Improved prediction of gene expression through integrating cell signalling models with machine learning.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: A key problem in bioinformatics is that of predicting gene expression levels. There are two broad approaches: use of mechanistic models that aim to directly simulate the underlying biology, and use of machine learning (ML) to empirically predict expression levels from descriptors of the experiments. There are advantages and disadvantages to both approaches: mechanistic models more directly reflect the underlying biological causation, but do not directly utilize the available empirical data; while ML methods do not fully utilize existing biological knowledge.

Authors

  • Nada Al Taweraqi
    Department of Computer Science, University of Manchester, Manchester, UK. Nadaaltaweraqi@postgrad.manchester.ac.uk.
  • Ross D King
    3Department of Biology and Biological Engineering, Division of Systems and Synthetic Biology, Chalmers University of Technology, Kemivägen 10, SE-412 96 Gothenburg, Sweden.