Selecting effective siRNA sequences by using radial basis function network and decision tree learning

Background: 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. Results: We propose two prediction methods for selecting effective siRNA target sequences from many possible candidate sequences, one based on the supervised learning of a radial basis function (RBF) network and other based on decision tree learning. 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 proposed methods were evaluated by applying them to recently reported effective and ineffective siRNA sequence...

• Type: Journal
• Year: 2006
• Where: BMCBI
• Authors: Shigeru Takasaki, Yoshihiro Kawamura, Akihiko Konagaya
• Keywords: BMCBI 2006, Candidate Sirna Sequences, Ineffective SiRNA Sequences, SiRNA Sequences