HMDD v4.0: a database for experimentally supported human microRNA-disease associations

OligoM-Cancer: A multidimensional information platform for deep phenotyping of heterogenous oligometastatic cancer

Patients with oligometastatic cancer (OMC) exhibit better response to local therapeutic interventions and a more treatable tendency than those with polymetastatic cancers. However, studies on OMC are limited and lack effective integration for systematic comparison and personalized application, and the diagnosis and precise treatment of OMC remain controversial. The application of large language models in medicine remains challenging because of the requirement of high-quality medical data. Moreover, these models must be enhanced using precise domain-specific knowledge. Therefore, we developed the OligoM-Cancer platform (http://oligo.sysbio.org.cn), pioneering knowledge curation that depicts various aspects of oligometastases spectrum, including markers, diagnosis, prognosis, and therapy choices. A user-friendly website was developed using HTML, FLASK, MySQL, Bootstrap, Echarts, and JavaScript. This platform encompasses comprehensive knowledge and evidence of phenotypes and their associated factors. With 4059 items of literature retrieved, OligoM-Cancer includes 1345 valid publications and 393 OMC-associated factors. Additionally, the included clinical assistance tools enhance the interpretability and credibility of clinical translational practice. OligoM-Cancer facilitates knowledge-guided modeling for deep phenotyping of OMC and potentially assists large language models in supporting specialised oligometastasis applications, thereby enhancing their generalization and reliability.

DCSGMDA: A dual-channel convolutional model based on stacked deep learning collaborative gradient decomposition for predicting miRNA-disease associations

Numerous studies have shown that microRNAs (miRNAs) play a key role in human diseases as critical biomarkers. Its abnormal expression is often accompanied by the emergence of specific diseases. Therefore, studying the relationship between miRNAs and diseases can deepen the insights of their pathogenesis, grasp the process of disease onset and development, and promote drug research of specific diseases. However, many undiscovered relationships between miRNAs and diseases remain, significantly limiting research on miRNA-disease correlations. To explore more potential correlations, we propose a dual-channel convolutional model based on stacked deep learning collaborative gradient decomposition for predicting miRNA-disease associations (DCSGMDA). Firstly, we constructed similarity networks for miRNAs and diseases, as well as an association relationship network. Secondly, potential features were fully mined using stacked deep learning and gradient decomposition networks, along with dual-channel convolutional neural networks. Finally, correlations were scored by a multilayer perceptron. We performed 5-fold and 10-fold cross-validation experiments on DCSGMDA using two datasets based on the Human MicroRNA Disease Database (HMDD). Additionally, parametric, ablation, and comparative experiments, along with case studies, were conducted. The experimental results demonstrate that DCSGMDA performs well in predicting miRNA-disease associations.

Molecular insights into the hedgehog signaling pathway correlated non-coding RNAs in acute lymphoblastic leukemia, a bioinformatics study

BACKGROUND

Acute lymphoblastic leukemia (ALL) is a common hematologic cancer with unique incidence and prognosis patterns in people of all ages. Recent molecular biology advances have illuminated ALL's complex molecular pathways, notably the Hedgehog (Hh) signaling system and non-coding RNAs (ncRNAs). This work aimed to unravel the molecular complexities of the link between Hh signaling and ALL by concentrating on long non-coding RNAs (lncRNAs) and their interactions with significant Hh pathway genes.

METHODS

To analyze differentially expressed lncRNAs and genes in ALL, microarray data from the Gene Expression Omnibus (GEO) was reanalyzed using a systems biology approach. Hh signaling pathway-related genes were identified and their relationship with differentially expressed long non-coding RNAs (DElncRNAs) was analyzed using Pearson's correlation analysis. A regulatory network was built by identifying miRNAs that target Hh signaling pathway-related mRNAs.

RESULTS

193 DEGs and 226 DElncRNAs were found between ALL and normal bone marrow samples. Notably, DEGs associated with the Hh signaling pathway were correlated to 26 DElncRNAs. Later studies showed interesting links between DElncRNAs and biological processes and pathways, including drug resistance, immune system control, and carcinogenic characteristics. DEGs associated with the Hh signaling pathway have miRNAs in common with miRNAs already known to be involved in ALL, including miR-155-5p, and miR-211, highlighting the complexity of the regulatory landscape in this disease.

CONCLUSION

The complex connections between Hh signaling, lncRNAs, and miRNAs in ALL have been unveiled in this study, indicating that DElncRNAs linked to Hh signaling pathway genes could potentially serve as therapeutic targets and diagnostic biomarkers for ALL.

MRDPDA: A multi-Laplacian regularized deepFM model for predicting piRNA-disease associations

PIWI-interacting RNAs (piRNAs) are a typical class of small non-coding RNAs, which are essential for gene regulation, genome stability and so on. Accumulating studies have revealed that piRNAs have significant potential as biomarkers and therapeutic targets for a variety of diseases. However current computational methods face the challenge in effectively capturing piRNA-disease associations (PDAs) from limited data. In this study, we propose a novel method, MRDPDA, for predicting PDAs based on limited data from multiple sources. Specifically, MRDPDA integrates a deep factorization machine (deepFM) model with regularizations derived from multiple yet limited datasets, utilizing separate Laplacians instead of a simple average similarity network. Moreover, a unified objective function to combine embedding loss about similarities is proposed to ensure that the embedding is suitable for the prediction task. In addition, a balanced benchmark dataset based on piRPheno is constructed and a deep autoencoder is applied for creating reliable negative set from the unlabeled dataset. Compared with three latest methods, MRDPDA achieves the best performance on the pirpheno dataset in terms of the five-fold cross validation test and independent test set, and case studies further demonstrate the effectiveness of MRDPDA.

TriFusion enables accurate prediction of miRNA-disease association by a tri-channel fusion neural network

The identification of miRNA-disease associations is crucial for early disease prevention and treatment. However, it is still a computational challenge to accurately predict such associations due to improper information encoding. Previous methods characterize miRNA-disease associations only from single levels, causing the loss of multi-level association information. In this study, we propose TriFusion, a powerful and interpretable deep learning framework for miRNA-disease association prediction. It develops a tri-channel architecture to encode the association features of miRNAs and diseases from different levels and designs a feature fusion encoder to smoothly fuse these features. After training and testing, TriFusion outperforms other leading methods and offers strong interpretability through its learned representations. Furthermore, TriFusion is applied to three high-risk sexually associated cancers (ovarian, breast, and prostate cancers) and exhibits remarkable ability in the identification of miRNAs associated with the three diseases.

Mask-Guided Target Node Feature Learning and Dynamic Detailed Feature Enhancement for lncRNA-Disease Association Prediction

Identifying new relevant long noncoding RNAs (lncRNAs) for various human diseases can facilitate the exploration of the causes and progression of these diseases. Recently, several graph inference methods have been proposed to predict disease-related lncRNAs by exploiting the topological structure and node attributes within graphs. However, these methods did not prioritize the target lncRNA and disease nodes over auxiliary nodes like miRNA nodes, potentially limiting their ability to fully utilize the features of the target nodes. We propose a new method, mask-guided target node feature learning and dynamic detailed feature enhancement for lncRNA-disease association prediction (MDLD), to enhance node feature learning for improved lncRNA-disease association prediction. First, we designed a heterogeneous graph masked transformer autoencoder to guide feature learning, focusing more on the features of target lncRNA (disease) nodes. The target nodes were increasingly masked as training progressed, which helps develop a more robust prediction model. Second, we developed a graph convolutional network with dynamic residuals (GCNDR) to learn and integrate the heterogeneous topology and features of all lncRNA, disease, and miRNA nodes. GCNDR employs an interlayer residual strategy and a residual evolution strategy to mitigate oversmoothing caused by multilayer graph convolution. The interlayer residual strategy estimates the importance of node features learned in the previous GCN encoding layer for nodes in the current encoding layer. Additionally, since there are dependencies in the importance of features of individual lncRNA (disease, miRNA) nodes across multiple encoding layers, a gated recurrent unit-based strategy is proposed to encode these dependencies. Finally, we designed a perspective-level attention mechanism to obtain more informative features of lncRNA and disease node pairs from the perspectives of mask-enhanced and dynamic-enhanced node features. Cross-validation experimental results demonstrated that MDLD outperformed 10 other state-of-the-art prediction methods. Ablation experiments and case studies on candidate lncRNAs for three diseases further proved the technical contributions of MDLD and its capability to discover disease-related lncRNAs.

Identification of Autophagy-Related Biomarkers and Diagnostic Model in Alzheimer's Disease

Alzheimer's disease (AD) is the most prevalent neurodegenerative disease. Its accurate pathogenic mechanisms are incompletely clarified, and effective therapeutic treatments are still inadequate. Autophagy is closely associated with AD and plays multiple roles in eliminating harmful aggregated proteins and maintaining cell homeostasis. This study identified 1191 differentially expressed genes (DEGs) based on the GSE5281 dataset from the GEO database, intersected them with 325 autophagy-related genes from GeneCards, and screened 26 differentially expressed autophagy-related genes (DEAGs). Subsequently, GO and KEGG enrichment analysis was performed and indicated that these DEAGs were primarily involved in autophagy-lysosomal biological process. Further, eight hub genes were determined by PPI construction, and experimental validation was performed by qRT-PCR on a SH-SY5Y cell model. Finally, three hub genes (TFEB, TOMM20, GABARAPL1) were confirmed to have potential application for biomarkers. A multigenic prediction model with good predictability (AUC = 0.871) was constructed in GSE5281 and validated in the GSE132903 dataset. Hub gene-targeted miRNAs closely associated with AD were also retrieved through the miRDB and HDMM database, predicting potential therapeutic agents for AD. This study provides new insights into autophagy-related genes in brain tissues of AD patients and offers more candidate biomarkers for AD mechanistic research as well as clinical diagnosis.

Quantifying the massive pleiotropy of microRNA: a human microRNA-disease causal association database generated with ChatGPT

MicroRNAs (miRNAs) are recognized as key regulatory factors in numerous human diseases, with the same miRNA often involved in several diseases simultaneously or being identified as a biomarker for dozens of separate diseases. While of evident biological importance, miRNA pleiotropy remains poorly understood, and quantifying this could greatly aid in understanding the broader role miRNAs play in health and disease. To this end, we introduce miRAIDD (miRNA Artificial Intelligence Disease Database), a comprehensive database of human miRNA-disease causal associations constructed using large language models (LLM). Through this endeavor, we provide two entirely novel contributions: 1) we systematically quantify miRNA pleiotropy, a property of evident translational importance; and 2) describe biological and bioinformatic characteristics of miRNAs which lead to increased pleiotropy. Further, we provide our code, database, and experience using AI LLMs to the broader research community.

Identification of shared gene signatures in major depressive disorder and triple-negative breast cancer

BACKGROUND

Patients with major depressive disorder (MDD) have an increased risk of breast cancer (BC), implying that these two diseases share similar pathological mechanisms. This study aimed to identify the key pathogenic genes that lead to the occurrence of both triple-negative breast cancer (TNBC) and MDD.

METHODS

Public datasets GSE65194 and GSE98793 were analyzed to identify differentially expressed genes (DEGs) shared by both datasets. A protein-protein interaction (PPI) network was constructed using STRING and Cytoscape to identify key PPI genes using cytoHubba. Hub DEGs were obtained from the intersection of hub genes from a PPI network with genes in the disease associated modules of the Weighed Gene Co-expression Network Analysis (WGCNA). Independent datasets (TCGA and GSE76826) and RT-qPCR validated hub gene expression.

RESULTS

A total of 113 overlapping DEGs were identified between TNBC and MDD. The PPI network was constructed, and 35 hub DEGs were identified. Through WGCNA, the blue, brown, and turquoise modules were recognized as highly correlated with TNBC, while the brown, turquoise, and yellow modules were similarly correlated with MDD. Notably, G3BP1, MAF, NCEH1, and TMEM45A emerged as hub DEGs as they appeared both in modules and PPI hub DEGs. Within the GSE65194 and GSE98793 datasets, G3BP1 and MAF exhibited a significant downregulation in TNBC and MDD groups compared to the control, whereas NCEH1 and TMEM45A demonstrated a significant upregulation. These findings were further substantiated by TCGA and GSE76826, as well as through RT-qPCR validation.

CONCLUSIONS

This study identified G3BP1, MAF, NCEH1 and TMEM45A as key pathological genes in both TNBC and MDD.

A Survey of Deep Learning for Detecting miRNA- Disease Associations: Databases, Computational Methods, Challenges, and Future Directions

MicroRNAs (miRNAs) are an important class of non-coding RNAs that play an essential role in the occurrence and development of various diseases. Identifying the potential miRNA-disease associations (MDAs) can be beneficial in understanding disease pathogenesis. Traditional laboratory experiments are expensive and time-consuming. Computational models have enabled systematic large-scale prediction of potential MDAs, greatly improving the research efficiency. With recent advances in deep learning, it has become an attractive and powerful technique for uncovering novel MDAs. Consequently, numerous MDA prediction methods based on deep learning have emerged. In this review, we first summarize publicly available databases related to miRNAs and diseases for MDA prediction. Next, we outline commonly used miRNA and disease similarity calculation and integration methods. Then, we comprehensively review the 48 existing deep learning-based MDA computation methods, categorizing them into classical deep learning and graph neural network-based techniques. Subsequently, we investigate the evaluation methods and metrics that are frequently used to assess MDA prediction performance. Finally, we discuss the performance trends of different computational methods, point out some problems in current research, and propose 9 potential future research directions. Data resources and recent advances in MDA prediction methods are summarized in the GitHub repository https://github.com/sheng-n/DL-miRNA-disease-association-methods.

Recent applications of artificial intelligence in RNA-targeted small molecule drug discovery

INTRODUCTION

Targeting RNAs with small molecules offers an alternative to the conventional protein-targeted drug discovery and can potentially address unmet and emerging medical needs. The recent rise of interest in the strategy has already resulted in large amounts of data on disease associated RNAs, as well as on small molecules that bind to such RNAs. Artificial intelligence (AI) approaches, including machine learning and deep learning, present an opportunity to speed up the discovery of RNA-targeted small molecules by improving decision-making efficiency and quality.

AREAS COVERED

The topics described in this review include the recent applications of AI in the identification of RNA targets, RNA structure determination, screening of chemical compound libraries, and hit-to-lead optimization. The impact and limitations of the recent AI applications are discussed, along with an outlook on the possible applications of next-generation AI tools for the discovery of novel RNA-targeted small molecule drugs.

EXPERT OPINION

Key areas for improvement include developing AI tools for understanding RNA dynamics and RNA - small molecule interactions. High-quality and comprehensive data still need to be generated especially on the biological activity of small molecules that target RNAs.

MHIF-MSEA: a novel model of miRNA set enrichment analysis based on multi-source heterogeneous information fusion

Introduction: MicroRNAs (miRNAs) are a class of non-coding RNA molecules that play a crucial role in the regulation of diverse biological processes across various organisms. Despite not encoding proteins, miRNAs have been found to have significant implications in the onset and progression of complex human diseases. Methods: Conventional methods for miRNA functional enrichment analysis have certain limitations, and we proposed a novel method called MiRNA Set Enrichment Analysis based on Multi-source Heterogeneous Information Fusion (MHIF-MSEA). Three miRNA similarity networks (miRSN-DA, miRSN-GOA, and miRSN-PPI) were constructed in MHIF-MSEA. These networks were built based on miRNA-disease association, gene ontology (GO) annotation of target genes, and protein-protein interaction of target genes, respectively. These miRNA similarity networks were fused into a single similarity network with the averaging method. This fused network served as the input for the random walk with restart algorithm, which expanded the original miRNA list. Finally, MHIF-MSEA performed enrichment analysis on the expanded list. Results and Discussion: To determine the optimal network fusion approach, three case studies were introduced: colon cancer, breast cancer, and hepatocellular carcinoma. The experimental results revealed that the miRNA-miRNA association network constructed using miRSN-DA and miRSN-GOA exhibited superior performance as the input network. Furthermore, the MHIF-MSEA model performed enrichment analysis on differentially expressed miRNAs in breast cancer and hepatocellular carcinoma. The achieved p-values were 2.17e(-75) and 1.50e(-77), and the hit rates improved by 39.01% and 44.68% compared to traditional enrichment analysis methods, respectively. These results confirm that the MHIF-MSEA method enhances the identification of enriched miRNA sets by leveraging multiple sources of heterogeneous information, leading to improved insights into the functional implications of miRNAs in complex diseases.

The 2024 Nucleic Acids Research database issue and the online molecular biology database collection

The 2024 Nucleic Acids Research database issue contains 180 papers from across biology and neighbouring disciplines. There are 90 papers reporting on new databases and 83 updates from resources previously published in the Issue. Updates from databases most recently published elsewhere account for a further seven. Nucleic acid databases include the new NAKB for structural information and updates from Genbank, ENA, GEO, Tarbase and JASPAR. The Issue's Breakthrough Article concerns NMPFamsDB for novel prokaryotic protein families and the AlphaFold Protein Structure Database has an important update. Metabolism is covered by updates from Reactome, Wikipathways and Metabolights. Microbes are covered by RefSeq, UNITE, SPIRE and P10K; viruses by ViralZone and PhageScope. Medically-oriented databases include the familiar COSMIC, Drugbank and TTD. Genomics-related resources include Ensembl, UCSC Genome Browser and Monarch. New arrivals cover plant imaging (OPIA and PlantPAD) and crop plants (SoyMD, TCOD and CropGS-Hub). The entire Database Issue is freely available online on the Nucleic Acids Research website (https://academic.oup.com/nar). Over the last year the NAR online Molecular Biology Database Collection has been updated, reviewing 1060 entries, adding 97 new resources and eliminating 388 discontinued URLs bringing the current total to 1959 databases. It is available at http://www.oxfordjournals.org/nar/database/c/.

Composition of Conditioned Media from Radioresistant and Chemoresistant Cancer Cells Reveals miRNA and Other Secretory Factors Implicated in the Development of Resistance

Resistance to chemo- or radiotherapy is the main obstacle to consistent treatment outcomes in oncology patients. A deeper understanding of the mechanisms driving the development of resistance is required. This review focuses on secretory factors derived from chemo- and radioresistant cancer cells, cancer-associated fibroblasts (CAFs), mesenchymal stem cells (MSCs), and cancer stem cells (CSCs) that mediate the development of resistance in unexposed cells. The first line of evidence considers the experiments with conditioned media (CM) from chemo- and radioresistant cells, CAFs, MSCs, and CSCs that elevate resistance upon the ionizing radiation or anti-cancer drug exposure of previously untreated cells. The composition of CM revealed factors such as circular RNAs; interleukins; plasminogen activator inhibitor; and oncosome-shuttled lncRNAs, mRNAs, and miRNAs that aid in cellular communication and transmit signals inducing the chemo- and radioresistance of sensitive cancer cells. Data, demonstrating that radioresistant cancer cells become resistant to anti-neoplastic drug exposure and vice versa, are also discussed. The mechanisms driving the development of cross-resistance between chemotherapy and radiotherapy are highlighted. The secretion of resistance-mediating factors to intercellular fluid and blood brings attention to its diagnostic potential. Highly stable serum miRNA candidates were proposed by several studies as prognostic markers of radioresistance; however, clinical studies are needed to validate their utility. The ability to predict a treatment response with the help of the miRNA resistance status database will help with the selection of an effective therapeutic strategy. The possibility of miRNA-based therapy is currently being investigated with ongoing clinical studies, and such approaches can be used to alleviate resistance in oncology patients.

Identification ferroptosis-related hub genes and diagnostic model in Alzheimer's disease

Background

Ferroptosis is a newly defined form of programmed cell death and plays an important role in Alzheimer's disease (AD) pathology. This study aimed to integrate bioinformatics techniques to explore biomarkers to support the correlation between ferroptosis and AD. In addition, further investigation of ferroptosis-related biomarkers was conducted on the transcriptome characteristics in the asymptomatic AD (AsymAD).

Methods

The microarray datasets GSE118553, GSE132903, GSE33000, and GSE157239 on AD were downloaded from the GEO database. The list of ferroptosis-related genes was extracted from the FerrDb website. Differentially expressed genes (DEGs) were identified by R "limma" package and used to screen ferroptosis-related hub genes. The random forest algorithm was used to construct the diagnostic model through hub genes. The immune cell infiltration was also analyzed by CIBERSORTx. The miRNet and DGIdb database were used to identify microRNAs (miRNAs) and drugs which targeting hub genes.

Results

We identified 18 ferroptosis-related hub genes anomalously expressed in AD, and consistent expression trends had been observed in both AsymAD The random forest diagnosis model had good prediction results in both training set (AUC = 0.824) and validation set (AUC = 0.734). Immune cell infiltration was analyzed and the results showed that CD4+ T cells resting memory, macrophages M2 and neutrophils were significantly higher in AD. A significant correlation of hub genes with immune infiltration was observed, such as DDIT4 showed strong positive correlation with CD4+ T cells memory resting and AKR1C2 had positive correlation with Macrophages M2. Additionally, the microRNAs (miRNAs) and drugs which targeting hub genes were screened.

Conclusion

These results suggest that ferroptosis-related hub genes we screened played a part in the pathological progression of AD. We explored the potential of these genes as diagnostic markers and their relevance to immune cells which will help in understanding the development of AD. Targeting miRNAs and drugs provides new research clues for preventing the development of AD.