Current Bioinformatics - Online First

Considering the heterogeneity of proteins across diverse cell types and states, studying protein thermostability at the single-cell level enables a more profound comprehension of cellular function and the mechanisms underlying disease progression.

In this study, we constructed classification and regression models to predict the thermostability difference of homologous protein pairs by integrating implicit features extracted from protein sequences using eight language models, including ProtBERT, AminoBERT, and ProtT5-XL, with explicit sequence features that are manually computed.

Our results demonstrate that the fusion of explicit and implicit features significantly enhances prediction performance. In classification tasks, the combination of implicit features extracted by AminoBERT and the optimal explicit feature set achieves an accuracy of 87.1%. In regression tasks, the combination of implicit features extracted by Word2vec and the optimal explicit feature set yields a PCC of 0.864 and a R2 of 0.742, which is better than previously reported results.

This study reveals the complementary strengths of language models and handcrafted features in predicting protein thermostability. Combining both types of features significantly improves the performance of classification and regression models and helps identify key factors affecting protein stability. However, the study is limited by its reliance on existing datasets, which may reduce its ability to generalize to novel or rare protein families.

The integration of implicit and explicit sequence features enables a more comprehensive representation of protein sequences and facilitates the identification of factors influencing the thermostability of orthologous proteins.

CircRNA, with its covalently closed circular structure, plays key roles in biological functions and diseases by interacting with RNA-binding proteins (RBPs) and microRNAs (miRNAs). However, existing computational methods struggle to capture secondary structure features.

We introduce CSGN, a graph neural network model that predicts circRNA-RBP interactions using secondary structure information. CSGN enhances physicochemical feature encodings by incorporating pseudo-secondary structures from thermodynamic models and utilizes graph convolutional networks (GCNs) for feature extraction. It also integrates Doc2Vec embeddings and employs CNNs, BiGRUs, and MLPs for efficient feature representation.

CSGN outperforms existing models across 16 datasets. Ablation studies confirm the significance of RNA secondary structure and GCNs in improving prediction accuracy. Principal component analysis further highlights CSGN's strength in feature extraction.

CSGN advances circRNA-RBP prediction by integrating GCNs and Doc2Vec, though global structural constraints remain. Future work should address longer-sequence modeling and experimental validation.

CSGN effectively improves circRNA-RBP interaction prediction, demonstrating superior performance through the integration of RNA secondary structure and GCNs.

Microbes have increasingly become critical new drug targets in human health. However, the paucity of known microbe-drug association data hinders drug discovery. Predicting potential microbe-drug associations can complement traditional experiments and accelerate drug development, making it crucial to develop efficient computational methods.

We proposed GAALSMDA, a graph attention-based fusion network. First, a microbe-drug heterogeneous network and feature matrix were constructed by integrating multiple similarities of microbes and drugs. Graph Attention Network (GAT) was used to mine low-dimensional features of microbes and drugs. Then, dual attention mechanism (CBAM) and Bidirectional Long Short-Term Memory (BiLSTM) were applied to fuse local and global features. Finally, a classifier output the likelihood scores of associations.

The experimental results indicated that the AUC and AUPR evaluation indices of the model reached 0.9900±0.0011, 0.9958±0.0015 and 0.9492±0.0051, 0.9668±0.0042 in MDAD and aBiofilm datasets, respectively, and the prediction performance was significantly superior to that of existing prediction methods.

The outstanding performance highlights GAALSMDA's ability to process sparse data and integrate multi-source information, addressing the limitations of previous models in terms of insufficient feature fusion. However, the similarity calculations of GIP and HIP may introduce parameter uncertainty, which still needs further optimization.

Our model demonstrates effectiveness and reliability in accurately inferring potential microbe-drug associations.

Single-cell multi-omics technologies provide a comprehensive view of cellular states and transcriptional regulatory mechanisms by integrating diverse omics data. However, their complexity and heterogeneity present significant analytical challenges, particularly in understanding neurodegenerative disorders such as Alzheimer's disease (AD), an irreversible and progressive condition.

This study introduces the Multi-Omics Attention Graphical Convolutional Networks (MOAGCN), a novel multilayer deep learning model that addresses the heterogeneity in single-cell multi-omics data to enhance the analysis of multi-omics datasets and uncover potential mechanisms underlying AD. MOAGCN combines Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs) to simultaneously capture local cellular connectivity and dynamically weight cell-to-cell interactions. The model was applied to AD-related single-cell RNA-seq and ATAC-seq datasets to identify significant gene expression and epigenetic alterations. It was further validated on datasets including DNA methylation, mRNA, and miRNA from other diseases. The model's performance was compared with conventional methods using metrics such as AUC, accuracy, and F1 scores.

MOAGCN effectively revealed key gene regulatory and protein interaction networks associated with AD, identifying significant changes in gene expression and epigenetic markers. In comparative validation across multiple datasets, MOAGCN outperformed traditional approaches in feature extraction and classification, achieving higher AUC, accuracy, and F1 scores. These results demonstrate its robustness in minimizing false positives and negatives while accurately identifying relevant features.

By testing in the classification of cell types and disease samples, MOAGCN achieved remarkable results, showing that its performance outperformed eight leading algorithms in multi-omics data classification tasks. Further analysis of MOAGCN's accuracy revealed a 95% confidence interval for its performance, reinforcing the model's robustness and stability across different datasets.

MOAGCN presents a robust and adaptable framework for integrating single-cell multi-omics data, addressing the challenges of complexity and heterogeneity. Its application to AD datasets highlights its potential to uncover regulatory mechanisms and bio-signals, advancing our understanding of complex diseases. This innovative approach holds promise for broad applications in multi-omics data analysis, particularly in elucidating mechanisms underlying neurodegenerative disorders.

Associations of abnormally expressed miRNAs with disease development have long been investigated in the biomedical field. The association types are diverse and complex, including circulation type, epigenetic type, target type, and genetic type, as well as various unknown associations and possibly novel association types. However, most current studies focus on the yes/no binary prediction of miRNA–disease associations. Algorithms for multi-type prediction or novel-type discovery of these associations are less developed.

Graph convolution and attention mechanisms, integrated within a deep learning framework, form the basis of deepMDpred. In the first step, deepMDpred employs the ViennaRNA tool to derive sequence and functional features of miRNAs by calculating base pairs, minimum free energy, and other relevant properties. In the second step, disease features are extracted using a Graph Convolutional Network (GCN) combined with attention learning, enabling the adaptive capture of the importance of different node features. Finally, a nonlinear fully connected layer (NFCL) is applied to generate the embedding vectors for both diseases and miRNAs.

In five-fold cross-validation, the model achieved high predictive performance for multi-type miRNA–disease associations. For task 1, the average AUC across the four predicted types exceeded 85%, with the genetics type achieving an accuracy of 0.919. For tasks 2 and 3, the average AUC exceeded 80%, and for the un-association type, the AUC reached 0.894. Validation using the HMDD v2.0 and HMDD v3.2 databases confirmed the robustness of the model, while additional case studies with the HMDD v3.2 and HMDD v4.0 databases demonstrated its applicability. Furthermore, investigations in breast and liver cancers supported the method’s capability to identify novel miRNA–disease associations.

The findings of this study demonstrate the potential of DeepMDpred as a novel and effective approach for predicting multi-type associations between miRNAs and diseases. Validation across multiple databases, along with successful application in case studies on breast and liver cancers, underscores the generalizability and practical utility of this approach. The framework also offers a pathway for identifying novel associations, which may accelerate the discovery of biomarkers and therapeutic targets in complex diseases such as cancer. Nonetheless, certain limitations remain. Although the model achieves strong performance on curated datasets, its robustness in real-world noisy datasets and its applicability to rare diseases require further investigation. Future research should also consider integrating additional data modalities, including epigenetic modifications and clinical phenotypes, to improve predictive accuracy further and broaden the scope of application.

DeepMDpred is an effective method that combines graph convolution and attention learning for the multi-type prediction of miRNA-disease associations. It provides a better ability to identify new association types between diseases and miRNAs, as well as broader applicability to unveil associated miRNAs with new diseases.

Genetic correlation plays a pivotal role in elucidating the shared genetic architecture underlying complex traits and diseases. Local genetic correlation can efficiently pinpoint specific genomic regions, thereby enhancing the precision of gene correlation analysis. However, accurate estimation of local genetic correlations remains challenging owing to linkage disequilibrium in local genomic regions and overlapping study samples.

In this work, we propose a novel method called LO-HDL that is based on high-dimensional maximum likelihood estimation. LO-HDL constructs marginal statistics using the summary statistics of GWAS and combines the 1000 Genomes Project Phase 3 data as a reference panel.

To assess the statistical power of LO-HDL, we performed a comparative analysis of LO-HDL with other local genetic correlation estimation methods on simulations with three different degrees of sample overlap. In the case of the absence of sample overlaps, the LO-HDL method improves the statistical power for cases with high local genetic covariance. In the case of partial sample overlap and complete sample overlap, LO-HDL demonstrates an overall improvement in statistical power. As an application, we used LO-HDL to estimate local genetic associations between the four autoimmune disorders. We found that LO-HDL could identify 31 regions with significant associations.

The LO-HDL method can identify genes or genomic regions that jointly influence multiple complex traits, thereby revealing the shared genetic architecture among traits. This approach elucidates the genetic relationships between traits and provides a basis for interpreting their associations. In simulated data, when the local genetic covariance ranges between (0.002–0.004), the statistical power of LO-HDL is slightly lower than that of previous methods. However, LO-HDL demonstrates superior performance in study scenarios with partial or complete sample overlap, as well as in real GWAS data analyses. Through LO-HDL, researchers can more accurately pinpoint genetically correlated regions among diseases. For instance, the TRIM27 gene on chromosome 6 exhibits significant associations with four diseases and may serve as a potential therapeutic target in future treatments.

LO-HDL is a novel method for estimating local genetic correlations, which is based on high-dimensional maximum likelihood estimation. Through its application in simulated datasets and four autoimmune diseases, LO-HDL improves the accuracy of estimating local genetic correlations, which has applicability for revealing relationships between genetic variants and specific traits or diseases.

The automatic classification of heart sound signals offers an economical and convenient approach for early diagnosis of cardiac diseases. By leveraging technological advancements, this method facilitates early detection and management of heart conditions, which is critical for improving patient outcomes.

To address the challenges in analyzing complex heart sound signals, we introduce a novel method utilizing EasyMKL-enhanced kernel partial least squares (KPLS). This approach begins with transforming segmented cardiac cycles into the time-frequency domain using the short-time Fourier transform (STFT). The STFT representations are then mapped into a high-dimensional feature space using multiple kernel functions derived from Easy MKL, designed to capture and enhance the discriminative nonlinear relationships among various heart sound categories. The extracted features are classified using a Support Vector Machine (SVM) for datasets with balanced samples and an XGBoost classifier for those with imbalanced samples.

The proposed method was evaluated on two publicly available heart sound datasets, the PhysioNet/CinC Challenge 2016 and the Yaseen dataset. On the PhysioNet/CinC Challenge 2016 dataset, our method achieved a sensitivity of 0.9217, a specificity of 0.8950, and an overall score of 0.9084. On the Yaseen dataset, our method achieved an average recall of 0.9933, precision of 0.9930, and F1-score of 0.9930, demonstrating high classification accuracy across different heart sound categories. These results confirm the effectiveness of our approach in extracting discriminative features and improving classification performance.

The high performance across two diverse datasets confirms the generalizability and robustness of the proposed method. Notably, the EasyMKL-enhanced KPLS framework captures complex nonlinear patterns while maintaining interpretability—an essential attribute for clinical applications. Compared to traditional approaches, our method significantly improves feature discriminability, as evidenced by ablation studies. While minor misclassifications persist in acoustically similar classes, the model consistently outperforms baselines, highlighting its strong potential for deployment in real-world intelligent auscultation systems.

The experimental results confirm the superiority of our proposed method, demonstrating its potential as a powerful tool for the automatic classification of heart sound signals. This approach not only enhances the accuracy of cardiac disease diagnostics but also offers a robust framework for handling complex and nonlinear characteristics of heart sound data, promising significant contributions to clinical practices and research in cardiology.

Previous studies have extensively reported various feature selection methods for identifying cancer signatures using RNA expression profiles. However, these methods often produce unreliable signatures due to four key factors. First, classifiers other than regression models are always inappropriately applied in prognostic survival analysis. Second, the unknown distribution of samples can lead to the ineffective selection of regression models. Third, high-dimensional expression profiles with small sample sizes typically result in poor predictive performance of the selected regression model. Fourth, variable control is usually overlooked.

To solve these problems, we have proposed a novel feature selection framework using ensemble regression to identify cancer prognostic signatures. This framework utilizes ensemble regression to overcome the limitations of classification models, as classification models reduce survival time to categorical labels, losing the original continuous information. At the same time, it incorporates up-sampling techniques to increase sample size and uses a bagging strategy to randomly select samples and features, addressing the challenges posed by high-dimensional data and small sample sizes. Additionally, the framework controls for clinical variables to ensure stable feature selection and reliable prediction results.

Experimental results demonstrate the effectiveness of this method in addressing the issues mentioned, providing reliable prognostic signatures. The ensemble regression method significantly improves predictive performance, with robust adaptability to unknown sample distributions.

The proposed ensemble regression model outperforms classification and single regressors in prognostic survival analysis by preserving continuous survival information, adapting to sample distribution, and benefiting from controlled variables. Using TCGA-GBM data, six prognostic miRNAs were validated as reliable biomarkers, whereas mRNA-based models showed limited robustness due to high dimensionality and small sample size.

The proposed feature selection framework offers a robust approach to improving the identification of cancer prognostic signatures, enhancing predictive accuracy in prognostic survival analysis.

Ovarian cancer (OC) is a fatal female reproductive system cancer with a high mortality rate and is hard to detect at an early stage. Recent studies have indicated that alternative splicing plays an important role in OC progression by activating genes and pathways involved in tumorigenesis. Circular RNAs (circRNAs) have also been found to play a regulating role in tumor progression and present their potential ability in alternative splicing regulation. However, the underlying mechanism by which circRNAs regulate alternative splicing events (ASEs) in OC remains unclear.

In this study, we performed a comprehensive transcriptomic study on the RNA-seq data of our collected tumor and normal samples from OC patients, aiming to investigate the regulatory roles of OC-specific circRNAs in aberrant splicing events and their underlying pathways in tumorigenesis.

We conducted a genome-wide regulatory network with strong correlations from 300 differentially expressed (DE) circRNAs and 1,150 aberrant ASEs, mediated by 31 DE SFs. Analyses of this network revealed that dysregulation of circRNAs may lead to aberrant ASEs that are closely involved in ovarian tumorigenesis. In addition, two crucial circRNAs, circ_AKT3 (hsa_circ_0000199) and circ_GSK3B (hsa_circ_0008797), were identified due to their significant roles in the network and associations with multiple tumor-related functional pathways.

These findings suggest that OC-specific circRNAs may participate in tumor progression by indirectly regulating groups of ASEs through multiple SFs, rather than through direct interaction. Subnetwork analyses centered on the two hub circRNAs revealed that their associated ASEs are functionally clustered and involved in coordinated biological processes relevant to tumor biology.

This study provides novel insights into the regulatory pathways by which circRNAs are involved in OC progression, offering clues for discovering diagnostic biomarkers and therapeutic targets.

Pre-mRNA alternative splicing (AS) is a prevalent phenomenon in mammals, playing a crucial role in various biological processes such as embryonic development, tissue differentiation, and disease pathogenesis. Despite the advancements in single-cell RNA sequencing (scRNA-seq) technology, the extent of AS heterogeneity at the transcript level during early mouse embryonic development remains largely unexplored.

The BRIE2 and expedition were employed to identify and quantify splicing events. Cell clustering was performed with Scanpy based on Percent Spliced In (PSI) values and gene expression levels. Then, marker AS events and differential AS events were detected by the Wlicocon rank-sum test and BRIE2's Mode-2 quantification mode. GO and KEGG enrichment analysis were conducted by ClusterProfiler.

The results suggested substantial heterogeneity in AS events and elucidated PSI values as a critical index of cell heterogeneity during early mouse embryonic development, shedding light on the regulatory mechanisms underlying these processes. By examining marker and differential AS events, the study provided a comprehensive understanding of the dynamic changes in splicing patterns throughout early mouse embryonic development.

This study revealed the heterogeneity of AS and elucidated its implications during early mouse embryonic development by analyzing AS at the single-cell level. However, the results are theoretical and lack experimental validation.

The findings offer critical insights into studying mouse embryonic development from the perspective of RNA cellular heterogeneity, emphasizing the importance of AS in shaping cellular diversity and developmental processes.

Bacterial and viral infections have been linked to an increased risk of coronary heart disease (CHD), potentially through natural killer (NK) cell-mediated innate immune mechanisms. This study aimed to integrate single-cell RNA sequencing (scRNA-seq) and bulk transcriptomics data to identify NK cell-associated genetic biomarkers that could aid in the diagnosis and assessment of CHD.

Publicly available single-cell and bulk RNA-seq datasets were analyzed to identify differentially expressed genes (DEGs). Functional enrichment analysis, protein-protein interaction (PPI) network construction, and biomarker validation were performed using standard bioinformatics pipelines.

A total of 106 shared DEGs were identified through integrated cross-comparative analysis. Enrichment analysis revealed involvement in immune activation, signal transduction, T-cell receptor signaling, and TYROBP signaling pathways. PPI network analysis identified key hub proteins, including CDK1 and PTPRC, as potential biomarkers. Regulatory analysis revealed transcription factors (TP53, YY1, and RELA) and post-transcriptional miRNAs (hsa-miR-195-5p, hsa-miR-34a-5p, and hsa-miR-16-5p) that may influence CHD-associated gene expression. Several small molecules were also predicted to interact with these targets, suggesting potential therapeutic applications.

The findings underscore the role of NK cell-mediated immune pathways in CHD pathogenesis. Hub genes such as CDK1 (involved in cell cycle regulation) and PTPRC (an immune signaling regulator) show promise as diagnostic biomarkers. The discovery of regulatory factors and druggable targets supports a complex, multi-level mechanism involving transcriptional and immune modulation.

This integrative study identifies novel NK cell-related molecular signatures and therapeutic targets, offering promising avenues for CHD diagnosis and the development of personalized treatment strategies.

The heterogeneity in tumours poses significant challenges to the accurate prediction of cancer stages, necessitating the expertise of highly trained medical professionals for diagnosis. Over the past decade, the integration of deep learning into medical diagnostics, particularly for predicting cancer stages, has been hindered by the black-box nature of these algorithms, which complicates the interpretation of their decision-making processes.

This study seeks to mitigate these issues by leveraging the complementary attributes found within functional genomics datasets (including mRNA, miRNA, and DNA methylation) and stained histopathology images. We introduced the Extended Squeeze- and-Excitation Multiheaded Attention (ESEMA) model, designed to harness these modalities. This model efficiently integrates and enhances the multimodal features, capturing biologically pertinent patterns that improve both the accuracy and interpretability of cancer stage predictions.

Our findings demonstrate that the explainable classifier utilised the salient features of the multimodal data to achieve an area under the curve (AUC) of 0.9985, significantly surpassing the baseline AUCs of 0.8676 for images and 0.995 for genomic data.

Furthermore, the extracted genomics features were the most relevant for cancer stage prediction, suggesting that these identified genes are promising targets for further clinical investigation.

An uncommon neurological condition known as Guillain-Barre syndrome (GBS) develops when the body's immunological system unintentionally targets peripheral nerves.

This work aimed to compare scRNA-seq and transcriptome data to find novel gene biomarkers linked to CD4⁺ T cells and B cells that might potentially be utilized for the diagnosis and assessment of GBS. It aimed to employ scRNA-seq data and bioinformatics tools analysis to identify cell-specific biomarkers for GBS diagnosis and prognosis.

scRNA-seq and microarray datasets from the GEO database were utilized to identify differentially expressed genes (DEGs). Pathway enrichment, identification of potential hub genes, and gene regulatory studies were employed using FunRich, DAVID, STRING, and NetworkAnalyst tools.

After integrating the DEGs and performing a comparative analysis, it was discovered that there were 84 DEGs shared between scRNA-seq and microarray datasets. The presence of signal transduction, immune system, cytokine signaling, NOD-like receptor signaling, and focal adhesion was detected in the most significant gene ontology and metabolic pathways. After generating a protein-protein interaction (PPI) network, we used eleven topological algorithms of the cytoHubba plugin for identifying six key hub genes, including CDC42, PTPRC, SRSF1, HNRNPA2B1, NIPBL, and FOS. Several crucial transcription factors (CHD1, IRF1, FOXC1, GATA2, YY1, E2F1, and CREB1) and two significant microRNAs (hsa-mir-20a-5p and hsa-mir-16-5p) were also discovered as hub gene regulators. The receiver operating characteristics (ROC) curve was used to evaluate the prognostic, expression, and diagnostic capabilities of the six major hub genes, indicating a good scoring value.

Finally, functional enrichment pathway analysis, PPI, and regulatory networks analysis demonstrated the critical functions of the identified key hub genes. After further wet lab research is validated, our research work may offer useful predicted potential biomarkers for the diagnosis and prognosis of GBS.

The 5' UTR plays a crucial role in gene regulation, which may be through its interaction with introns. Hence, there is a need to further study this interaction.

This study aimed to investigate the interactions between 5' UTR and introns and their correlation with species evolution.

The optimally matched segments between 5' UTR and introns were identified using Smith-Waterman local similarity matching, and the biological statistical methods were applied to compare the optimally matched segments between different species.

The interactions between 5' UTR and introns were found to be primarily mediated by weak bonds and demonstrated a directional change with species evolution. Additionally, a large proportion of the optimally matched segments were very similar to miRNA and siRNA in terms of length and matching rate characteristics.

The weak bonds in the interactions between the 5' UTR and the introns could enhance the flexibility of expression regulation, and an important correlation was found between the characteristic distributions of the optimally matched segments and species evolution. Additionally, the length and matching rate of a large proportion of optimally matched segments were very similar to those of miRNA and siRNA. In conclusion, it is highly probable that quite a few of the optimally matched segments are some kinds of functional non-coding RNAs.

Multi-omics data integration has transformed personalized medicine, providing a comprehensive understanding of disease mechanisms and informed precision therapeutic options. Multi-omics data generated for the same samples/patients can help in getting insights into the flow of biological information at several levels, thereby providing in-depth information regarding the molecular mechanisms underlying pathological conditions. Multi-omics integration plays a pivotal role in personalized medicine by providing comprehensive insights into the complex biological systems of individual patients. This review provides a comprehensive account of the current and future progress brought into multi-omics methodologies, promising to refine diagnostics and therapeutic strategy by integrating genomic, transcriptomic analyses, proteomics approaches and metabolome screens.

A literature search was performed in PubMed using keywords like genomics, proteomics, transcriptomics, metabolomics, multi-omics, and precision medicine to identify published research articles. A thorough review of all results was then conducted, and their results and conclusions were compiled and summarized.

By analyzing various omics layers, such as genomics, transcriptomics, proteomics, and metabolomics, multi-omics approaches enable the identification of patient-specific molecular traits and the discovery of new clinical therapeutics for diseases. Integration of various data types augments diagnostics, optimizes therapeutic regimens and supports personalized medicine according to an individual patient profile.

Integration of multi-omics data and its applications in various fields, such as cancer research, helps in optimizing patient-specific treatment and improvement of patient health. With time, as these technologies reach more people, they stand to democratize precision medicine and hopefully bridge health disparities. In conclusion, the present review highlights multiomics data integration as a transformative step towards personalized medicine and ultimately changing patient care from empirical-based to precision or individualized.