Identification of Post-myocardial Infarction Blood Expression Signatures Using Multiple Feature Selection Strategies

Abstract

Myocardial infarction (MI) is a type of serious heart attack in which the blood flow to the heart is suddenly interrupted, resulting in injury to the heart muscles due to a lack of oxygen supply. Although clinical diagnosis methods can be used to identify the occurrence of MI, using the changes of molecular markers or characteristic molecules in blood to characterize the early phase and later trend of MI will help us choose a more reasonable treatment plan. Previously, comparative transcriptome studies focused on finding differentially expressed genes between MI patients and healthy people. However, signature molecules altered in different phases of MI have not been well excavated. We developed a set of computational approaches integrating multiple machine learning algorithms, including Monte Carlo feature selection (MCFS), incremental feature selection (IFS), and support vector machine (SVM), to identify gene expression characteristics on different phases of MI. 134 genes were determined to serve as features for building optimal SVM classifiers to distinguish acute MI and post-MI. Subsequently, functional enrichment analyses followed by protein-protein interaction analysis on 134 genes identified several hub genes (IL1R1, TLR2, and TLR4) associated with progression of MI, which can be used as new diagnostic molecules for MI.

Keywords: Monte Carlo feature selection; gene; incremental feature selection; myocardial infarction; support vector machine.

FIGURE 1

The IFS-curve obtained by IFS method. The X-axis represents the number of features participating in the classification. The Y-axis represents the LOOCV accuracy produced by SVM. The accuracy reached 0.831 when the top 134 features were used. When even more features were added, the accuracy did not increase too much. It reached the plateau area. Therefore, to balance the number of features and the accuracy, 134 features were selected.

FIGURE 2

Heatmap of all MI samples on the top 134 genes. The columns refer to samples and the rows refer to genes. Different phases of samples were colored by green (D0 represents acute MI), red (D30 represents 30-days post-MI), and blue (Y1 represents 1-year post-MI), respectively. It can be seen that the samples from different time points had different expression patterns. For each time point, there was a corresponding cluster with highly expressed genes at this time point.

FIGURE 3

The boxplots of representative post-MI expression patterns. The expression level of genes like DCK (A) and RNU4-7P (B) increased in post-MI while the expression levels of genes like FCAR (C) and IL17RA (D) decreased in post-MI. These expression patterns may reveal the mechanisms of MI.

FIGURE 4

Gene networks containing IL1R1, TLR2, TLR4, and other related genes. These gene interactions were extracted from the protein-protein interaction network reported in a STRING database and plotted by the online drawing tool of STRING. IL1R1, TLR2, and TLR4 were located in the center positions and were hub genes.