Recently, the greatest statistical computational challenge in genetic epidemiology is to identify and characterize the genes that interact with other genes and environment factors that bring the effect on complex multifactorial disease. These gene-gene interactions are also denoted as epitasis in which this phenomenon cannot be solved by traditional statistical method due to the high dimensionality of the data and the occurrence of multiple polymorphism. Hence, there are several machine learning methods to solve such problems by identifying such susceptibility gene which are neural networks (NNs), support vector machine (SVM), and random forests (RFs) in such common and multifactorial disease. This paper gives an overview on machine learning methods, describing the methodology of each machine learning methods and its application in detecting gene-gene and gene-environment interactions. Lastly, this paper discussed each machine learning method and presents the strengths and weaknesses of each machine learning method in detecting gene-gene interactions in complex human disease.

No abstract

Metabolic engineering of microorganism is widely used to enhance the production of metabolites that is useful in food additives, pharmaceutical, supplements, cosmetics, and polymer materials. One of the approaches for enhancing the biomass production is to utilize gene deletion strategies. Flux Balance Analysis is introduced to delete the gene that eventually leads the overproduction of the biomass and then to increase the biomass production. However, the result of biomass production obtained does not achieve the optimal production. Therefore, we proposed a hybrid algorithm of Particle Swarm Optimization and Flux Balance Analysis to attain an optimal gene deletion that is able to produce a higher biomass production. In this research, Particle Swarm Optimization is introduced as an optimization algorithm to obtain optimal gene deletions while Flux Balance Analysis is used to evaluate the fitness (biomass production or growth rate) of gene deletions. By performing an experiment on Escherichia coli, the results indicate that the proposed hybrid algorithm of Particle Swarm Optimization and Flux Balance Analysis is able to obtain optimal gene deletions that can produce the highest ethanol production. A hybrid algorithm is suggested due to its ability in seeking a higher ethanol production and growth rate than OptReg methods.