Abstract
BackgroundThe evolution of high throughput technologies that measure gene expression levels has created a data base for inferring GRNs (a process also known as reverse engineering of GRNs). However, the nature of these data has made this process very difficult. At the moment, several methods of discovering qualitative causal relationships between genes with high accuracy from microarray data exist, but large scale quantitative analysis on real biological datasets cannot be performed, to date, as existing approaches are not suitable for real microarray data which are noisy and insufficient.ResultsThis paper performs an analysis of several existing evolutionary algorithms for quantitative gene regulatory network modelling. The aim is to present the techniques used and offer a comprehensive comparison of approaches, under a common framework. Algorithms are applied to both synthetic and real gene expression data from DNA microarrays, and ability to reproduce biological behaviour, scalability and robustness to noise are assessed and compared.ConclusionsPresented is a comparison framework for assessment of evolutionary algorithms, used to infer gene regulatory networks. Promising methods are identified and a platform for development of appropriate model formalisms is established.
Highlights
The evolution of high throughput technologies that measure gene expression levels has created a data base for inferring gene regulatory network (GRN)
In order to be able to evaluate our implementation on the chosen criteria, (Table 1), six datasets generated by S-System models of regulation and five for the artificial neural network (ANN) model were used
The models for two and five-gene S-System synthetic regulatory networks were taken from the literature, [24], and the ones for larger systems, (10, 20, 30, 50 genes), and for ANNs (5, 10, 20, 30, 50 genes) were randomly generated so that they conform to well known characteristics of real GRNs, i.e. scale-free sparse networks
Summary
The evolution of high throughput technologies that measure gene expression levels has created a data base for inferring GRNs (a process known as reverse engineering of GRNs). DNA Microarray technology enables us to measure mRNA concentrations in a cell for a large number of genes at the same time. These levels can be viewed as a snapshot of the expression levels of genes under certain conditions. One approach is to mathematically model the GRN and to find parameters of the model from available data Once built, these models can be used to predict the behaviour of the organism under certain conditions, related to different treatments or diseases.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
