Abstract:
A multi-objective genetic algorithm is applied to the problem of identifying genes associated with Alzheimer's disease. The input to the genetic algorithm is a set of cen...Show MoreMetadata
Abstract:
A multi-objective genetic algorithm is applied to the problem of identifying genes associated with Alzheimer's disease. The input to the genetic algorithm is a set of centrality measures obtained by merging various biological evidence types into a complex network, based on a set of 11 genes already known to be associated with this disease. In terms of leave-one-out validation, the strongest results are obtained using betweenness, with ranking showing that better results are sometimes obtained by including either stress or load with betweenness. The overall ranking of the genes across all runs is examined and suggests some genes worthy of further study with respect to their link to this disease. The methodology is also evaluated with respect to robustness by modifying the original network by a range of percentages, and applying the methodology to these variations. The results show that the methodology returns very similar results under these circumstances.
Published in: 2021 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB)
Date of Conference: 13-15 October 2021
Date Added to IEEE Xplore: 18 October 2021
ISBN Information: