other fields of data mining applications, chemical data mining does not confine itself to conventional database queries but rather generates new information from the data. 

A most important task in the handling of molecular data is the evaluation of "hidden information in large chemical data sets. One of the differences between data mining techniques and conventional database queries is the generation of new data that are used subsequently to characterize molecular features in a more general way. Generally, it is not possible to hold all the potentially important information in a data set of chemical structures. Thus, the extraction of relevant information and the production of reliable secondary information are important topics. 

The described computational tools provide interactive, fast, and flexible data visualizations of chemical data that help and even enhance the human thought processes. However, visualization alone is often inadequate when multiple data points must be considered. A number of data mining methods that seek to identify significant relationships in large multidimensional databases are now being used for library design. 

Today, most data are entered into corporate databases which consider the need of the user and the purpose of data. They are structured, searchable, contain both raw and metadata. Decision-making tools can mine these databases and if necessary combine data from various sources, including genetic, proteomic, clinical and chemical databases. 

Attempts to manage specialized scientific information have given birth to the new discipline of informatics. The branch of informatics that deals primarily with genomic (sequence) data is bioinformatics, whereas cheminformatics deals with chemically oriented data. Informatics examines the way people work with computer-based information. Computers can access huge warehouses of information in the form of databases. Effective mining of these databases can, in principle, lead to knowledge. 

Data mining of chemical databases is still at its very early stage. Nevertheless, as a result of the data explosion in pharmaceutical industry, it is expected that data mining techniques will play an increasingly important role in the drug discovery process. Future studies may include, for example, the definition of chemical space, the validation of various algorithms (206), and the representation of extremely large virtual databases (207). 

---