Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Selecting Maximally Informative Genes: the Interplay between Accuracy and Complexity
 

Summary: Selecting Maximally Informative Genes: the Interplay between
Accuracy and Complexity
James Wu1
and Ioannis P. Androulakis1,2,#
Department of 1
Chemical and Biochemical Engineering and 2
Biomedical Engineering
Rutgers, The State University of New Jersey
#
E-mail: yannis@rci.rutgers.edu
Abstract
Microarray experiments are emerging as one of the main driving forces in modern biology.
Via simultaneous monitoring of the expression of the entire genome for a given organism, array
experiments provide tremendous insight into the fundamental biological processes that
translate genetic information. We explore the relationship between computational complexity,
robustness, and biological relevance. We formulate the problem of identifying maximally
informative genes as a combinatorial optimization problem and demonstrate how the
combination of integer optimization and machine learning approaches produces biologically
interpretable sets of informative genes with strong biological implications. We suggest how to
analyze the complexity of the model and how to incorporate complexity issues in the selection

  

Source: Androulakis, Ioannis (Yannis) - Biomedical Engineering Department & Department of Chemical and Biochemical Engineering, Rutgers University

 

Collections: Engineering; Biology and Medicine