Identifying Alzheimer’s Disease-related miRNA Based on Semi-clustering

HNetGO: protein function prediction via heterogeneous network transformer

Protein function annotation is one of the most important research topics for revealing the essence of life at molecular level in the post-genome era. Current research shows that integrating multisource data can effectively improve the performance of protein function prediction models. However, the heavy reliance on complex feature engineering and model integration methods limits the development of existing methods. Besides, models based on deep learning only use labeled data in a certain dataset to extract sequence features, thus ignoring a large amount of existing unlabeled sequence data. Here, we propose an end-to-end protein function annotation model named HNetGO, which innovatively uses heterogeneous network to integrate protein sequence similarity and protein-protein interaction network information and combines the pretraining model to extract the semantic features of the protein sequence. In addition, we design an attention-based graph neural network model, which can effectively extract node-level features from heterogeneous networks and predict protein function by measuring the similarity between protein nodes and gene ontology term nodes. Comparative experiments on the human dataset show that HNetGO achieves state-of-the-art performance on cellular component and molecular function branches.

Integrated Analysis of miRNA and mRNA Expression Profiles Reveals the Molecular Mechanism of Posttraumatic Stress Disorder and Therapeutic Drugs

Purpose

Post-traumatic stress disorder (PTSD) is a result of trauma exposure and is related to psychological suffering as a long-lasting health issue. Further analysis of the networks and genes involved in PTSD are critical to the molecular mechanisms of PTSD.

Methods

In this study, we aimed to identify key genes and molecular interaction networks involved in the pathogenesis of PTSD by integrating mRNA and miRNA data.

Results

By integrating three high-throughput datasets, 5606 differentially expressed genes (DEGs) were detected, including five differentially expressed miRNAs (DEmiRNAs) and 5525 differentially expressed mRNAs (DEmRNAs). Nineteen upregulated and 46 downregulated DEmRNAs were identified in both GSE64813 and GSE89866 datasets, while five upregulated DEmiRNAs were found in the GSE87768 dataset. Functional annotations of these DEmRNAs indicated that they were mainly enriched in blood coagulation, cell adhesion, platelet activation, and extracellular matrix (ECM)-receptor interaction. Integrated protein-protein and miRNA-protein interaction networks among the DEGs were established with the help of 65 nodes and 121 interactions. Finally, 286 small molecules were obtained based on the Drug-Gene Interaction database (DGIdb). Three genes, prostaglandin-endoperoxide synthase 1 (PTGS1), beta-tubulin gene (TUBB1), and cyclin-dependent kinase inhibitor 1A (CDKN1A), were the most promising targets for PTSD therapy. Additionally, the present study also provided a higher performance diagnostic model for PTSD based on 17 DEmRNAs, which was validated in two independent datasets, GSE109409 and GSE63878.

Conclusion

Our data provides a new molecular aspect that ECM-receptor interaction and the platelet activation process could be the potential molecular mechanism of PTSD, and the genes involved in this process may be promising therapeutic targets. A higher-performance diagnostic model for PTSD has also been identified.

Abnormal characterization of dynamic functional connectivity in Alzheimer's disease

Numerous studies have shown abnormal brain functional connectivity in individuals with Alzheimer's disease (AD) or amnestic mild cognitive impairment (aMCI). However, most studies examined traditional resting state functional connections, ignoring the instantaneous connection mode of the whole brain. In this case-control study, we used a new method called dynamic functional connectivity (DFC) to look for abnormalities in patients with AD and aMCI. We calculated dynamic functional connectivity strength from functional magnetic resonance imaging data for each participant, and then used a support vector machine to classify AD patients and normal controls. Finally, we highlighted brain regions and brain networks that made the largest contributions to the classification. We found differences in dynamic function connectivity strength in the left precuneus, default mode network, and dorsal attention network among normal controls, aMCI patients, and AD patients. These abnormalities are potential imaging markers for the early diagnosis of AD.

Bioinformatics Research on Drug Sensitivity Prediction

Modeling-based anti-cancer drug sensitivity prediction has been extensively studied in recent years. While most drug sensitivity prediction models only use gene expression data, the remarkable impacts of gene mutation, methylation, and copy number variation on drug sensitivity are neglected. Drug sensitivity prediction can both help protect patients from some adverse drug reactions and improve the efficacy of treatment. Genomics data are extremely useful for drug sensitivity prediction task. This article reviews the role of drug sensitivity prediction, describes a variety of methods for predicting drug sensitivity. Moreover, the research significance of drug sensitivity prediction, as well as existing problems are well discussed.

Regulatory Non-coding RNAs for Death Associated Protein Kinase Family

The death associated protein kinases (DAPKs) are a family of calcium dependent serine/threonine kinases initially identified in the regulation of apoptosis. Previous studies showed that DAPK family members, including DAPK1, DAPK2 and DAPK3 play a crucial regulatory role in malignant tumor development, in terms of cell apoptosis, proliferation, invasion and metastasis. Accumulating evidence has demonstrated that non-coding RNAs, including microRNA (miRNA), long non-coding RNA (lncRNA) and circRNA, are involved in the regulation of gene expression and tumorigenesis. Recent studies indicated that non-coding RNAs participate in the regulation of DAPKs. In this review, we summarized the current knowledge of non-coding RNAs, as well as the potential miRNAs, lncRNAs and circRNAs, that are involved in the regulation of DAPKs.

Identifying diseases that cause psychological trauma and social avoidance by GCN-Xgboost

Background

With the rapid development of medical treatment, many patients not only consider the survival time, but also care about the quality of life. Changes in physical, psychological and social functions after and during treatment have caused a lot of troubles to patients and their families. Based on the bio-psycho-social medical model theory, mental health plays an important role in treatment. Therefore, it is necessary for medical staff to know the diseases which have high potential to cause psychological trauma and social avoidance (PTSA).

Results

Firstly, we obtained diseases which can cause PTSA from literatures. Then, we calculated the similarities of related-diseases to build a disease network. The similarities between diseases were based on their known related genes. Then, we obtained these diseases-related proteins from UniProt. These proteins were extracted as the features of diseases. Therefore, in the disease network, each node denotes a disease and contains the information of its related proteins, and the edges of the network are the similarities of diseases. Then, graph convolutional network (GCN) was used to encode the disease network. In this way, each disease’s own feature and its relationship with other diseases were extracted. Finally, Xgboost was used to identify PTSA diseases.

Conclusion

We developed a novel method ‘GCN-Xgboost’ and compared it with some traditional methods. Using leave-one-out cross-validation, the AUC and AUPR were higher than some existing methods. In addition, case studies have been done to verify our results. We also discussed the trajectory of social avoidance and distress during acute survival of breast cancer patients.

Identifying Cancer-Related lncRNAs Based on a Convolutional Neural Network

Millions of people are suffering from cancers, but accurate early diagnosis and effective treatment are still tough for all doctors. In recent years, long non-coding RNAs (lncRNAs) have been proven to play an important role in diseases, especially cancers. These lncRNAs execute their functions by regulating gene expression. Therefore, identifying lncRNAs which are related to cancers could help researchers gain a deeper understanding of cancer mechanisms and help them find treatment options. A large number of relationships between lncRNAs and cancers have been verified by biological experiments, which give us a chance to use computational methods to identify cancer-related lncRNAs. In this paper, we applied the convolutional neural network (CNN) to identify cancer-related lncRNAs by lncRNA's target genes and their tissue expression specificity. Since lncRNA regulates target gene expression and it has been reported to have tissue expression specificity, their target genes and expression in different tissues were used as features of lncRNAs. Then, the deep belief network (DBN) was used to unsupervised encode features of lncRNAs. Finally, CNN was used to predict cancer-related lncRNAs based on known relationships between lncRNAs and cancers. For each type of cancer, we built a CNN model to predict its related lncRNAs. We identified more related lncRNAs for 41 kinds of cancers. Ten-cross validation has been used to prove the performance of our method. The results showed that our method is better than several previous methods with area under the curve (AUC) 0.81 and area under the precision–recall curve (AUPR) 0.79. To verify the accuracy of our results, case studies have been done.