SBIR Phase I: Library Design Algorithms for Active Learning in Drug Discovery

This Small Business Innovation Research Phase I project aims to develop a software platform for intelligent library design in small molecule drug discovery. High throughput chemistry and screening technologies combined with a growing list of drug targets from genomics are flooding the drug discovery process with data. Data mining methods are routinely applied to attempt to extract valuable knowledge from these large data sets and build predictive models. However, to maximize the perceptive power of these methods, the size of a data set is secondary to its information content. This project will conduct research towards the development of new algorithms for information-driven library design that enable successful data mining and the rapid construction of robust predictive models for activity. The commercial application of this project will be in the area of drug discovery. Efficient library design and subset selection are expected to maximize the potential of high throughput methods for identifying promising drug candidates in the pharmaceutical industry.