Drug discovery through information extraction technology

Increasingly, the pharmaceutical industry is a knowledge-based discipline. Knowledge, and information, is kept in both structured and unstructured form. For example, the results of experiments and clinical studies, are most often stored in structured database management systems or spreadsheets. In addition, more scientific information, such as chemical structures and properties are kept in structured form and are accessible through query languages such as SQL. However, a great deal of the most current, and most valuable, information resides not in a structured data source, but only in unstructured text, typically in the scientific literature. The ability to automatically and accurately extract information from unstructured text is of great value at every point in the drug discovery and development process.