|
Activity Number:
|
194
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 10, 2004 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Biometrics Section
|
| Abstract - #301721 |
|
Title:
|
Analysis of a Large Structure/Biological Activity Dataset Using Recursive Partitioning, Simulated Annealing, and Genetic Algorithm
|
|
Author(s):
|
Ke Zhang*+ and Jacqueline M. Hughes-Oliver and S. Stanley Young
|
|
Companies:
|
North Carolina State University and North Carolina State University and NISS
|
|
Address:
|
3109A, Kings Ct., Raleigh, NC, 27606,
|
|
Keywords:
|
recursive partitioning ; simulated annealing ; genetic algorithm ; SAR ; HTS ; drug discovery
|
|
Abstract:
|
Large quantities of structure and biological activity data are quickly accumulated with the development of high-throughput screening (HTS) and combinatorial chemistry. Analysis of structure-activity relationships (SAR) from such large datasets is becoming challenging. We propose a method which implements Recursive Partitioning (RP), Simulated Annealing (SA), and Genetic Algorithm (GA) to produce stochastic RP trees. RP is a statistical method that can identify SAR rules for classes of compounds that are acting through different mechanisms in the same dataset. In the new algorithm a set of structural descriptors is extracted at each splitting node by using SA combined with GA as a stochastic optimization tool. For one dataset, results show that the new method is advantageous in predicting potency based on quantitative SAR model.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2004 program |
