Principal Component Analysis Based Feature Extraction Approach to Identify Circulating microRNA Biomarkers

Abstract

The discovery and characterization of blood-based disease biomarkers are clinically important because blood collection is easy and involves relatively little stress for the patient. However, blood generally reflects not only targeted diseases, but also the whole body status of patients. Thus, the selection of biomarkers may be difficult. In this study, we considered miRNAs as biomarker candidates for several reasons. First, since miRNAs were discovered relatively recently, they have not yet been tested extensively. Second, since the number of miRNAs is relatively limited, selection is expected to be easy. Third, since they are known to play critical roles in a wide range of biological processes, their expression may be disease specific. We applied a newly proposed method to select combinations of miRNAs that discriminate between healthy controls and each of 14 diseases that include 5 cancers. A new feature selection method is based on principal component analysis. Namely this method does not require knowledge of whether each sample was derived from a disease patient or a healthy control. Using this method, we found that hsa-miR-425, hsa-miR-15b, hsa-miR-185, hsa-miR-92a, hsa-miR-140-3p, hsa-miR-320a, hsa-miR-486-5p, hsa-miR-16, hsa-miR-191, hsa-miR-106b, hsa-miR-19b, and hsa-miR-30d were potential biomarkers; combinations of 10 of these miRNAs allowed us to discriminate each disease included in this study from healthy controls. These 12 miRNAs are significantly up- or downregulated in most cancers and other diseases, albeit in a cancer- or disease-specific combinatory manner. Therefore, these 12 miRNAs were also previously reported to be cancer- and disease-related miRNAs. Many disease-specific KEGG pathways were also significantly enriched by target genes of up−/downregulated miRNAs within several combinations of 10 miRNAs among these 12 miRNAs. We also selected miRNAs that could discriminate one disease from another or from healthy controls. These miRNAs were found to be largely overlapped with miRNAs that discriminate each disease from healthy controls.

Universal disease biomarker: can a fixed set of blood microRNAs diagnose multiple diseases?

“…Mean accuracies were 0.791 and 0.815, respectively, and they were coincident with the mean accuracy (0.784) estimated using PCA-based LDA with UDB in a previous study [23] (see Table 1). Values of accuracy together with sensitivity and specificity values are also listed in Table 1.…”

“…PCA-based unsupervised FE was used for the previous UDB discovery [23]. The importance of stability was previously demonstrated by Wehrens et al [24], who showed that a stable FE improved the performance.…”

Cancer Affects microRNA Expression, Release, and Function in Cardiac and Skeletal Muscle

“…Reason for the discrepancy in separation of samples to three groups with and without normalization is unclear. However, a recent study has shown PCA as a better method to identify circulating microRNAs 18 . Samples utilized in this study were from inbred mice housed under similar condition, and collected and analyzed at the same time, which should limit inter-mice and technical variability.…”

Genome-wide epigenomic profiling for biomarker discovery

“…Importantly, the identification of individual genomic loci or genes as biomarkers from large datasets requires robust statistical testing such as multiple-testing correction (although traditional tests like the Bonferroni correction are over-conservative since there is often correlation between loci, i.e., they are not independent) or stringent false discovery rate (FDR) control (for example, by the Benjamini–Hochberg procedure) [80–82]. To define sets of biomarkers from large dataset, alternative statistical methods (such as sparse principle component analysis (PCA) or sparse canonical correlation analysis (CCA) [83, 84]) are available as well. In light of (i) challenges with the experimental setup when using patient material, (ii) costs, and (iii) the extensive computational analysis associated with the exploratory phase of biomarker discovery, genome-wide screens are often performed on relatively small cohorts.…”