MicroRNAs (miRNAs) have great potential serving as tumor biomarkers and therapeutic targets. As the rapid development of high-throughput experimental technology, gene expression experiments have become more and more specialized and diversified. The complex data structure has brought great challenge for the identification of biomarkers. In the meantime, current statistical and machine learning methods for detecting biomarkers have the problem of low reliability and biased criteria. This study aims to select combinatorial miRNA biomarkers, which have higher sensitivity and specificity than single-gene biomarkers. In order to avoid exhaustive search and redundant information, miRNAs are firstly clustered, then the combinations of representative cluster members are assessed as potential biomarkers. Both the criteria for the partition of clusters and selection of representative members are based on Fisher linear discriminant analysis (FDA). The FDA-based criterion has been demonstrated to be superior to three other criteria in selecting representative members, and also good at refining clusters. In the comparison with eight common feature selection methods, this clustering-based method performs the best with regard to the discriminative ability of selected biomarkers. Our experimental results demonstrate that the clustering-based method can identify microRNA combinatorial biomarkers with high accuracy and efficiency. Our method and data are available to the public upon request.

The wide use of high-throughput DNA microarray technology provide an increasingly detailed view of human transcriptome from hundreds to thousands of genes. Although biomedical researchers typically design microarray experiments to explore specific biological contexts, the relationships between genes are hard to identified because they are complex and noisy high-dimensional data and are often hindered by low statistical power. The main challenge now is to extract valuable biological information from the colossal amount of data to gain insight into biological processes and the mechanisms of human disease. To overcome the challenge requires mathematical and computational methods that are versatile enough to capture the underlying biological features and simple enough to be applied efficiently to large datasets. Unsupervised machine learning approaches provide new and efficient analysis of gene expression profiles. In our study, two unsupervised knowledge-based matrix factorization methods, independent component analysis (ICA) and nonnegative matrix factorization (NMF) are integrated to identify significant genes and related pathways in microarray gene expression dataset of Alzheimer’s disease. The advantage of these two approaches is they can be performed as a biclustering method by which genes and conditions can be clustered simultaneously. Furthermore, they can group genes into different categories for identifying related diagnostic pathways and regulatory networks. The difference between these two method lies in ICA assume statistical independence of the expression modes, while NMF need positivity constrains to generate localized gene expression profiles. In our work, we performed FastICA and non-smooth NMF methods on DNA microarray gene expression data of Alzheimer’s disease respectively. The simulation results shows that both of the methods can clearly classify severe AD samples from control samples, and the biological analysis of the identified significant genes and their related pathways demonstrated that these genes play a prominent role in AD and relate the activation patterns to AD phenotypes. It is validated that the combination of these two methods is efficient. Unsupervised matrix factorization methods provide efficient tools to analyze high-throughput microarray dataset. According to the facts that different unsupervised approaches explore correlations in the high-dimensional data space and identify relevant subspace base on different hypotheses, integrating these methods to explore the underlying biological information from microarray dataset is an efficient approach. By combining the significant genes identified by both ICA and NMF, the biological analysis shows great efficient for elucidating the molecular taxonomy of Alzheimer’s disease and enable better experimental design to further identify potential pathways and therapeutic targets of AD.

Discovering the signaling pathway and regulatory network would provide significant advance in genome-wide understanding of pathogenesis of human diseases. Despite the rich transcriptome data, the limitation for microarray data is unable to detect changes beyond transcriptional level and insufficient in reconstructing pathways and regulatory networks. In our study, protein-protein interaction (PPI) data is introduced to add molecular biological information for predicting signaling pathway of Alzheimer’s disease (AD). Combining PPI with gene expression data, significant genes are selected by modified linear regression model firstly. Then, according to the biological researches that inflammation reaction plays an important role in the generation and deterioration of AD, NF-κB (nuclear factor-kappa B), as a significant inflammatory factor, has been selected as the beginning gene of the predicting signaling pathway. Based on that, integer linear programming (ILP) model is proposed to reconstruct the signaling pathway between NF-κB and AD virulence gene APP (amyloid precursor protein). The results identify 6 AD virulence genes included in the predicted inflammatory signaling pathway, and a large amount of molecular biological analysis shows the great understanding of the underlying biological process of AD.

MRNA and IncRNA serve as a type of endogenous RNA in cell, which can competitively bind to the same miRNA through miRNA response elements (MREs), thereby regulating their respective expression levels, playing an important role in post-transcriptional regulation, and regulating the progress of tumors. The proposed competing endogenous RNA (ceRNA) hypothesis provides novel clues for the occurrence and development of tumors, but the integrative analysis methods of diverse RNA data are significantly limited. In order to find out the relationship among miRNA, mRNA and IncRNA, the previous studies only used individual dataset as seeds to search two other related data in the database to construct ceRNA network, but it was difficult to identify the synchronized effects from multiple regulatory levels. Here, we developed the joint matrix factorization method integrating prior knowledge to map the three types of RNA data of lung cancer to the common coordinate system and construct the ceRNA network corresponding to the common module. The results show that more than 90% of the modules are closely related to cancer, including lung cancer. Furthermore, the resulting ceRNA network not only accurately excavates the known correlation of the three types of RNA molecular, but also further discovers the potential biological associations of them. Our work provides support and foundation for future biological validation how competitive relationships of multiple RNAs affects the development of tumors.