CHAPTER 9

KERNEL FUNCTION APPLICATIONS IN CHEMINFORMATICS

AARON SMALTER AND JUN HUAN

9.1 INTRODUCTION

The fast accumulation of data describing chemical compound structures and biological activity calls for the development of efficient informatics tools. Cheminformatics is a rapidly emerging research discipline that employs a wide array of statistical, data mining, and machine learning techniques with the goal of establishing robust relationships between chemical structures and their biological properties. Hence, cheminformatics is an important component on the application side of applying informatics approach to life science problems. It has a broad range of applications in chemistry and biology; arguably the most commonly known roles are in the area of drug discovery where cheminformatics tools play a central role in the analysis and interpretation of structure–activity data collected by various means of modern high throughput screening technology. Traditionally, the analysis of large chemical structure–activity databases was done only within pharmaceutical companies, and up until recently the academic community has had only limited access to such databases. This situation, however, has changed dramatically in very recent years.

In 2002, the National Cancer Institute created the Initiative for Chemical Genetics (ICG) with the goal of offering to the academic research community a large database of chemicals with their roles in cancer research [11]. Two years later, the National ...

Get Computational Intelligence and Pattern Analysis in Biological Informatics now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.