Hippocampal Subregion and Gene Detection in Alzheimer's Disease Based on Genetic Clustering Random Forest

Abstract

The distinguishable subregions that compose the hippocampus are differently involved in functions associated with Alzheimer's disease (AD). Thus, the identification of hippocampal subregions and genes that classify AD and healthy control (HC) groups with high accuracy is meaningful. In this study, by jointly analyzing the multimodal data, we propose a novel method to construct fusion features and a classification method based on the random forest for identifying the important features. Specifically, we construct the fusion features using the gene sequence and subregions correlation to reduce the diversity in same group. Moreover, samples and features are selected randomly to construct a random forest, and genetic algorithm and clustering evolutionary are used to amplify the difference in initial decision trees and evolve the trees. The features in resulting decision trees that reach the peak classification are the important "subregion gene pairs". The findings verify that our method outperforms well in classification performance and generalization. Particularly, we identified some significant subregions and genes, such as hippocampus amygdala transition area (HATA), fimbria, parasubiculum and genes included RYR3 and PRKCE. These discoveries provide some new candidate genes for AD and demonstrate the contribution of hippocampal subregions and genes to AD.

Keywords: clustering evolution; genetic algorithm; hippocampus; random forest; subregion.

Figure 1

The Manhattan plots of CA1 of HC and AD. CA1 = cornu ammonis 1 region; HC = healthy control; AD = Alzheimer’s disease.

Figure 2

The anatomical representation of the 12 hippocampal subregions. The color represented different subregions. HATA = the hippocampus amygdala transition area; GL_ML_DG = the granule cell layer and molecular of the dentate gyrus; CA1 = cornu ammonis 1 region; CA3 = cornu ammonis 3 region; CA4 = cornu ammonis 4 region.

Figure 3

The schematic diagram of genetic clustering random forest. Genetic algorithm and clustering evolution were applied to increase the difference among basic classifiers and further improve their diversity and accuracy.

Figure 4

The schematic diagram of genetic evolution. The clustering evolutionary was used to select the parent.

Figure 5

The relationship among the clustering evolution times, the genetic evolution times and the size of initial random forest in genetic clustering random forest. The dotted line indicates the accuracy of classification. The solid lines and bars indicate the number of genetic evolution times and clustering evolution times according to the initial random forest size.

Figure 6

The relationship between the accuracies and the size of initial random forest.

Figure 7

The relationship between the genetic evolution times and the size of initial random forest.

Figure 8

The relationship between the clustering evolution times and the size of initial random forest. The dotted line indicates the accuracy of classification. The solid lines indicate the number of clustering evolution times according to the initial random forest size.

Figure 9

The relationship curves of accuracy and the four methods in 10 experiments.

Figure 10

The ability of the traditional random forest to classify the subsets.

Figure 11

The top 475 “subregion-gene pairs” and the first 15 important “subregion-gene pairs”. Nodes denote the subregions and genes. Edges denote the association between subregions and genes, and the widths of edges denote the frequency of each “subregion-gene pair”.

Figure 12

The classification accuracy curve of the proposed model based on three datasets.