Identification of gene-level methylation for disease prediction.

DNA methylation is an epigenetic alteration that plays a fundamental part in governing gene regulatory processes. The DNA methylation mechanism affixes methyl groups to distinct cytosine residues, influencing chromatin architectures. Multiple studies have demonstrated that DNA methylation's regulatory effect on genes is linked to the beginning and progression of several disorders. Researchers have recently uncovered thousands of phenotype-related methylation sites through the epigenome-wide association study (EWAS). However, combining the methylation levels of several sites within a gene and determining the gene-level DNA methylation remains challenging. In this study, we proposed the supervised UMAP Assisted Gene-level Methylation method (sUAGM) for disease prediction based on supervised UMAP (Uniform Manifold Approximation and Projection), a manifold learning-based method for reducing dimensionality. The methylation values at the gene level generated using the proposed method are evaluated by employing various feature selection and classification algorithms on three distinct DNA methylation datasets derived from blood samples. The performance has been assessed employing classification accuracy, F-1 score, Mathews Correlation Coefficient (MCC), Kappa, Classification Success Index (CSI) and Jaccard Index. The Support Vector Machine with the linear kernel (SVML) classifier with Recursive Feature Elimination (RFE) performs best across all three datasets. From comparative analysis, our method outperformed existing gene-level and site-level approaches by achieving 100% accuracy and F1-score with fewer genes. The functional analysis of the top 28 genes selected from the Parkinson's disease dataset revealed a significant association with the disease.

Blood-based gene-expression biomarkers identification for the non-invasive diagnosis of Parkinson's disease using two-layer hybrid feature selection.

Parkinson's disease (PD) is one of the most prevalent neurodegenerative diseases. Understanding the molecular mechanism and identifying potential biomarkers of PD promote effective treatments to the patients. Due to less invasiveness and easy accessibility, biomarkers from blood support early detection and diagnosis of PD. This study combined three independent PD microarray gene expression data from blood samples applying the early integration approach. Moderated t-statistics was employed to identify differentially expressed genes (DEGs). Relevant genes were selected using a two-layer embedded wrapper feature selection method with gradient boosting machine (GBM) in the first layer followed by an ensemble of wrappers including Recursive Feature Elimination (RFE), Genetic algorithm (GA) and Bi-directional elimination (Stepwise). All three wrappers were based on logistic regression classifier (LR). The PD-predictability of the generated signature was tested using nine supervised classification models, including eight shallow machine learning and one deep learning. On an independent dataset, GSE72267, Support Vector Machine-Radial (SVMR), and Deep Neural Network (DNN) showed the best performance with AUC 0.821 and 0.82, respectively. Comparison with existing blood-based PD signatures and the biological analysis verified the reliability of the proposed signature.

Inferring Potential CircRNA-Disease Associations via Deep Autoencoder-Based Classification.

AIM: Circular RNAs (circRNA) are endogenous non-coding RNA molecules with a stable circular conformation. Growing evidence from recent experiments reveals that dysregulations and abnormal expressions of circRNAs are correlated with complex diseases. Therefore, identifying the causal circRNAs behind diseases is invaluable in explaining the disease pathogenesis. Since biological experiments are difficult, slow-progressing, and prohibitively expensive, computational approaches are necessary for identifying the relationships between circRNAs and diseases. METHODS: We propose an ensemble method called AE-RF, based on a deep autoencoder and random forest classifier, to predict potential circRNA-disease associations. The method first integrates circRNA and disease similarities to construct features. The integrated features are sent to the deep autoencoder, to extract hidden biological patterns. With the extracted deep features, the random forest classifier is trained for association prediction. RESULTS AND DISCUSSION: AE-RF achieved AUC scores of 0.9486 and 0.9522, in fivefold and tenfold cross-validation experiments, respectively. We conducted case studies on the top-most predicted results and three common human cancers. We compared the method with state-of-the-art classifiers and related methods. The experimental results and case studies demonstrate the prediction power of the model, and it outperforms previous methods with high degree of robustness. Training the classifier with the unique features retrieved by the autoencoder enhanced the model's predictive performance. The top predicted circRNAs are promising candidates for further biological tests.

An ensemble approach for CircRNA-disease association prediction based on autoencoder and deep neural network.

Circular RNAs (circRNA) are a special kind of covalently closed single-stranded RNA molecules. They have been shown to control and coordinate various biological processes. Recent researches show that circRNAs are closely associated with numerous chronic human diseases. Identification of circRNA-disease associations will contribute towards diagnosing the pathogenesis of diseases. Experimental methods for finding the relation between the diseases and their causal circRNAs are difficult and time-consuming. So computational methods are of critical need for predicting the associations between circRNAs and various human diseases. In this study, we propose an ensemble approach AE-DNN, which relies on autoencoder and deep neural networks to predict new circRNA-disease relationships. We utilized circRNA sequence similarity, disease semantic similarity, and Gaussian interaction profile kernel similarities of circRNAs and diseases for feature construction. The constructed features are fed to a deep autoencoder, and the extracted compact, high-level features are fed to the deep neural network for association prediction. We conducted 5-fold and 10-fold cross-validation experiments to assess the performance; AE-DNN could achieve AUC scores of 0.9392 and 0.9431, respectively. Experimental results and case studies indicate the robustness of our model in circRNA-disease association prediction.

Drug repositioning based on the target microRNAs using bilateral-inductive matrix completion.

Identifying the cause-and-effect mechanism behind the drug-disease associations is a challenging task. Recent studies indicate that microRNAs (miRNAs) play critical roles in human diseases. Targeting specific miRNAs with drugs to treat diseases provides a new aspect for drug repositioning. Drug repositioning provides a way to identify new clinical applications for approved drugs. Drug discovery is expensive and complicated. Therefore, computational methods are necessary for predicting the potential associations between drugs and diseases based on the target miRNAs. Our approach bilateral-inductive matrix completion (BIMC) performed two rounds of inductive matrix completion algorithm, one on the drug-miRNA and another on the miRNA-disease, association matrices, and integrated the results for predicting the drug-disease relationships through the target miRNAs. The fundamental idea of inductive matrix completion (IMC) is to fill the unknown entries of the association matrices by utilizing existing associations and side information. In our study, the integrated similarities of drugs, miRNAs, and diseases were utilized as side information. Our method predicts drug-miRNA and miRNA-disease associations, as intermediate results. To estimate the performance of our approach, we conducted leave-one-out cross-validation (LOOCV) experiments. The method could achieve AUC scores of 0.792, 0.759, and 0.791 in drug-disease, drug-miRNA, and miRNA-diseases association predictions. The results and case studies indicate the prediction ability of our method, and it is superior to previous models with high robustness. The proposed approach predicts new drug-disease relationships and the causal miRNAs. The top predicted relationships are the promising candidates, and they are released for further biological tests.

Immuno-hybrid algorithm: a novel hybrid approach for GRN reconstruction.

Bio-inspired algorithms are widely used to optimize the model parameters of GRN. In this paper, focus is given to develop improvised versions of bio-inspired algorithm for the specific problem of reconstruction of gene regulatory network. The approach is applied to the data set that was developed by the DNA microarray technology through biological experiments in the lab. This paper introduced a novel hybrid method, which combines the clonal selection algorithm and BFGS Quasi-Newton algorithm. The proposed approach implemented for real world E. coli data set and identified most of the relations. The results are also compared with the existing methods and proven to be efficient.