Predicting the potential human lncRNA-miRNA interactions based on graph convolution network with conditional random field

A potential therapeutic molecule target: lncRNA AK023507 inhibits the metastasis of breast cancer by regulating the WNT/DOCK4/β-catenin axis

PURPOSE

Breast cancer (BC) has become the most common malignant tumor in women worldwide. This study was carried out to find and validate a novel molecular therapeutic target for BC.

METHODS

Long non-coding RNA (lncRNA) AK023507 was selected as the study objects through microarray analysis. The function of lncRNA AK023507 was verified by various cell function experiments in vitro, subcutaneous tumorigenesis experiments, and lung metastasis model experiments in vivo. The RNA pull-down experiment and Western blot experiment were used to confirm the mechanism regulation pathway and the recovery experiment was used to verify it. TCGA datasets were used for clinical and immune function prediction analysis.

RESULTS

In vitro cell function tests and in vivo experiments suggested that overexpression of lncRNA AK023507 inhibited the proliferation and metastasis of BC cells. The RNA pull-down experiment and Western blot analysis validated that lncRNA AK023507 interacted with the dedicator of cytokinesis 4 (DOCK4) protein. Analysis of public databases predicted that DOCK4 is a potential prognostic risk factor associated with epithelial-mesenchymal transition (EMT) and central memory T cell (TCM) cellular immune infiltration.

CONCLUSIONS

LncRNA AK023507 inhibits the proliferation and metastasis of BC by regulating the DOCK4/β-catenin axis. This discovery will provide new potential therapeutic targets for BC.

Attention-augmented multi-domain cooperative graph representation learning for molecular interaction prediction

Accurate identification of molecular interactions is crucial for biological network analysis, which can provide valuable insights into fundamental regulatory mechanisms. Despite considerable progress driven by computational advancements, existing methods often rely on task-specific prior knowledge or inherent structural properties of molecules, which limits their generalizability and applicability. Recently, graph-based methods have emerged as a promising approach for predicting links in molecular networks. However, most of these methods focus primarily on aggregating topological information within individual domains, leading to an inadequate characterization of molecular interactions. To mitigate these challenges, we propose AMCGRL, a generalized multi-domain cooperative graph representation learning framework for multifarious molecular interaction prediction tasks. Concretely, AMCGRL incorporates multiple graph encoders to simultaneously learn molecular representations from both intra-domain and inter-domain graphs in a comprehensive manner. Then, the cross-domain decoder is employed to bridge these graph encoders to facilitate the extraction of task-relevant information across different domains. Furthermore, a hierarchical mutual attention mechanism is developed to capture complex pairwise interaction patterns between distinct types of molecules through inter-molecule communicative learning. Extensive experiments conducted on the various datasets demonstrate the superior representation learning capability of AMCGRL compared to the state-of-the-art methods, proving its effectiveness in advancing the prediction of molecular interactions.

IRF4 as a molecular biomarker in pan-cancer through multiple omics integrative analysis

IRF4, characterized by its unique helix-turn-helix DNA-binding motif, is a member of the interferon regulatory factor (IRF) family. It plays a critical role in regulating host defense mechanisms, including innate and adaptive immune responses, as well as oncogenesis. However, the precise role of IRF4 in malignant tumors remains poorly understood. In this study, we first investigated IRF4 gene expression across various cancer types and its distribution within different molecular and immunological subtypes, providing a comprehensive understanding of its expression patterns in pan-cancer. We further explored the interacting proteins, diagnostic significance, molecular characteristics, prognostic relevance, and biological functions of IRF4 in diverse cancers. Focusing on colorectal cancer (CRC), we conducted a detailed analysis of IRF4, examining its associations with clinical features and outcomes across multiple clinical subgroups and databases. Additionally, we assessed IRF4 expression at both transcriptional and translational levels in CRC tumor specimens using tissue microarrays. Our findings revealed that IRF4 expression varies significantly not only across cancer types but also among molecular and immunological subtypes. In CRC, elevated IRF4 expression was associated with poorer overall survival. Notably, IRF4 was predominantly expressed in immune cells and showed a strong correlation with tumor immune regulation. Given its high predictive accuracy for cancer outcomes and robust prognostic associations, IRF4 may serve as a valuable prognostic biomarker for CRC. In conclusion, IRF4 represents a unique molecular biomarker for pan-cancer prognosis and an independent prognostic risk factor for CRC. Its critical role in immune regulation also positions IRF4 as a promising target for immunotherapeutic strategies in CRC.

A Multi-Task Self-Supervised Strategy for Predicting Molecular Properties and FGFR1 Inhibitors

Studying the molecular properties of drugs and their interactions with human targets aids in better understanding the clinical performance of drugs and guides drug development. In computer-aided drug discovery, it is crucial to utilize effective molecular feature representations for predicting molecular properties and designing ligands with high binding affinity to targets. However, designing an effective multi-task and self-supervised strategy remains a significant challenge for the pretraining framework. In this study, a multi-task self-supervised deep learning framework is proposed, MTSSMol, which utilizes ≈10 million unlabeled drug-like molecules for pretraining to identify potential inhibitors of fibroblast growth factor receptor 1 (FGFR1). During the pretraining of MTSSMol, molecular representations are learned through a graph neural networks (GNNs) encoder. A multi-task self-supervised pretraining strategy is proposed to fully capture the structural and chemical knowledge of molecules. Extensive computational tests on 27 datasets demonstrate that MTSSMol exhibits exceptional performance in predicting molecular properties across different domains. Moreover, MTSSMol's capability is validated to identify potential inhibitors of FGFR1 through molecular docking using RoseTTAFold All-Atom (RFAA) and molecular dynamics simulations. Overall, MTSSMol provides an effective algorithmic framework for enhancing molecular representation learning and identifying potential drug candidates, offering a valuable tool to accelerate drug discovery processes. All of the codes are freely available online at https:// github.com/zhaoqi106/MTSSMol.

AI-Derived Blood Biomarkers for Ovarian Cancer Diagnosis: Systematic Review and Meta-Analysis

BACKGROUND

Emerging evidence underscores the potential application of artificial intelligence (AI) in discovering noninvasive blood biomarkers. However, the diagnostic value of AI-derived blood biomarkers for ovarian cancer (OC) remains inconsistent.

OBJECTIVE

We aimed to evaluate the research quality and the validity of AI-based blood biomarkers in OC diagnosis.

METHODS

A systematic search was performed in the MEDLINE, Embase, IEEE Xplore, PubMed, Web of Science, and the Cochrane Library databases. Studies examining the diagnostic accuracy of AI in discovering OC blood biomarkers were identified. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-AI tool. Pooled sensitivity, specificity, and area under the curve (AUC) were estimated using a bivariate model for the diagnostic meta-analysis.

RESULTS

A total of 40 studies were ultimately included. Most (n=31, 78%) included studies were evaluated as low risk of bias. Overall, the pooled sensitivity, specificity, and AUC were 85% (95% CI 83%-87%), 91% (95% CI 90%-92%), and 0.95 (95% CI 0.92-0.96), respectively. For contingency tables with the highest accuracy, the pooled sensitivity, specificity, and AUC were 95% (95% CI 90%-97%), 97% (95% CI 95%-98%), and 0.99 (95% CI 0.98-1.00), respectively. Stratification by AI algorithms revealed higher sensitivity and specificity in studies using machine learning (sensitivity=85% and specificity=92%) compared to those using deep learning (sensitivity=77% and specificity=85%). In addition, studies using serum reported substantially higher sensitivity (94%) and specificity (96%) than those using plasma (sensitivity=83% and specificity=91%). Stratification by external validation demonstrated significantly higher specificity in studies with external validation (specificity=94%) compared to those without external validation (specificity=89%), while the reverse was observed for sensitivity (74% vs 90%). No publication bias was detected in this meta-analysis.

CONCLUSIONS

AI algorithms demonstrate satisfactory performance in the diagnosis of OC using blood biomarkers and are anticipated to become an effective diagnostic modality in the future, potentially avoiding unnecessary surgeries. Future research is warranted to incorporate external validation into AI diagnostic models, as well as to prioritize the adoption of deep learning methodologies.

TRIAL REGISTRATION

PROSPERO CRD42023481232; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023481232.

lncRNA TUG1 and kidney diseases

Long noncoding RNAs (lncRNAs) cover a large class of transcribed RNA molecules that are more than 200 nucleotides in length. An increasing number of studies have shown that lncRNAs control gene expression through different mechanisms and play important roles in a range of biological processes including growth, cell differentiation, proliferation, apoptosis, and invasion. TUG1 was originally discovered in a genomic screen of taurine-treated mouse retinal cells. Previous evidences pointed out that lncRNA TUG1 could inhibit apoptosis and the release of inflammatory factors, improve mitochondrial function, thereby protecting cells from damage, and showing a protective role of TUG1 in diseases. Given that TUG1 has multiple targets and can interfere with multiple steps in the oncogenic process, it has been proposed as a therapeutic target. In this review, we summarize the research progress of lncRNA TUG1 in kidney diseases in the past 8 years, and discuss its related molecular mechanisms.

CNV-mediated dysregulation of the ceRNA network mechanism revealed heterogeneity in diffuse and intestinal gastric cancers

BACKGROUND

Gastric cancer (GC) is a highly heterogeneous tumour with high morbidity. Approximately 95% of GC cases are gastric adenocarcinomas, which are further categorized into two predominant subtypes: diffuse gastric cancer (DGC) and intestinal gastric cancer (IGC). These subtypes exhibit distinct pathophysiological and molecular characteristics, reflecting their unique tumorigenic mechanisms.

METHOD

In this study, we employed a comprehensive approach to identify driver genes associated with DGC and IGC by focusing on copy number variation (CNV) genes within the competing endogenous RNA (ceRNA) network. The influence of driver CNV genes on the molecular, cellular, and clinical differences between DGC and IGC was subsequently analysed. Finally, therapeutic strategies for DGC and IGC were evaluated based on the status and functional pathways of the driver CNV genes.

RESULTS

A total of 17 and 22 driver CNV genes were identified in DGC and IGC, respectively. These genes drive subtype differences through the ceRNA network, resulting in alterations in the tumour microenvironment (TME). Based on these differences, personalized treatment strategies for DGC or IGC could be developed. Immune checkpoint inhibitors may be an effective treatment option in IGC. Additionally, DGC patients with homozygous deletion of PPIF might benefit from adjuvant chemotherapy, whereas those with high-level amplification of MTAP could respond to targeted therapy.

CONCLUSION

Driver CNV genes were identified to reveal the underlying cause of heterogeneity in DGC and IGC. Furthermore, specific driver CNV genes were identified as potential therapeutic targets, facilitating personalized treatment.

Identification and validation of the common pathogenesis and hub biomarkers in Papillary thyroid carcinoma complicated by rheumatoid arthritis

BACKGROUND

Papillary thyroid carcinoma coexisting with rheumatoid arthritis is frequently observed in clinical patients, yet its pathogenesis has not been fully elucidated. This investigation sought to further explore the molecular underpinnings of these two diseases.

METHODS

Gene expression profiles for thyroid papillary carcinoma and rheumatoid arthritis patients were obtained from the Comprehensive Gene Expression Database (GEO). Following the discovery of shared differentially expressed genes (DEGs) between these two conditions, three separate analyses were conducted. These included functional annotation, the establishment of a protein‒protein interaction (PPI) network and module, and the identification of hub genes via coexpression analysis. The final step involved the validation of target genes via clinical specimens.

RESULTS

This study analyzed datasets from four GEO databases and identified 64 common DEGs. Functional enrichment analysis revealed that these genes are predominantly associated with pathways related to immunity and signal transduction. Protein‒protein interaction (PPI) network analysis revealed complex interactions among these differentially expressed genes and highlighted several genes that may play pivotal roles in shared pathological mechanisms, namely, CCR5, CD4, IL6, CXCL13, FOXM1, CXCL9, and CXCL10.

CONCLUSION

Our study highlights the shared pathogenesis between papillary thyroid cancer and rheumatoid arthritis. Shared pathways and crucial genes could offer novel perspectives for subsequent investigations into the mechanisms of these diseases.

Investigation of cell development and tissue structure network based on natural Language processing of scRNA-seq data

BACKGROUND

Single-cell multi-omics technologies, particularly single-cell RNA sequencing (scRNA-seq), have revolutionized our understanding of cellular heterogeneity and development by providing insights into gene expression at the single-cell level. Investigating the influence of genes on cellular behavior is crucial for elucidating cell fate determination and differentiation, cell development processes, and disease mechanisms.

METHODS

Inspired by NLP, we present a novel scRNA-seq analysis method that treats genes as analogous to words. Using word2vec to embed gene sequences derived from gene networks, we generate vector representations of genes, which are then used to represent cells by summing gene vectors and subsequently tissues by aggregating cell vectors.

RESULTS

Our NLP-based approach analyzes scRNA-seq data by generating vector representations of genes, cells, and tissues. This multi-scale analysis includes mapping cell states in vector space to reveal developmental trajectories, quantifying cell similarity using Euclidean distance, and constructing inter-tissue relationship networks from aggregated cell vectors.

CONCLUSIONS

This method offers a computationally efficient approach for analyzing scRNA-seq data by constructing embedding representations similar to those used in large language model pre-training, but without requiring high-performance computing clusters. By generating gene embeddings that capture functional relationships, this method facilitates the study of cell development trajectories, the impact of gene perturbations, cell clustering, and the construction and analysis of tissue networks. This provides a valuable tool for single-cell data analysis.

BINDTI: A Bi-Directional Intention Network for Drug-Target Interaction Identification Based on Attention Mechanisms

The identification of drug-target interactions (DTIs) is an essential step in drug discovery. In vitro experimental methods are expensive, laborious, and time-consuming. Deep learning has witnessed promising progress in DTI prediction. However, how to precisely represent drug and protein features is a major challenge for DTI prediction. Here, we developed an end-to-end DTI identification framework called BINDTI based on bi-directional Intention network. First, drug features are encoded with graph convolutional networks based on its 2D molecular graph obtained by its SMILES string. Next, protein features are encoded based on its amino acid sequence through a mixed model called ACmix, which integrates self-attention mechanism and convolution. Third, drug and target features are fused through bi-directional Intention network, which combines Intention and multi-head attention. Finally, unknown drug-target (DT) pairs are classified through multilayer perceptron based on the fused DT features. The results demonstrate that BINDTI greatly outperformed four baseline methods (i.e., CPI-GNN, TransfomerCPI, MolTrans, and IIFDTI) on the BindingDB, BioSNAP, DrugBank, and Human datasets. More importantly, it was more appropriate to predict new DTIs than the four baseline methods on imbalanced datasets. Ablation experimental results elucidated that both bi-directional Intention and ACmix could greatly advance DTI prediction. The fused feature visualization and case studies manifested that the predicted results by BINDTI were basically consistent with the true ones. We anticipate that the proposed BINDTI framework can find new low-cost drug candidates, improve drugs' virtual screening, and further facilitate drug repositioning as well as drug discovery.

The Optimization of Culture Conditions for Injectable Recombinant Collagen Hydrogel Preparation Using Machine Learning

Injectable recombinant collagen hydrogels (RCHs) are crucial in biomedical applications. Culture conditions play an important role in the preparation of hydrogels. However, determining the characteristics of hydrogels under certain conditions and determining the optimal conditions swiftly still remain challenging tasks. In this study, a machine learning approach was introduced to explore the correlation between hydrogel characteristics and culture conditions and determine the optimal culture conditions. The study focused on four key factors as independent variables: initial substrate concentration, reaction temperature, pH level, and reaction time, while the dependent variable was the elastic modulus of the hydrogels. To analyze the impact of these factors on the elastic modulus, four mathematical models were employed, including multiple linear regression (ML), decision tree (DT), support vector machine (SVM), and neural network (NN). The theoretical outputs of NN were closest to the actual values. Therefore, NN proved to be the most suitable model. Subsequently, the optimal culture conditions were identified as a substrate concentration of 15% (W/V), a reaction temperature of 4 °C, a pH of 7.0, and a reaction time of 12 h. The hydrogels prepared under these specific conditions exhibited a predicted elastic modulus of 15,340 Pa, approaching that of natural elastic cartilage.

Investigating the relevance of nucleotide metabolism in the prognosis of glioblastoma through bioinformatics models

Nucleotide metabolism (NM) is a fundamental process that enables the rapid growth of tumors. Glioblastoma (GBM) primarily relies on NM for its invasion, leading to severe clinical outcomes. This study focuses on NM to identify potential biomarkers associated with GBM. Publicly available databases were used as the primary data source for this study, excluding biological tissue samples. We identified and evaluated key genes involved in NM, followed by developing and validating a prognostic model. Patients were classified into high- and low-risk groups based on this model, and the two groups were compared with respect to cellular immunity and mutation profiles. The biomarkers were confirmed using real-time reverse-transcriptase polymerase chain reaction. Our study identified UPP1, CDA, NUDT1, and ADSL as significant biomarkers associated with prognosis, all of which were upregulated in patients with GBM. The risk score and clinical factors such as age, sex, GBM stage, MGMT promoter status, and IDH mutation status were found to be independent prognostic factors. Patients with glioblastoma showed a higher overall mutation burden. Using bioinformatics, this study identifies key factors associated with NM in GBM that may influence patient prognosis. This study enhances our understanding of GBM, provides valuable insights for further research, and serves as a reference for evaluating patient outcomes.

CLSSATP: Contrastive learning and self-supervised learning model for aquatic toxicity prediction

As compound concentrations in aquatic environments increase, the habitat degradation of aquatic organisms underscores the growing importance of studying the impact of chemicals on diverse aquatic populations. Understanding the potential impacts of different chemical substances on different species is a necessary requirement for protecting the environment and ensuring sustainable human development. In this regard, deep learning methods offer significant advantages over traditional experimental approaches in terms of cost, accuracy, and generalization ability. This research introduces CLSSATP, an efficient contrastive self-supervised learning deep neural network prediction model for organic toxicity. The model integrates two modules, a self-supervised learning module using molecular fingerprints for representation, and a contrastive learning module utilizing molecular graphs. Through dual-perspective learning, the model gains clear insights into the structural and property relationships of molecules. The experiment results indicate that our model outperforms comparative methods, demonstrating the effectiveness of our proposed architecture. Moreover, ablation experiments show that the self-supervised module and contrastive learning module respectively provide average performance improvements of 9.43 % and 10.98 % to CLSSATP. Furthermore, by visualizing the representations of our model, we observe that it correctly identifies the substructures that determine the molecular properties, granting itself with interpretability. In conclusion, CLSSATP offers a novel and effective perspective for future research in aquatic toxicity assessment. All of codes and datasets are freely available online at https://github.com/zhaoqi106/CLSSATP.

Multi-task aquatic toxicity prediction model based on multi-level features fusion

INTRODUCTION

With the escalating menace of organic compounds in environmental pollution imperiling the survival of aquatic organisms, the investigation of organic compound toxicity across diverse aquatic species assumes paramount significance for environmental protection. Understanding how different species respond to these compounds helps assess the potential ecological impact of pollution on aquatic ecosystems as a whole. Compared with traditional experimental methods, deep learning methods have higher accuracy in predicting aquatic toxicity, faster data processing speed and better generalization ability.

OBJECTIVES

This article presents ATFPGT-multi, an advanced multi-task deep neural network prediction model for organic toxicity.

METHODS

The model integrates molecular fingerprints and molecule graphs to characterize molecules, enabling the simultaneous prediction of acute toxicity for the same organic compound across four distinct fish species. Furthermore, to validate the advantages of multi-task learning, we independently construct prediction models, named ATFPGT-single, for each fish species. We employ cross-validation in our experiments to assess the performance and generalization ability of ATFPGT-multi.

RESULTS

The experimental results indicate, first, that ATFPGT-multi outperforms ATFPGT-single on four fish datasets with AUC improvements of 9.8%, 4%, 4.8%, and 8.2%, respectively, demonstrating the superiority of multi-task learning over single-task learning. Furthermore, in comparison with previous algorithms, ATFPGT-multi outperforms comparative methods, emphasizing that our approach exhibits higher accuracy and reliability in predicting aquatic toxicity. Moreover, ATFPGT-multi utilizes attention scores to identify molecular fragments associated with fish toxicity in organic molecules, as demonstrated by two organic molecule examples in the main text, demonstrating the interpretability of ATFPGT-multi.

CONCLUSION

In summary, ATFPGT-multi provides important support and reference for the further development of aquatic toxicity assessment. All of codes and datasets are freely available online at https://github.com/zhaoqi106/ATFPGT-multi.

ISLRWR: A network diffusion algorithm for drug-target interactions prediction

Machine learning techniques and computer-aided methods are now widely used in the pre-discovery tasks of drug discovery, effectively improving the efficiency of drug development and reducing the workload and cost. In this study, we used multi-source heterogeneous network information to build a network model, learn the network topology through multiple network diffusion algorithms, and obtain compressed low-dimensional feature vectors for predicting drug-target interactions (DTIs). We applied the metropolis-hasting random walk (MHRW) algorithm to improve the performance of the random walk with restart (RWR) algorithm, forming the basis by which the self-loop probability of the current node is removed. Additionally, the propagation efficiency of the MHRW was improved using the improved metropolis-hasting random walk (IMRWR) algorithm, facilitating network deep sampling. Finally, we proposed a correction of the transfer probability of the entire network after increasing the self-loop rate of isolated nodes to form the ISLRWR algorithm. Notably, the ISLRWR algorithm improved the area under the receiver operating characteristic curve (AUROC) by 7.53 and 5.72%, and the area under the precision-recall curve (AUPRC) by 5.95 and 4.19% compared to the RWR and MHRW algorithms, respectively, in predicting DTIs performance. Moreover, after excluding the interference of homologous proteins (popular drugs or targets may lead to inflated prediction results), the ISLRWR algorithm still showed a significant performance improvement.

Recent advances in investigation of circRNA/lncRNA-miRNA-mRNA networks through RNA sequencing data analysis

Non-coding RNAs (ncRNAs) are RNA molecules that are transcribed from DNA but are not translated into proteins. Studies over the past decades have revealed that ncRNAs can be classified into small RNAs, long non-coding RNAs and circular RNAs by genomic size and structure. Accumulated evidences have eludicated the critical roles of these non-coding transcripts in regulating gene expression through transcription and translation, thereby shaping cellular function and disease pathogenesis. Notably, recent studies have investigated the function of ncRNAs as competitive endogenous RNAs (ceRNAs) that sequester miRNAs and modulate mRNAs expression. The ceRNAs network emerges as a pivotal regulatory function, with significant implications in various diseases such as cancer and neurodegenerative disease. Therefore, we highlighted multiple bioinformatics tools and databases that aim to predict ceRNAs interaction. Furthermore, we discussed limitations of using current technologies and potential improvement for ceRNAs network detection. Understanding of the dynamic interplay within ceRNAs may advance the biological comprehension, as well as providing potential targets for therapeutic intervention.

Predicting noncoding RNA and disease associations using multigraph contrastive learning

MiRNAs and lncRNAs are two essential noncoding RNAs. Predicting associations between noncoding RNAs and diseases can significantly improve the accuracy of early diagnosis.With the continuous breakthroughs in artificial intelligence, researchers increasingly use deep learning methods to predict associations. Nevertheless, most existing methods face two major issues: low prediction accuracy and the limitation of only being able to predict a single type of noncoding RNA-disease association. To address these challenges, this paper proposes a method called K-Means and multigraph Contrastive Learning for predicting associations among miRNAs, lncRNAs, and diseases (K-MGCMLD). The K-MGCMLD model is divided into four main steps. The first step is the construction of a heterogeneous graph. The second step involves down sampling using the K-means clustering algorithm to balance the positive and negative samples. The third step is to use an encoder with a Graph Convolutional Network (GCN) architecture to extract embedding vectors. Multigraph contrastive learning, including both local and global graph contrastive learning, is used to help the embedding vectors better capture the latent topological features of the graph. The fourth step involves feature reconstruction using the balanced positive and negative samples and the embedding vectors fed into an XGBoost classifier for multi-association classification prediction. Experimental results have shown that AUC value for miRNA-disease association is 0.9542, lncRNA-disease association is 0.9603, and lncRNA-miRNA association is 0.9687. Additionally, this study has conducted case analyses using K-MGCMLD, which has validated the associations of all the top 30 miRNAs predicted to be associated with lung cancer and Alzheimer's diseases.

CLHGNNMDA: Hypergraph Neural Network Model Enhanced by Contrastive Learning for miRNA-Disease Association Prediction

Numerous biological experiments have demonstrated that microRNA (miRNA) is involved in gene regulation within cells, and mutations and abnormal expression of miRNA can cause a myriad of intricate diseases. Forecasting the association between miRNA and diseases can enhance disease prevention and treatment and accelerate drug research, which holds considerable importance for the development of clinical medicine and drug research. This investigation introduces a contrastive learning-augmented hypergraph neural network model, termed CLHGNNMDA, aimed at predicting associations between miRNAs and diseases. Initially, CLHGNNMDA constructs multiple hypergraphs by leveraging diverse similarity metrics related to miRNAs and diseases. Subsequently, hypergraph convolution is applied to each hypergraph to extract feature representations for nodes and hyperedges. Following this, autoencoders are employed to reconstruct information regarding the feature representations of nodes and hyperedges and to integrate various features of miRNAs and diseases extracted from each hypergraph. Finally, a joint contrastive loss function is utilized to refine the model and optimize its parameters. The CLHGNNMDA framework employs multi-hypergraph contrastive learning for the construction of a contrastive loss function. This approach takes into account inter-view interactions and upholds the principle of consistency, thereby augmenting the model's representational efficacy. The results obtained from fivefold cross-validation substantiate that the CLHGNNMDA algorithm achieves a mean area under the receiver operating characteristic curve of 0.9635 and a mean area under the precision-recall curve of 0.9656. These metrics are notably superior to those attained by contemporary state-of-the-art methodologies.

SVM-LncRNAPro: An SVM-Based Method for Predicting Long Noncoding RNA Promoters

Long non-coding RNAs (lncRNAs) are closely associated with the regulation of gene expression, whose promoters play a crucial role in comprehensively understanding lncRNA regulatory mechanisms, functions and their roles in diseases. Due to limitations of the current techniques, accurately identifying lncRNA promoters remains a challenge. To address this challenge, we propose a support vector machine (SVM)-based method for predicting lncRNA promoters, called SVM-LncRNAPro. This method uses position-specific trinucleotide propensity based on single-strand (PSTNPss) to encode the DNA sequences and employs an SVM as the learning algorithm. The SVM-LncRNAPro achieves state-of-the-art performance with reduced complexity. Additionally, experiments demonstrate that this method exhibits a strong generalisation ability. For the convenience of academic research, we have made the source code of SVM-LncRNAPro publicly available. Researchers can download the code and perform the prediction of the lncRNA promoter via the following link: https://github.com/TG0F7/Prom/tree/master.

PPDAMEGCN: Predicting piRNA-Disease Associations Based on Multi-Edge Type Graph Convolutional Network

Recently, many studies have proven that Piwi-interacting RNAs (piRNAs) play key roles in various biological processes and also associate with human complicated diseases. Therefore, in order to accelerate the traditional biomedical experimental methods for determining piRNA-disease associations, many computational approaches have been proposed. However, piRNA-disease associations can be classified into known and unknown associations, each of which may provide distinct types of information. Traditional graph convolutional networks (GCNs) typically treat all edges in a graph as identical, overlooking the fact that different edge types may carry different signals and influence the learning process in unique ways. In this study, we also provide a new piRNA-disease association prediction method, called PPDAMEGCN, based on a multi-edge type graph convolutional network. First, we calculate the piRNA sequence similarity based on the piRNA sequence information and Smith-Waterman method. The disease semantic similarity is also computed by disease ontology (DO). In addition, we calculate the Gaussian interaction profile (GIP) kernel similarities of piRNA and diseases through the known piRNA-disease associations. Then, we construct the piRNA similarity network by integrating the piRNA's sequence similarity and GIP similarity. We also construct the disease similarity network by integrating disease's semantic similarity and GIP similarity. Finally, we obtain the piRNA and disease embeddings by the multi-edge type graph convolutional network model on the heterogenous piRNA-disease association network. The piRNA-disease pair association probability score is calculated by a multilayer perceptron (MLP) with its concatenated embedding. We also compare PPDAMEGCN to other piRNA-disease prediction methods. The experimental results show that our method outperforms compared methods.

Design and implementation of a radiomic-driven intelligent dental hospital diversion system utilizing multilabel imaging data

BACKGROUND

With the increasing burden of dental diseases and the limited availability of healthcare resources, traditional triage methods are inadequate in efficiently utilizing healthcare resources and meeting patient needs. The aim of this study is to develop an advanced triage system that combines oral radiomics and biological multi-omics data, which enables accurate departmental referral of patients by automatically interpreting biological information in oral X-ray images.

METHODS

Using a multi-label learning algorithm, we analyzed multi-omics data from 3,942 patients with oral diseases from three cohorts between July 1, 2023 and August 18, 2023, and continuously monitored classification accuracy (ACC) metrics.

RESULTS

In the test cohort and external validation cohort, we used the DenseNet121 model to analyze the multi-omics data and achieved classification accuracies of 0.80 and 0.82, respectively.

CONCLUSIONS

The main contribution of this study is to propose a new treatment process that incorporates biological multi-omics data, which reduces the workload of physicians while providing timely and accurate medical care to patients. Through comparative experiments, we demonstrate that the process is more efficient than existing processes. In addition, this intelligent triage system demonstrates high prediction accuracy in practical applications, providing new ideas and methods for biological multi-omics research.

A heterogeneous information network learning model with neighborhood-level structural representation for predicting lncRNA-miRNA interactions

Long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) are closely related to the treatment of human diseases. Traditional biological experiments often require time-consuming and labor-intensive in their search for mechanisms of disease. Computational methods are regarded as an effective way to predict unknown lncRNA-miRNA interactions (LMIs). However, most of them complete their tasks by mainly focusing on a single lncRNA-miRNA network without considering the complex mechanism between biomolecular in life activities, which are believed to be useful for improving the accuracy of LMI prediction. To address this, a heterogeneous information network (HIN) learning model with neighborhood-level structural representation, called HINLMI, to precisely identify LMIs. In particular, HINLMI first constructs a HIN by integrating nine interactions of five biomolecules. After that, different representation learning strategies are applied to learn the biological and network representations of lncRNAs and miRNAs in the HIN from different perspectives. Finally, HINLMI incorporates the XGBoost classifier to predict unknown LMIs using final embeddings of lncRNAs and miRNAs. Experimental results show that HINLMI yields a best performance on the real dataset when compared with state-of-the-art computational models. Moreover, several analysis experiments indicate that the simultaneous consideration of biological knowledge and network topology of lncRNAs and miRNAs allows HINLMI to accurately predict LMIs from a more comprehensive perspective. The promising performance of HINLMI also reveals that the utilization of rich heterogeneous information can provide an alternative insight for HINLMI to identify novel interactions between lncRNAs and miRNAs.

Unraveling the biological functions of UCEC: Insights from a prognostic signature model

BACKGROUND

Uterine corpus endometrial carcinoma (UCEC) is a prevalent gynecological tumor with a bleak prognosis. Anomalous glycosylation plays a pivotal role in tumorigenesis. Currently, there is a lack of prognostic signatures based on glycosylation-related genes for UCEC. Thus, our research aims to construct a predictive model and validate the correlation between relevant genes and biological functions.

METHODS

Using the TCGA database, we developed prognostic models and explored their relationships with survival outcomes. We further selected key genes to verify their expression in tissues and assess their impact on cellular behavior.

RESULTS

The clinical prognosis of the high-risk group was significantly worse than that of the low-risk group. The nomogram model accurately predicted UCEC patient prognosis. Additionally, we identified OLFML1 as a unique signature gene that can inhibit UCEC progression and reduce radiation resistance in vitro.

CONCLUSIONS

Our model, which is based on glycosylation-related genes in UCEC, effectively identifies high-risk patients and provides valuable prognostic information. In addition, OLFML1 acts as a tumor suppressor in UCEC and enhances radiosensitivity, suggesting a new potential target for improving therapeutic efficacy.

CVGAE: A Self-Supervised Generative Method for Gene Regulatory Network Inference Using Single-Cell RNA Sequencing Data

Gene regulatory network (GRN) inference based on single-cell RNA sequencing data (scRNAseq) plays a crucial role in understanding the regulatory mechanisms between genes. Various computational methods have been employed for GRN inference, but their performance in terms of network accuracy and model generalization is not satisfactory, and their poor performance is caused by high-dimensional data and network sparsity. In this paper, we propose a self-supervised method for gene regulatory network inference using single-cell RNA sequencing data (CVGAE). CVGAE uses graph neural network for inductive representation learning, which merges gene expression data and observed topology into a low-dimensional vector space. The well-trained vectors will be used to calculate mathematical distance of each gene, and further predict interactions between genes. In overall framework, FastICA is implemented to relief computational complexity caused by high dimensional data, and CVGAE adopts multi-stacked GraphSAGE layers as an encoder and an improved decoder to overcome network sparsity. CVGAE is evaluated on several single cell datasets containing four related ground-truth networks, and the result shows that CVGAE achieve better performance than comparative methods. To validate learning and generalization capabilities, CVGAE is applied in few-shot environment by change the ratio of train set and test set. In condition of few-shot, CVGAE obtains comparable or superior performance.

MSA-MaxNet: Multi-Scale Attention Enhanced Multi-Axis Vision Transformer Network for Medical Image Segmentation

Convolutional neural networks (CNNs) are well established in handling local features in visual tasks; yet, they falter in managing complex spatial relationships and long-range dependencies that are crucial for medical image segmentation, particularly in identifying pathological changes. While vision transformer (ViT) excels in addressing long-range dependencies, their ability to leverage local features remains inadequate. Recent ViT variants have merged CNNs to improve feature representation and segmentation outcomes, yet challenges with limited receptive fields and precise feature representation persist. In this work, we propose MSA-MaxNet. Specifically, our model utilises an encoder-decoder structure, using MaxViT blocks that apply multi-axis self-attention (Max-SA) as the encoder for local and global feature extraction. To restore the feature map's spatial resolution during upsampling operations, a symmetric MaxViT block-based decoder and upsampling layers are employed. To address the feature mismatches in the skip connections of UNet architecture, we introduce convolutional block attention module (CBAM). Furthermore, we design a multi-scale convolutional block attention module (MCBAM) based on CBAM, which utilises multi-scale features to enhance feature representation and refine the skip connection. We evaluate the segmentation performance of MSA-MaxNet on three publicly available medical imaging datasets, including Synapse for multi-organ segmentation, ACDC for cardiac analysis and Kvasir-SEG for gastrointestinal polyp detection. Notably, MSA-MaxNet achieves state-of-the-art (SOTA) Dice scores of 85.59% and 95.26% on Synapse and Kvasir-SEG datasets, respectively, with 40.28 M parameters. Additionally, we introduce two smaller versions of MSA-MaxNet to meet the demands of various scenarios. In summary, our work provides a robust framework for diverse medical imaging tasks, offering potential applications in early cancer detection, cardiovascular disease diagnosis and comprehensive organ-level assessments.

Cross-modal embedding integrator for disease-gene/protein association prediction using a multi-head attention mechanism

Knowledge graphs, powerful tools that explicitly transfer knowledge to machines, have significantly advanced new knowledge inferences. Discovering unknown relationships between diseases and genes/proteins in biomedical knowledge graphs can lead to the identification of disease development mechanisms and new treatment targets. Generating high-quality representations of biomedical entities is essential for successfully predicting disease-gene/protein associations. We developed a computational model that predicts disease-gene/protein associations using the Precision Medicine Knowledge Graph, a biomedical knowledge graph. Embeddings of biomedical entities were generated using two different methods-a large language model (LLM) and the knowledge graph embedding (KGE) algorithm. The LLM utilizes information obtained from massive amounts of text data, whereas the KGE algorithm relies on graph structures. We developed a disease-gene/protein association prediction model, "Cross-Modal Embedding Integrator (CMEI)," by integrating embeddings from different modalities using a multi-head attention mechanism. The area under the receiver operating characteristic curve of CMEI was 0.9662 (± 0.0002) in predicting disease-gene/protein associations. In conclusion, we developed a computational model that effectively predicts disease-gene/protein associations. CMEI may contribute to the identification of disease development mechanisms and new treatment targets.

MEAs-Filter: a novel filter framework utilizing evolutionary algorithms for cardiovascular diseases diagnosis

Cardiovascular disease management often involves adjusting medication dosage based on changes in electrocardiogram (ECG) signals' waveform and rhythm. However, the diagnostic utility of ECG signals is often hindered by various types of noise interference. In this work, we propose a novel filter based on a multi-engine evolution framework named MEAs-Filter to address this issue. Our approach eliminates the need for predefined dimensions and allows adaptation to diverse ECG morphologies. By leveraging state-of-the-art optimization algorithms as evolution engine and incorporating prior information inputs from classical filters, MEAs-Filter achieves superior performance while minimizing order. We evaluate the effectiveness of MEAs-Filter on a real ECG database and compare it against commonly used filters such as the Butterworth, Chebyshev filters, and evolution algorithm-based (EA-based) filters. The experimental results indicate that MEAs-Filter outperforms other filters by achieving a reduction of approximately 30% to 60% in terms of the loss function compared to the other algorithms. In denoising experiments conducted on ECG waveforms across various scenarios, MEAs-Filter demonstrates an improvement of approximately 20% in signal-to-noise (SNR) ratio and a 9% improvement in correlation. Moreover, it does not exhibit higher losses of the R-wave compared to other filters. These findings highlight the potential of MEAs-Filter as a valuable tool for high-fidelity extraction of ECG signals, enabling accurate diagnosis in the field of cardiovascular diseases.

Introducing TEC-LncMir for prediction of lncRNA-miRNA interactions through deep learning of RNA sequences

The interactions between long noncoding RNA (lncRNA) and microRNA (miRNA) play critical roles in life processes, highlighting the necessity to enhance the performance of state-of-the-art models. Here, we introduced TEC-LncMir, a novel approach for predicting lncRNA-miRNA interaction using Transformer Encoder and convolutional neural networks (CNNs). TEC-LncMir treats lncRNA and miRNA sequences as natural languages, encodes them using the Transformer Encoder, and combines representations of a pair of microRNA and lncRNA into a contact tensor (a three-dimensional array). Afterward, TEC-LncMir treats the contact tensor as a multi-channel image, utilizes a four-layer CNN to extract the contact tensor's features, and then uses these features to predict the interaction between the pair of lncRNA and miRNA. We applied a series of comparative experiments to demonstrate that TEC-LncMir significantly improves lncRNA-miRNA interaction prediction, compared with existing state-of-the-art models. We also trained TEC-LncMir utilizing a large training dataset, and as expected, TEC-LncMir achieves unprecedented performance. Moreover, we integrated miRanda into TEC-LncMir to show the secondary structures of high-confidence interactions. Finally, we utilized TEC-LncMir to identify microRNAs interacting with lncRNA NEAT1, where NEAT1 performs as a competitive endogenous RNA of the microRNAs' targets (mRNAs) in brain cells. We also demonstrated the regulatory mechanism of NEAT1 in Alzheimer's disease via transcriptome analysis and sequence alignment analysis. Overall, our results demonstrate the effectivity of TEC-LncMir, suggest a potential regulation of miRNAs by NEAT1 in Alzheimer's disease, and take a significant step forward in lncRNA-miRNA interaction prediction.

The improved de Bruijn graph for multitask learning: predicting functions, subcellular localization, and interactions of noncoding RNAs

Noncoding RNA refers to RNA that does not encode proteins. The lncRNA and miRNA it contains play crucial regulatory roles in organisms, and their aberrant expression is closely related to various diseases. Traditional experimental methods for validating the interactions of these RNAs have limitations, and existing prediction models exhibit relatively limited functionality, relying on isolated feature extraction and performing poorly in handling various types of small sample tasks. This paper proposes an improved de Bruijn graph that can inject RNA structural information into the graph while preserving sequence information. Furthermore, the improved de Bruijn graph enables graph neural networks to learn broader dependencies and correlations among data by introducing richer edge relationships. Meanwhile, the multitask learning model, DVMnet, proposed in this paper can handle multiple related tasks, and we optimize model parameters by integrating the total loss of three tasks. This enables multitask prediction of RNA interactions, disease associations, and subcellular localization. Compared with the best existing models in this field, DVMnet has achieved the best performance with a 3% improvement in the area under the curve value and demonstrates robust results in predicting diseases and subcellular localization. The improved de Bruijn graph is also applicable to various scenarios and can unify the sequence and structural information of various nucleic acids into a single graph.

HERC5: a comprehensive in silico analysis of its diagnostic, prognostic, and therapeutic potential in cancer

HERC5, a vital protein in the HERC family, plays crucial roles in immune response, cancer progression, and antiviral defense. This bioinformatic study comprehensively assessed HERC5's significance across various malignancies by analyzing its gene expression, immune and molecular subtype expressions, target proteins, biological functions, and prognostic and diagnostic values in pan-cancer. We further examined its correlation with clinical features, co-expressed and differentially expressed genes, and prognosis in clinical subgroups, focusing on endometrial cancer (UCEC). Our findings showed that HERC5 RNA is expressed at low levels in most cancers and significantly differs across immune and molecular subtypes. HERC5 accurately predicts cancer and correlates with most cancer prognoses. In UCEC, HERC5 was significantly associated with age, hormonal status, clinical stage, treatment status, and metastasis. Elevated HERC5 expression was linked to worse progression-free interval, disease-specific survival, and overall survival in UCEC, particularly in diverse clinical subgroups. Significant differences in HERC5 expression were also observed in various human cancer cell line validations. In summary, HERC5 may be a critical biomarker for pan-cancer prognosis, progression, and diagnosis, as well as a promising new target for cancer therapy.

Prediction of Potential miRNA-Disease Associations Based on a Masked Graph Autoencoder

Biomedical evidence has demonstrated the relevance of microRNA (miRNA) dysregulation in complex human diseases, and determining the relationship between miRNAs and diseases can aid in the early detection and prevention of diseases. Traditional biological experimental methods have the disadvantages of high cost and low efficiency, which are well compensated by computational methods. However, many computational methods have the challenge of excessively focusing on the neighbor relationship, ignoring the structural information of the graph, and belittling the redundant information of the graph structure. This study proposed a computational model based on a graph-masking autoencoder named MGAEMDA. MGAEMDA is an asymmetric framework in which the encoder maps partially observed graphs into latent representations. The decoder reconstructs the masked structural information based on the edge and node levels and combines it with linear matrices to obtain the result. The empirical results on the two datasets reveal that the MGAEMDA model performs better than its counterparts. We also demonstrated the predictive performance of MGAEMDA using a case study of four diseases, and all the top 30 predicted miRNAs were validated in the database, providing further evidence of the excellent performance of the model.

Artificial intelligence-based evaluation of prognosis in cirrhosis

Cirrhosis represents a significant global health challenge, characterized by high morbidity and mortality rates that severely impact human health. Timely and precise prognostic assessments of liver cirrhosis are crucial for improving patient outcomes and reducing mortality rates as they enable physicians to identify high-risk patients and implement early interventions. This paper features a thorough literature review on the prognostic assessment of liver cirrhosis, aiming to summarize and delineate the present status and constraints associated with the application of traditional prognostic tools in clinical settings. Among these tools, the Child-Pugh and Model for End-Stage Liver Disease (MELD) scoring systems are predominantly utilized. However, their accuracy varies significantly. These systems are generally suitable for broad assessments but lack condition-specific applicability and fail to capture the risks associated with dynamic changes in patient conditions. Future research in this field is poised for deep exploration into the integration of artificial intelligence (AI) with routine clinical and multi-omics data in patients with cirrhosis. The goal is to transition from static, unimodal assessment models to dynamic, multimodal frameworks. Such advancements will not only improve the precision of prognostic tools but also facilitate personalized medicine approaches, potentially revolutionizing clinical outcomes.

The prognostic value and immunological role of calcium/calmodulin dependent protein kinase kinase 2 (CAMKK2) in pan-cancer study

A thorough assessment of calcium/calmodulin dependent protein kinase kinase 2 (CAMKK2) in pan-cancer studies is currently absent. We integrate multi-omics and clinical data to conduct a molecular landscape of CAMKK2. Gene variation results revealed abnormal high frequency mutations of CAMKK2 in uterine corpus endometrial carcinoma, while expression level analysis demonstrated relatively high expression of CAMKK2 in prostate adenocarcinoma. The aberrant expression of CAMKK2 was found to be predictive of survival outcomes in several cancer types. Additionally, we identified potential regulators of CAMKK2 expression, including miRNAs such as miR.129.1.3p, as well as small-molecule drugs such as EPZ004777, which significantly correlated with CAMKK2 expression. Single-cell transcriptome analysis of kidney renal clear cell carcinoma further revealed a significantly higher expression of CAMKK2 in and monocyte and macrophage M1. Furthermore, in the kidney renal clear cell carcinoma IMvigor210 cohort, patients ongoing immunotherapy with higher CAMKK2 expression experienced a significantly longer median overall survival, but it was observed that in bladder urothelial carcinoma GSE176307 and skin cutaneous melanoma GSE78220 cohorts, CAMKK2 might significantly prolong overall survival. Briefly, CAMKK2 emerges as a promising molecular biomarker that holds potential implications for prognostic evaluation and predicting the effectiveness of immunotherapy across cancers.

LncRNA-miRNA interactions prediction based on meta-path similarity and Gaussian kernel similarity

Long non-coding RNAs (lncRNAs) and microRNAs (miRNAs) are two typical types of non-coding RNAs that interact and play important regulatory roles in many animal organisms. Exploring the unknown interactions between lncRNAs and miRNAs contributes to a better understanding of their functional involvement. Currently, studying the interactions between lncRNAs and miRNAs heavily relies on laborious biological experiments. Therefore, it is necessary to design a computational method for predicting lncRNA-miRNA interactions. In this work, we propose a method called MPGK-LMI, which utilizes a graph attention network (GAT) to predict lncRNA-miRNA interactions in animals. First, we construct a meta-path similarity matrix based on known lncRNA-miRNA interaction information. Then, we use GAT to aggregate the constructed meta-path similarity matrix and the computed Gaussian kernel similarity matrix to update the feature matrix with neighbourhood information. Finally, a scoring module is used for prediction. By comparing with three state-of-the-art algorithms, MPGK-LMI achieves the best results in terms of performance, with AUC value of 0.9077, AUPR of 0.9327, ACC of 0.9080, F1-score of 0.9143 and precision of 0.8739. These results validate the effectiveness and reliability of MPGK-LMI. Additionally, we conduct detailed case studies to demonstrate the effectiveness and feasibility of our approach in practical applications. Through these empirical results, we gain deeper insights into the functional roles and mechanisms of lncRNA-miRNA interactions, providing significant breakthroughs and advancements in this field of research. In summary, our method not only outperforms others in terms of performance but also establishes its practicality and reliability in biological research through real-case analysis, offering strong support and guidance for future studies and applications.

Predicting the potential associations between circRNA and drug sensitivity using a multisource feature-based approach

The unique non-coding RNA molecule known as circular RNA (circRNA) is distinguished from conventional linear RNA by having a longer half-life, greater degree of conservation and inherent solidity. Extensive research has demonstrated the profound impact of circRNA expression on cellular drug sensitivity and therapeutic efficacy. There is an immediate need for the creation of efficient computational techniques to anticipate the potential correlations between circRNA and drug sensitivity, as classical biological research approaches are time-consuming and costly. In this work, we introduce a novel deep learning model called SNMGCDA, which aims to forecast the relationships between circRNA and drug sensitivity. SNMGCDA incorporates a diverse range of similarity networks, enabling the derivation of feature vectors for circRNAs and drugs using three distinct calculation methods. First, we utilize a sparse autoencoder for the extraction of drug characteristics. Subsequently, the application of non-negative matrix factorization (NMF) enables the identification of relationships between circRNAs and drugs based on their shared features. Additionally, the multi-head graph attention network is employed to capture the characteristics of circRNAs. After acquiring the characteristics from these three separate components, we combine them to form a unified and inclusive feature vector for each cluster of circRNA and drug. Finally, the relevant feature vectors and labels are inputted into a multilayer perceptron (MLP) to make predictions. The outcomes of the experiment, obtained through 5-fold cross-validation (5-fold CV) and 10-fold cross-validation (10-fold CV), demonstrate SNMGCDA outperforms five other state-of-art methods in terms of performance. Additionally, the majority of case studies have predominantly confirmed newly discovered correlations by SNMGCDA, thereby emphasizing its reliability in predicting potential relationships between circRNAs and drugs.

Connecting the dots: Computational network analysis for disease insight and drug repurposing

Network biology is a powerful framework for studying the structure, function, and dynamics of biological systems, offering insights into the balance between health and disease states. The field is seeing rapid progress in all of its aspects: data availability, network synthesis, network analytics, and impactful applications in medicine and drug development. We review the most recent and significant results in network biomedicine, with a focus on the latest data, analytics, software resources, and applications in medicine. We also discuss what in our view are the likely directions of impactful development over the next few years.

Dual-neighbourhood information aggregation and feature fusion for prediction of miRNA-disease association

Studying the intricate relationship between miRNAs and diseases is crucial to prevent and treat miRNA-related disorders. Existing computational methods often overlook the importance of features of different nodes and the propagation of features among heterogeneous nodes. Many prediction models focus only on the feature coding of miRNA and diseases and ignore the importance of feature aggregation. We propose a prediction method via dual-neighbourhood feature aggregation and feature fusion, which uses multiple sources of information, aggregates information on homogeneous and heterogeneous nodes and fuses learned features to predict multiple representations of disease nodes. We constructed similarity networks of multiple homogeneous nodes based on different similarity computation methods respectively, and fused the attention mechanism by using graph convolutional networks to obtain information of different levels of importance. To alleviate the problem of sparse connectivity in the dataset, we built a two-neighbourhood heterogeneous graph neural network model to integrate the homogeneous similarity network into a miRNA-disease heterogeneous network by using known miRNA-disease association information. We used the neighbourhood information associated with the nodes in the network to perform feature aggregation. In addition, we used a feature fusion module to learn the importance of different types of nodes to predict miRNA-disease associations. Our experimental results on the Human microRNA Disease Database (HMDD v3.2) show that the model demonstrates superior performance. This work demonstrates the capability of our model to identify potential miRNAs associated with diseases through a case study of two common cancers.

ACLNDA: an asymmetric graph contrastive learning framework for predicting noncoding RNA-disease associations in heterogeneous graphs

Noncoding RNAs (ncRNAs), including long noncoding RNAs (lncRNAs) and microRNAs (miRNAs), play crucial roles in gene expression regulation and are significant in disease associations and medical research. Accurate ncRNA-disease association prediction is essential for understanding disease mechanisms and developing treatments. Existing methods often focus on single tasks like lncRNA-disease associations (LDAs), miRNA-disease associations (MDAs), or lncRNA-miRNA interactions (LMIs), and fail to exploit heterogeneous graph characteristics. We propose ACLNDA, an asymmetric graph contrastive learning framework for analyzing heterophilic ncRNA-disease associations. It constructs inter-layer adjacency matrices from the original lncRNA, miRNA, and disease associations, and uses a Top-K intra-layer similarity edges construction approach to form a triple-layer heterogeneous graph. Unlike traditional works, to account for both node attribute features (ncRNA/disease) and node preference features (association), ACLNDA employs an asymmetric yet simple graph contrastive learning framework to maximize one-hop neighborhood context and two-hop similarity, extracting ncRNA-disease features without relying on graph augmentations or homophily assumptions, reducing computational cost while preserving data integrity. Our framework is capable of being applied to a universal range of potential LDA, MDA, and LMI association predictions. Further experimental results demonstrate superior performance to other existing state-of-the-art baseline methods, which shows its potential for providing insights into disease diagnosis and therapeutic target identification. The source code and data of ACLNDA is publicly available at https://github.com/AI4Bread/ACLNDA.

Resveratrol shields against cisplatin-induced ototoxicity through epigenetic lncRNA GAS5 modulation of miR-455-5p/PTEN pathway

BACKGROUND

Our previous research demonstrated that resveratrol counters DDP-induced ototoxicity by upregulating miR-455-5p, which targets PTEN. This study aimed to elucidate the underlying mechanisms involving GAS5 and DNA methyltransferase 1 (DNMT1) in resveratrol's protective action.

METHODS

A luciferase reporter assay and RNA immunoprecipitation (RIP) assay were employed to study the binding between GAS5 and miR-455-5p, as well as between miR-455-5p and PTEN. HEI-OC1 cells treated with DDP were transfected with vectors for GAS5, si-GAS5, DNMT1, si-DNMT1, and miR-455-5p mimics, as well as PTEN. Subsequently, they were treated with resveratrol and exposed to DDP, both separately and in combination. The distribution of CpG islands in the GAS5 promoter was identified using MethyPrimer, and methylation-specific PCR (MSP) was conducted to determine the methylation levels of GAS5. Chromatin immunoprecipitation (ChIP) was utilized to examine the interaction between DNMT1 and GAS5. The viability of HEI-OC1 cells, catalase (CAT) activity, apoptosis, and ROS levels were assessed using the CCK-8 assay, CAT assay, TUNEL staining, and flow cytometry, respectively. An in vivo mouse model was developed to measure auditory brainstem response (ABR) thresholds, while RT-qPCR and Western blot analysis were employed to evaluate molecular levels.

RESULTS

Our study discovered that GAS5 acts as a sponge for miR-455-5p, thereby increasing PTEN expression in DDP-treated HEI-OC1 cells. This process was reversed upon treatment with resveratrol. Importantly, DNMT1 promoted the methylation of the GAS5 promoter, leading to the suppression of GAS5 expression. This suppression enhanced the effectiveness of resveratrol in combating DDP-induced apoptosis and ROS in HEI-OC1 cells and amplified its protective effect against DDP's ototoxicity in vivo.

CONCLUSIONS

Our research emphasizes the significance of the DNMT1/GAS5/miR-455-5p/PTEN axis as a promising new route to boost resveratrol's effectiveness against DDP-induced ototoxicity.

Identifying crucial lncRNAs and mRNAs in hypoxia-induced A549 lung cancer cells and investigating their underlying mechanisms via high-throughput sequencing

BACKGROUND

Rapid proliferation and outgrowth of tumor cells frequently result in localized hypoxia, which has been implicated in the progression of lung cancer. The present study aimed to identify key long non-coding RNAs (lncRNAs) and messenger RNAs (mRNAs) involved in hypoxia-induced A549 lung cancer cells, and to investigate their potential underlying mechanisms of action.

METHODS

High-throughput sequencing was utilized to obtain the expression profiles of lncRNA and mRNA in both hypoxia-induced and normoxia A549 lung cancer cells. Subsequently, a bioinformatics analysis was conducted on the differentially expressed molecules, encompassing functional enrichment analysis, protein-protein interaction (PPI) network analysis, and competitive endogenous RNA (ceRNA) analysis. Finally, the alterations in the expression of key lncRNAs and mRNAs were validated using real-time quantitative PCR (qPCR).

RESULTS

In the study, 1155 mRNAs and 215 lncRNAs were identified as differentially expressed between the hypoxia group and the normoxia group. Functional enrichment analysis revealed that the differentially expressed mRNAs were significantly enriched in various pathways, including the p53 signaling pathway, DNA replication, and the cell cycle. Additionally, key lncRNA-miRNA-mRNA relationships, such as RP11-58O9.2-hsa-miR-6749-3p-XRCC2 and SNAP25-AS1-hsa-miR-6749-3p-TENM4, were identified. Notably, the qPCR assay demonstrated that the expression of SNAP25-AS1, RP11-58O9.2, TENM4, and XRCC2 was downregulated in the hypoxia group compared to the normoxia group. Conversely, the expression of LINC01164, VLDLR-AS1, RP11-14I17.2, and CDKN1A was upregulated.

CONCLUSION

Our findings suggest a potential involvement of SNAP25-AS1, RP11-58O9.2, TENM4, XRCC2, LINC01164, VLDLR-AS1, RP11-14I17.2, and CDKN1A in the development of hypoxia-induced lung cancer. These key lncRNAs and mRNAs exert their functions through diverse mechanisms, including the competitive endogenous RNA (ceRNA) pathway.

ANS-SCMC: A matrix completion method based on adaptive neighbourhood similarity and sparse constraints for predicting microbe-disease associations

The use of matrix completion methods to predict the association between microbes and diseases can effectively improve treatment efficiency. However, the similarity measures used in the existing methods are often influenced by various factors such as neighbourhood size, choice of similarity metric, or multiple parameters for similarity fusion, making it challenging. Additionally, matrix completion is currently limited by the sparsity of the initial association matrix, which restricts its predictive performance. To address these problems, we propose a matrix completion method based on adaptive neighbourhood similarity and sparse constraints (ANS-SCMC) for predict microbe-disease potential associations. Adaptive neighbourhood similarity learning dynamically uses the decomposition results as effective information for the next learning iteration by simultaneously performing local manifold structure learning and decomposition. This approach effectively preserves fine local structure information and avoids the influence of weight parameters directly involved in similarity measurement. Additionally, the sparse constraint-based matrix completion approach can better handle the sparsity challenge in the association matrix. Finally, the algorithm we proposed has achieved significantly higher predictive performance in the validation compared to several commonly used prediction methods proposed to date. Furthermore, in the case study, the prediction algorithm achieved an accuracy of up to 80% for the top 10 microbes associated with type 1 diabetes and 100% for Crohn's disease respectively.

Predicting circRNA-RBP Binding Sites Using a Hybrid Deep Neural Network

Circular RNAs (circRNAs) are non-coding RNAs generated by reverse splicing. They are involved in biological process and human diseases by interacting with specific RNA-binding proteins (RBPs). Due to traditional biological experiments being costly, computational methods have been proposed to predict the circRNA-RBP interaction. However, these methods have problems of single feature extraction. Therefore, we propose a novel model called circ-FHN, which utilizes only circRNA sequences to predict circRNA-RBP interactions. The circ-FHN approach involves feature coding and a hybrid deep learning model. Feature coding takes into account the physicochemical properties of circRNA sequences and employs four coding methods to extract sequence features. The hybrid deep structure comprises a convolutional neural network (CNN) and a bidirectional gated recurrent unit (BiGRU). The CNN learns high-level abstract features, while the BiGRU captures long-term dependencies in the sequence. To assess the effectiveness of circ-FHN, we compared it to other computational methods on 16 datasets and conducted ablation experiments. Additionally, we conducted motif analysis. The results demonstrate that circ-FHN exhibits exceptional performance and surpasses other methods. circ-FHN is freely available at https://github.com/zhaoqi106/circ-FHN .

Synchronous Mutual Learning Network and Asynchronous Multi-Scale Embedding Network for miRNA-Disease Association Prediction

MicroRNA (miRNA) serves as a pivotal regulator of numerous cellular processes, and the identification of miRNA-disease associations (MDAs) is crucial for comprehending complex diseases. Recently, graph neural networks (GNN) have made significant advancements in MDA prediction. However, these methods tend to learn one type of node representation from a single heterogeneous network, ignoring the importance of multiple network topologies and node attributes. Here, we propose SMDAP (Sequence hierarchical modeling-based Mirna-Disease Association Prediction framework), a novel GNN-based framework that incorporates multiple network topologies and various node attributes including miRNA seed and full-length sequences to predict potential MDAs. Specifically, SMDAP consists of two types of MDA representation: following a heterogeneous pattern, we construct a transfer learning-like synchronous mutual learning network to learn the first MDA representation in conjunction with the miRNA seed sequence. Meanwhile, following a homogeneous pattern, we design a subgraph-inspired asynchronous multi-scale embedding network to obtain the second MDA representation based on the miRNA full-length sequence. Subsequently, an adaptive fusion approach is designed to combine the two branches such that we can score the MDAs by the downstream classifier and infer novel MDAs. Comprehensive experiments demonstrate that SMDAP integrates the advantages of multiple network topologies and node attributes into two branch representations. Moreover, the area under the receiver operating characteristic curve is 0.9622 on DB1, which is a 5.06% increase from the baselines. The area under the precision-recall curve is 0.9777, which is a 7.33% increase from the baselines. In addition, case studies on three human cancers validated the predictive performance of SMDAP. Overall, SMDAP represents a powerful tool for MDA prediction.

RDGAN: Prediction of circRNA-Disease Associations via Resistance Distance and Graph Attention Network

As a series of single-stranded RNAs, circRNAs have been implicated in numerous diseases and can serve as valuable biomarkers for disease therapy and prevention. However, traditional biological experiments demand significant time and effort. Therefore, various computational methods have been proposed to address this limitation, but how to extract features more comprehensively remains a challenge that needs further attention in the future. In this study, we propose a unique approach to predict circRNA-disease associations based on resistance distance and graph attention network (RDGAN). First, the associations of circRNA and disease are obtained by fusing multiple databases, and resistance distance as a similarity matrix is used to further deal with the sparse of the similarity matrices. Then the circRNA-disease heterogeneous network is constructed based on the similiarity of circRNA-circRNA, disease-disease and the known circRNA-disease adjacency matric. Second, leveraging the three neural network modules-ResGatedGraphConv, GAT and MFConv-we gather node feature embeddings collected from the heterogeneous network. Subsequently, all the characteristics are supplied to the self-attention mechanism to predict new potential connections. Finally, our model obtains a remarkable AUC value of 0.9630 through five-fold cross-validation, surpassing the predictive performance of the other eight state-of-the-art models.

SeFilter-DIA: Squeeze-and-Excitation Network for Filtering High-Confidence Peptides of Data-Independent Acquisition Proteomics

Mass spectrometry is crucial in proteomics analysis, particularly using Data Independent Acquisition (DIA) for reliable and reproducible mass spectrometry data acquisition, enabling broad mass-to-charge ratio coverage and high throughput. DIA-NN, a prominent deep learning software in DIA proteome analysis, generates peptide results but may include low-confidence peptides. Conventionally, biologists have to manually screen peptide fragment ion chromatogram peaks (XIC) for identifying high-confidence peptides, a time-consuming and subjective process prone to variability. In this study, we introduce SeFilter-DIA, a deep learning algorithm, aiming at automating the identification of high-confidence peptides. Leveraging compressed excitation neural network and residual network models, SeFilter-DIA extracts XIC features and effectively discerns between high and low-confidence peptides. Evaluation of the benchmark datasets demonstrates SeFilter-DIA achieving 99.6% AUC on the test set and 97% for other performance indicators. Furthermore, SeFilter-DIA is applicable for screening peptides with phosphorylation modifications. These results demonstrate the potential of SeFilter-DIA to replace manual screening, providing an efficient and objective approach for high-confidence peptide identification while mitigating associated limitations.

Calcium homeostasis and endometriosis: A Mendelian randomization study

Background

Previous observational studies have investigated the correlation between calcium homeostasis modulator levels and endometriosis risk. Yet, the genetic association between body calcium homeostasis and endometriosis risk remains to be elucidated.

Methods

Four tiers of Mendelian randomization (MR) analysis were conducted, as follows: (1) single univariate MR and (2) multivariate MR to evaluate the correlation between calcium homeostasis regulators and endometriosis; (3) inverse MR to probe the influence of endometriosis on body calcium homeostasis; (4) two-sample MR to scrutinize the connection between calcium levels and endometriosis categories.

Results

The two-sample MR analysis unveiled a robust positive correlation between genetically inferred calcium levels and endometriosis risk (IVW: OR = 1.15, 95 % CI: 1.02-1.29, p = 0.018). The MVMR analysis corroborated that the positive correlation of calcium levels with endometriosis persisted after adjusting for 25(OH)D and PTH. The inverse MR analysis disclosed a significant association between endometriosis and 25(OH)D (β = 0.01, 95 % CI: 0.00-0.02, p = 0.007) and calcium (β = 0.02, 95 % CI: 0.00-0.04, p = 0.035). The two-sample MR analysis further demonstrated that calcium levels were positively linked solely to endometriosis of uterus (i.e. adenomyosis, IVW: OR = 1.23, 95 % CI: 1.01-1.49, p = 0.038), with no evidence of a influence on other endometriosis categories.

Conclusions

This study, employing various types of MR, offers some genetic evidence for the relationship between calcium homeostasis and endometriosis, augmenting the current comprehension of the complex association between the two and suggesting that calcium levels are a risk factor for endometriosis. These findings provide a unique genetic perspective that may spur further investigation and may inform future strategies for managing patients with endometriosis.

Exploration of microRNAs as transcriptional regulator in mumps virus infection through computational studies

Mumps is a common childhood infection caused by the mumps virus (MuV). Aseptic meningitis and encephalitis are usual symptoms of mumps together with orchitis and oophoritis that can arise in males and females, respectively. We have used computational tools: RNA22, miRanda and psRNATarget to predict the microRNA-mRNA binding sites to find the putative microRNAs playing role in the host response to mumps virus infection. Our computational studies indicate that hsa-mir-3155a is most likely involved in mumps infection. This was further investigated by the prediction of binding sites of hsa-mir-3155a to the MuV genome. Additionally, structure prediction using MC-Fold and MC-Sym, respectively has been applied to predict the 3D structures of miRNA and mRNA. The miRNA-mRNA interaction profile between has been confirmed through molecular docking simulation studies. Taken together, the putative miRNA (hsa_miR_6794_5p) has been found to be most likely involved in the regulation of transcriptional activity in the MuV infection.

An ensemble approach for circular RNA-disease association prediction using variational autoencoder and genetic algorithm

Circular RNAs (circRNAs) are endogenous non-coding RNAs with a covalently closed loop structure. They have many biological functions, mainly regulatory ones. They have been proven to modulate protein-coding genes in the human genome. CircRNAs are linked to various diseases like Alzheimer's disease, diabetes, atherosclerosis, Parkinson's disease and cancer. Identifying the associations between circular RNAs and diseases is essential for disease diagnosis, prevention, and treatment. The proposed model, based on the variational autoencoder and genetic algorithm circular RNA disease association (VAGA-CDA), predicts novel circRNA-disease associations. First, the experimentally verified circRNA-disease associations are augmented with the synthetic minority oversampling technique (SMOTE) and regenerated using a variational autoencoder, and feature selection is applied to these vectors by a genetic algorithm (GA). The variational autoencoder effectively extracts features from the augmented samples. The optimized feature selection of the genetic algorithm effectively carried out dimensionality reduction. The sophisticated feature vectors extracted are then given to a Random Forest classifier to predict new circRNA-disease associations. The proposed model yields an AUC value of 0.9644 and 0.9628 under 5-fold and 10-fold cross-validations, respectively. The results of the case studies indicate the robustness of the proposed model.

NPI-DCGNN: An Accurate Tool for Identifying ncRNA-Protein Interactions Using a Dual-Channel Graph Neural Network

Noncoding RNA (NcRNA)-protein interactions (NPIs) play fundamentally important roles in carrying out cellular activities. Although various predictors based on molecular features and graphs have been published to boost the identification of NPIs, most of them often ignore the information between known NPIs or exhibit insufficient learning ability from graphs, posing a significant challenge in effectively identifying NPIs. To develop a more reliable and accurate predictor for NPIs, in this article, we propose NPI-DCGNN, an end-to-end NPI predictor based on a dual-channel graph neural network (DCGNN). NPI-DCGNN initially treats the known NPIs as an ncRNA-protein bipartite graph. Subsequently, for each ncRNA-protein pair, NPI-DCGNN extracts two local subgraphs centered around the ncRNA and protein, respectively, from the bipartite graph. After that, it utilizes a dual-channel graph representation learning layer based on GNN to generate high-level feature representations for the ncRNA-protein pair. Finally, it employs a fully connected network and output layer to predict whether an interaction exists between the pair of ncRNA and protein. Experimental results on four experimentally validated datasets demonstrate that NPI-DCGNN outperforms several state-of-the-art NPI predictors. Our case studies on the NPInter database further demonstrate the prediction power of NPI-DCGNN in predicting NPIs. With the availability of the source codes (https://github.com/zhangxin11111/NPI-DCGNN), we anticipate that NPI-DCGNN could facilitate the studies of ncRNA interactome by providing highly reliable NPI candidates for further experimental validation.

Predicting potential microbe-disease associations based on dual branch graph convolutional network

Studying the association between microbes and diseases not only aids in the prevention and diagnosis of diseases, but also provides crucial theoretical support for new drug development and personalized treatment. Due to the time-consuming and costly nature of laboratory-based biological tests to confirm the relationship between microbes and diseases, there is an urgent need for innovative computational frameworks to anticipate new associations between microbes and diseases. Here, we propose a novel computational approach based on a dual branch graph convolutional network (GCN) module, abbreviated as DBGCNMDA, for identifying microbe-disease associations. First, DBGCNMDA calculates the similarity matrix of diseases and microbes by integrating functional similarity and Gaussian association spectrum kernel (GAPK) similarity. Then, semantic information from different biological networks is extracted by two GCN modules from different perspectives. Finally, the scores of microbe-disease associations are predicted based on the extracted features. The main innovation of this method lies in the use of two types of information for microbe/disease similarity assessment. Additionally, we extend the disease nodes to address the issue of insufficient features due to low data dimensionality. We optimize the connectivity between the homogeneous entities using random walk with restart (RWR), and then use the optimized similarity matrix as the initial feature matrix. In terms of network understanding, we design a dual branch GCN module, namely GlobalGCN and LocalGCN, to fine-tune node representations by introducing side information, including homologous neighbour nodes. We evaluate the accuracy of the DBGCNMDA model using five-fold cross-validation (5-fold-CV) technique. The results show that the area under the receiver operating characteristic curve (AUC) and area under the precision versus recall curve (AUPR) of the DBGCNMDA model in the 5-fold-CV are 0.9559 and 0.9630, respectively. The results from the case studies using published experimental data confirm a significant number of predicted associations, indicating that DBGCNMDA is an effective tool for predicting potential microbe-disease associations.