Presentation 2006-06-15
Building a New Mutation Model based on Bayesian Networks and estimation by a modified Belief Propagation algorithm
Yoshinori DOI, Noboru MURATA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is thought that ancient DNA repair proteins were more active than present ones, and obtaining the ancient DNA repair proteins would be helpful for hereditary diseases such as cancer. We propose a mutation model using Bayesian Networks and a modified the belief propagation algorithm, which is applied to estimate an ancient protein from multiple proteins that are present. Also, we applied the cross-validation to derive an optimum parameter. We virtually generated multiple proteins from an ancient protein following a specific mutation probability, and evaluated our model by estimating the ancient protein by the proposed model.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Bayesian Networks / Bayes estimation / Belief Propagation / Mutation model
Paper # NC2006-20
Date of Issue

Conference Information
Committee NC
Conference Date 2006/6/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Building a New Mutation Model based on Bayesian Networks and estimation by a modified Belief Propagation algorithm
Sub Title (in English)
Keyword(1) Bayesian Networks
Keyword(2) Bayes estimation
Keyword(3) Belief Propagation
Keyword(4) Mutation model
1st Author's Name Yoshinori DOI
1st Author's Affiliation Waseda University()
2nd Author's Name Noboru MURATA
2nd Author's Affiliation Waseda University
Date 2006-06-15
Paper # NC2006-20
Volume (vol) vol.106
Number (no) 101
Page pp.pp.-
#Pages 6
Date of Issue