Jump to main content
Jump to site search

All chapters
Previous chapter Next chapter

Chapter 9

In Silico Solutions for Predicting Efficacy and Toxicity

This chapter describes a variety of in silico methods that provide support for research decisions on efficacy and toxicity. It reviews the use of two-dimensional chemical structures and their associated biological data, including biological activity data generated from human cell lines, in computational methods and explains how the data is typically represented for import into these tools. Searching databases of historical information helps to answer precise research questions and common approaches to querying these databases based on both chemical structures as well as the associated data are outlined. In silico methods used to analyse the relationships between the biological and chemical data require the generation of molecular descriptors, which are then used in advanced data mining methods, such as clustering or decision trees. Encoding the relationships between the chemical structures and activity or toxicity as mathematical models enables the application of this historical experience to support both current and future research directions. Two case studies are used to illustrate how these approaches can be used to support regulatory decisions on impurities and how these approaches can be used to predict human-based adverse events.

Publication details

https://doi.org/10.1039/9781782620136-00194
Print publication date
09 Dec 2014
Copyright year
2015
Print ISBN
978-1-84973-825-5
PDF eISBN
978-1-78262-013-6
ePub eISBN
978-1-78262-355-7
From the book series:
Drug Discovery