Efficient prediction methods for selecting effective siRNA sequences

• Published in: Computers in biology and medicine Vol. 40; no. 2; pp. 149 - 158
• Main Author: Takasaki, Shigeru
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.02.2010; Elsevier Limited
• Subjects: Algorithms; Animals; Artificial Intelligence; Base Sequence; Candidates; Computational Biology - methods; Computer-Aided Design; Data mining; Databases, Nucleic Acid; Decision Trees; Design; Estimation of gene silencing; Gene Silencing; Humans; Internal Medicine; Mathematical programming; Methods; Neural Networks (Computer); Other; Probability; RBF network; Ribonucleic acid; RNA; RNA Interference; RNA, Small Interfering - genetics; RNA, Small Interfering - metabolism; ROC Curve; siRNA design; Studies; Gene silencing; RBF network; RNA interference; Estimation of gene silencing; siRNA design
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2009.11.011

Abstract Although short interfering RNA (siRNA) has been widely used for studying gene functions in mammalian cells, its gene silencing efficacy varies markedly and there are only a few consistencies among the recently reported design rules/guidelines for selecting siRNA sequences effective for mammalian genes. Another shortcoming of the previously reported methods is that they cannot estimate the probability that a candidate sequence will silence the target gene. This paper first reviewed the recently reported siRNA design guidelines and clarified the problems concerning the guidelines. It then proposed two prediction methods—Radial Basis Function (RBF) network and decision tree learning—and their combined method for selecting effective siRNA target sequences from many possible candidate sequences. They are quite different from the previous score-based siRNA design techniques and can predict the probability that a candidate siRNA sequence will be effective. The methods imply high estimation accuracy for selecting candidate siRNA sequences.