In the recent few years, an increasing number of studies have shown that microRNAs (miRNAs) play critical roles in many fundamental and important biological processes. As one pathogenetic factors, molecular mechanisms underlying human complex diseases still not been completely understood from perspective miRNA. Predicting potential miRNA-disease associations makes contributions to understanding pathogenesis diseases, developing new drugs, formulating individualized diagnosis treatment for...

With the increasing prevalence of autism spectrum disorder (ASD), it is important to identify ASD patients for effective treatment and intervention, especially in early childhood. Neuroimaging techniques have been used characterize complex biomarkers based on functional connectivity anomalies ASD. However, diagnosis still adopts symptom-based criteria by clinical observation. The existing computational models tend achieve unreliable diagnostic classification large-scale aggregated data sets....

An increasing number of evidences indicate microbes are implicated in human physiological mechanisms, including complicated disease pathology. Some have been demonstrated to be associated with diverse important diseases or disorders. Through investigating these disease-related microbes, we can obtain a better understanding mechanisms for advancing medical scientific progress terms diagnosis, treatment, prevention, prognosis and drug discovery. Based on the known microbe-disease association...

Accumulating clinical researches have shown that specific microbes with abnormal levels are closely associated the development of various human diseases. Knowledge microbe-disease associations can provide valuable insights for complex disease mechanism understanding as well prevention, diagnosis and treatment However, little effort has been made to predict microbial candidates diseases on a large scale.In this work, we developed new computational model predicting by combining two single...

Deep learning (DL) techniques have been introduced to assist doctors in the interpretation of medical images by detecting image-derived phenotype abnormality. Yet privacy-preserving policy disables effective training DL model using sufficiently large datasets. As a decentralized computing paradigm address this issue, federated (FL) allows process occur individual institutions with local datasets, and then aggregates resultant weights without risk privacy leakage.We propose an multi-task...

Neuroimaging techniques have been widely adopted to detect the neurological brain structures and functions of nervous system. As an effective noninvasive neuroimaging technique, functional magnetic resonance imaging (fMRI) has extensively used in computer-aided diagnosis (CAD) mental disorders, e.g., autism spectrum disorder (ASD) attention deficit/hyperactivity (ADHD). In this study, we propose a spatial–temporal co-attention learning (STCAL) model for diagnosing ASD ADHD from fMRI data....

Cell type identification is an indispensable analytical step in single-cell data analyses. To address the high noise stemming from gene expression data, existing computational methods often overlook biologically meaningful relationships between genes, opting to reduce all genes a unified space. We assume that such can aid characterizing cell features and improving recognition accuracy. this end, we introduce scPriorGraph, dual-channel graph neural network integrates multi-level biosemantics....

Single-cell analysis has revolutionized our understanding of cellular heterogeneity, yet current approaches face challenges in efficiency and interpretability. In this study, we present scKAN, a framework that leverages Kolmogorov-Arnold Networks for interpretable single-cell through three key innovations: efficient knowledge transfer from large language models lightweight distillation strategy; systematic identification cell-type-specific functional gene sets KAN's learned activation...

With the advance of sequencing technology and microbiology, microorganisms have been found to be closely related various important human diseases. The increasing identification microbe-disease associations offers insights into underlying disease mechanism understanding from perspective microbes, which are greatly helpful for investigating pathogenesis, promoting early diagnosis improving precision medicine. However, current knowledge in this domain is still limited far complete. Here, we...

The interaction of miRNA and lncRNA is known to be important for gene regulations. However, the number lncRNA-miRNA interactions still very limited there are computational tools available predicting new ones. Considering that lncRNAs miRNAs share internal patterns in partnership between each other, underlying could predicted by utilizing ones, which considered as a semi-supervised learning problem. It shown attributes have close relationship with other. Effective use side information helpful...

The offloading of computation-intensive tasks to an edge server near resource-constrained mobile devices can provide improved application performance and user experience. However, with the rapid growth connected server, it is challenging directly obtain optimal task scheme due increasing computational cost problem scale. In this study, we model costly (CTOP) in computing networks achieve efficient joint optimization energy consumption processing latency for devices. Inspired by success...

The high prevalence of mental disorders gradually poses a huge pressure on the public healthcare services. Deep learning-based computer-aided diagnosis (CAD) has emerged to relieve tension in institutions by detecting abnormal neuroimaging-derived phenotypes. However, training deep learning models relies sufficient annotated datasets, which can be costly and laborious. Semi-supervised (SSL) transfer (TL) mitigate this challenge leveraging unlabeled data within same institution advantageous...

Current knowledge and data on miRNA-lncRNA interactions is still limited little effort has been made to predict target lncRNAs of miRNAs. Accumulating evidences suggest that the interaction patterns between miRNAs are closely related relative expression level, forming a titration mechanism. It could provide an effective approach for characteristic feature extraction. In addition, using coding non-coding co-expression network sequence also help measure similarities among lncRNAs. By...

Identifying microRNAs that are associated with different diseases as biomarkers is a problem of great medical significance. Existing computational methods for uncovering such microRNA-diseases associations (MDAs) mostly developed under the assumption similar tend to associate diseases. Since an not always valid, these may be applicable all kinds MDAs. Considering relationship between long noncoding RNA (lncRNA) and co-regulation relationships biological functions lncRNA microRNA have been...

The globally rising prevalence of mental disorders leads to shortfalls in timely diagnosis and therapy reduce patients' suffering. Facing such an urgent public health problem, professional efforts based on symptom criteria are seriously overstretched. Recently, the successful applications computer-aided approaches have provided opportunities relieve tension healthcare services. Particularly, multimodal representation learning gains increasing attention thanks high temporal spatial resolution...

Content-based medical image retrieval (CBMIR) enables physicians to make evidence-based diagnoses by retrieving similar images and recalling previous cases stored in databases. However, existing CBMIR models are prone capturing superficial correlations due confounding factors such as complex host organs lesions, imaging discrepancies, artifacts, inconsistent protocols. To address this issue, we propose a plug-and-play anti-confounding hashing (ACH) method, which uses debiased sample...

Neuroimaging analysis aims to reveal the information-processing mechanisms of human brain in a noninvasive manner. In past, graph neural networks (GNNs) have shown promise capturing non-Euclidean structure networks. However, existing neuroimaging studies focused primarily on spatial functional connectivity, despite temporal dynamics complex To address this gap, we propose spatio-temporal interactive representation framework (STIGR) for dynamic that encompasses different aspects from...

The interactions between T-cell receptors (TCR) and peptide-major histocompatibility complex (pMHC) are essential for the adaptive immune system. However, identifying these can be challenging due to limited availability of experimental data, sequence data heterogeneity, high validation costs.

The rise of single-cell sequencing technologies has revolutionized the exploration drug resistance, revealing crucial role cellular heterogeneity in advancing precision medicine. By building computational models from existing response data, we can rapidly annotate responses to drugs subsequent trials. To this end, developed scGSDR, a model that integrates two pipelines grounded knowledge states and gene signaling pathways, both essential for understanding biological semantics. scGSDR...

The exploration of cellular heterogeneity within the tumor microenvironment (TME) via single-cell RNA sequencing (scRNA-seq) is essential for understanding cancer progression and response to therapy. Current scRNA-seq approaches, however, lack spatial context rely on incomplete datasets ligand-receptor interactions (LRIs), limiting accurate cell type annotation cell-cell communication (CCC) inference. This study addresses these challenges using a novel graph neural network (GNN) model that...

Functional MRI (fMRI) and single-cell transcriptomics are pivotal in Alzheimer's disease (AD) research, each providing unique insights into neural function molecular mechanisms. However, integrating these complementary modalities remains largely unexplored. Here, we introduce scBIT, a novel method for enhancing AD prediction by combining fMRI with single-nucleus RNA (snRNA). scBIT leverages snRNA as an auxiliary modality, significantly improving fMRI-based models comprehensive...

The rapid progress of high-throughput DNA sequencing techniques has dramatically reduced the costs whole genome sequencing, which leads to revolutionary advances in gene industry. explosively increasing volume raw data outpaces decreasing disk cost and storage huge become a bottleneck downstream analyses. Data compression is considered as solution reduce dependency on storage. Efficient methods are highly demanded. In this article, we present lossless reference-based method namely LW-FQZip 2...