Resumo: |
Genome-scale molecular networks, including gene pathways, gene regulatory networks and protein interactions, are central to the investigation of the nascent disciplines of systems biology and bio-complexity. Dissecting these genome-scale molecular networks in its all-possible manifestations is paramount in our quest for a genotype-input phenotype-output application which will also take environment-genome interactions into account.

Machine learning approaches are now increasingly being used for reverse engineering such networks. Our work stresses the importance of a system approach in biological research and how artificial neural networks are at the forefront of Artificial Intelligence techniques that are increasingly being used to construct as well as dissect molecular networks, the building blocks of the living system.

Our paper will show the application of artificial neural networks to reverse engineer a temporal gene pathway 
In this paper we will also explore the pruning of nodes of these artificial neural networks to simulate gene silencing and thus generate novel biological insight into these molecular networks (The Biological Motherboard).

The research described is novel, in that this may be the first time that the application of neural networks to temporal gene expression data is described. It will be shown that a trained artificial neural network, with pruning, can also be described as a gene network with minimal re-interpretation, where the weights on links between nodes reflect the probability of one gene affecting another gene in time.
|