Inferring Signaling Pathways from RNAi Data Using Machine Learning

Mazloomian, Alborz | 2010

517 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 41334 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Beigy, Hamid
  7. Abstract:
  8. One of the standing problems in Molecular Biology and Bioinformatics is uncovering signaling pathways. Discovering the causes of many cancer-like diseases and developing better treatments for them, requires a better understanding of the behavior of cellular processes. Understanding signaling pathways can help to realize cellular processes. Due to the fast increase of possible signaling pathways when the number of components increases, the problem seems to have an inherent complexity. One of the recent methods for generating data relating to such networks is RNA interference technique. In this thesis we use data which are provided by this method. We propose two methods to infer signaling pathways. The first method is based on an evolutionary approach that uses the transitivity assumption of the model during the whole procedure. Transitivity is a prior knowledge according to the data we use. This extremely restricts the solution space of candidate models. The second method is an averaging-technique over small sub-models. When network size is large, it will be difficult to use evolutionary method. Moreover averaging can reduce the effects of noise in inferred networks. Applying the proposed methods to artificial and real biological networks shows a high level of accuracy in different situations and by changing parameters. These methods are also compared with previous methods of inferring signaling pathways
  9. Keywords:
  10. Bioinformatics ; Averaging Method ; Evolutionary Algorithm ; Molecular Biology ; Signaling Pathways ; RNA Interference

 Digital Object List

  • محتواي پايان نامه
  •   view