Abstract
AbstractGenome-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.
Highlights
Tem poralgene expression data is ofparticular interestto researchers as itcan be used to create regulatory gene netw orks.Such gene netw orks representthe regulatory relationships betw een genes overtim e and provide insight into how genes upand dow nregulate each otherfrom one tim epointto the
O ne ofthe problem s in the application ofartificialneuralnetw orks in this research area concerns to the difficulty in creating com plex regulatory netw orks from the analysis ofhighdim ensionalw eightm atrices thatrepresentthe individual connections betw een genes overtim e
The results presented here provide evidence ofa novel,alternative approach to reverse engineering thatcan lead to autom atic extraction ofrules from tem poralgene expression data.The process is sim ple and repeatable,w ith clearvisualisations resulting from the m ethod
Summary
Tem poralgene expression data is ofparticular interestto researchers as itcan be used to create regulatory gene netw orks.Such gene netw orks representthe regulatory relationships betw een genes overtim e and provide insight into how genes upand dow nregulate each otherfrom one tim epointto the (the B iologicalM otherboard). R esearchers believe thattem poralgene expression m odels the biologicalsystem m ore accurately and closely as dynam ic living system s
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.
