A5051004995- Machine Learning in Bioinformatics
- Bioinformatics and Genomic Networks
- MicroRNA in disease regulation
- Computational Drug Discovery Methods
- Metabolomics and Mass Spectrometry Studies
- Cancer-related molecular mechanisms research
- Single-cell and spatial transcriptomics
- Cell Image Analysis Techniques
- Gene expression and cancer classification
- Software-Defined Networks and 5G
- RNA and protein synthesis mechanisms
- Infrared Target Detection Methodologies
- Genetic Associations and Epidemiology
- Genomics and Phylogenetic Studies
- vaccines and immunoinformatics approaches
- Supply Chain and Inventory Management
- Antimicrobial Peptides and Activities
- Sustainable Supply Chain Management
- Extracellular vesicles in disease
- Monoclonal and Polyclonal Antibodies Research
- Advanced Image Fusion Techniques
- Machine Learning in Materials Science
- Pharmacogenetics and Drug Metabolism
- Efficiency Analysis Using DEA
- Advanced MIMO Systems Optimization
Harbin Institute of Technology
2016-2025
Cell and Gene Therapy Catapult
2025
Heilongjiang Institute of Technology
2020-2024
Shanghai Medical College of Fudan University
2024
Fudan University Shanghai Cancer Center
2024
Institute of Special Animal and Plant Sciences
2024
Sun Yat-sen University
2023
Shaanxi Normal University
2023
Dalian University of Technology
2017-2022
Second Hospital of Hebei Medical University
2021-2022
Identification of new drug-target interactions (DTIs) is an important but a time-consuming and costly step in drug discovery. In recent years, to mitigate these drawbacks, researchers have sought identify DTIs using computational approaches. However, most existing methods construct networks target separately, then predict novel based on known associations between the drugs targets without accounting for drug-protein pairs (DPPs). To incorporate DPPs into DTI modeling, we built DPP network...
Although long non-coding RNAs (lncRNAs) have limited capacity for encoding proteins, they been verified as biomarkers in the occurrence and development of complex diseases. Recent wet-lab experiments shown that lncRNAs function by regulating expression protein-coding genes (PCGs), which could also be mechanism responsible causing Currently, lncRNA-related biological data are increasing rapidly. Whereas, no computational methods designed predicting novel target lncRNA.In this study, we...
Abstract SC2disease (http://easybioai.com/sc2disease/) is a manually curated database that aims to provide comprehensive and accurate resource of gene expression profiles in various cell types for different diseases. With the development single-cell RNA sequencing (scRNA-seq) technologies, uncovering cellular heterogeneity tissues diseases has become feasible by profiling transcriptomes across at level. In particular, comparing between identifying cell-type-specific genes offers new...
Abstract Interactions between proteins and small molecule metabolites play vital roles in regulating protein functions controlling various cellular processes. The activities of metabolic enzymes, transcription factors, transporters membrane receptors can all be mediated through protein–metabolite interactions (PMIs). Compared with the rich knowledge protein–protein interactions, little is known about PMIs. To best our knowledge, no existing database has been developed for collecting recent...
Abstract Gut microbiota plays a significant role in maintaining host health, and conversely, disorders potentially lead to dysbiosis, an imbalance the composition of gut microbial community. Intervention approaches, such as medications, diets, several others, also alter either beneficial or harmful direction. In 2020, gutMDisorder was developed facilitate researchers investigation dysbiosis microbes occurs various well with therapeutic interventions. The database has been updated this year,...
Abstract Spatial transcriptomics unveils the complex dynamics of cell regulation and transcriptomes, but it is typically cost-prohibitive. Predicting spatial gene expression from histological images via artificial intelligence offers a more affordable option, yet existing methods fall short in extracting deep-level information pathological images. In this paper, we present THItoGene, hybrid neural network that utilizes dynamic convolutional capsule networks to adaptively sense potential...
Metabolites disrupted by abnormal state of human body are deemed as the effect diseases. In comparison with cause diseases like genes, these markers easier to be captured for prevention and diagnosis metabolic Currently, a large number need explored, which drive us do this work.The existing metabolite-disease associations were extracted from Human Metabolome Database (HMDB) using text mining tool NCBO annotator priori knowledge. Next we calculated similarity pair-wise metabolites based on...
The functional changes of the genes, RNAs and proteins will eventually be reflected in metabolic level. Increasing number researchers have researched mechanism, biomarkers targeted drugs by metabolites. However, compared with our knowledge about RNAs, proteins, we still know few diseases-related All existed methods for identifying metabolites ignore chemical structure metabolites, fail to recognize association pattern between diseases, apply isolated diseases metabolites.In this study,...
Background: Heart failure (HF) is a heterogeneous disease characterized by significant metabolic disturbances; however, the breadth of dysfunction before onset overt not well understood. The purpose this study was to determine association circulating metabolites with incident HF uncover novel pathways disease. Methods: We performed targeted plasma metabolomic profiling in deeply phenotyped group Black adults from JHS (Jackson Study; n=2199). related associated established etiological...
Abstract The prediction of molecular interactions is vital for drug discovery. Existing methods often focus on individual tasks and overlook the relationships between them. Additionally, certain encounter limitations due to insufficient data availability, resulting in limited performance. To overcome these limitations, we propose KGE-UNIT, a unified framework that combines knowledge graph embedding (KGE) multi-task learning, simultaneous drug–target (DTIs) drug–drug (DDIs) enhancing...
Abstract Non-coding RNAs (ncRNAs) participate in multiple biological processes associated with cancers as tumor suppressors or oncogenic drivers. Due to their high stability plasma, urine, and many other fluids, ncRNAs have the potential serve key biomarkers for early diagnosis screening of cancers. During cancer progression, heterogeneity plays a crucial role, it is particularly important understand gene expression patterns individual cells. With development single-cell RNA sequencing...
It is estimated that the impact of related genes on risk Alzheimer's disease (AD) nearly 70%. Identifying candidate causal can help treatment and diagnosis. The maturity sequencing technology reduction cost make genome-wide association study (GWAS) become an important means to find disease-related mutation sites. Because linkage disequilibrium (LD), neither gene regulated by SNP nor specific be determined. GWAS affected sample size interaction, we introduced empirical Bayes (EB) a...
<title>Abstract</title> Combined methylmalonic acidemia and homocystinemia (cblC) is an autosomal recessive disorder characterized by aberrant organic acid metabolism. The c.80A > G mutation in the <italic>MMACHC</italic> gene has been documented numerous studies linked to cblC phenotypes. However, this mutation's pathogenic mechanisms remain elusive, as it not yet validated through functional studies. In a previous study, we developed murine model with Mmachc elucidate intricacies of...
<title>Abstract</title> Deconvolution algorithm enables estimation of cell type abundances from tissue-level data, providing a crucial way for exploring plentiful cohort data at the cellular level. However, most deconvolution algorithms are specifically designed single-omics thereby limiting their generalizability and scalability multiomics different cohorts. A applicable to various omics can use abundance as bridge improve comparability Here, we developed DECODE, universal framework both...
<title>Abstract</title> Combined methylmalonic acidemia and homocystinemia (cblC) is an autosomal recessive disorder characterized by aberrant organic acid metabolism. The c.80A > G mutation in the <italic>MMACHC</italic> gene has been documented numerous studies linked to cblC phenotypes. However, this mutation's pathogenic mechanisms remain elusive, as it not yet validated through functional studies. In a previous study, we developed murine model with Mmachc elucidate intricacies of...
Alzheimer disease (AD) is the fourth major cause of death in elderly following cancer, heart and cere-brovascular disease. Finding candidate causal genes can help human design Gene targeted drugs effectively reduce risk Complex diseases such as AD are usual-ly caused by multiple genes. By Genome-wide association study (GWAS), has identified pote dntial genetic variants for most diseases. However, because exist-ence linkage disequilibrium (LD), it difficult to identi-fy causative mutations...
Seasonal influenza A viruses continue to pose a public health threat, and current vaccines are not sufficiently effective because of virus mutation. There is an urgent need develop broad-protection vaccine. Our team previously designed potential universal hemagglutinin (HA) sequences against seasonal H1N1 H3N2 (mH1 mH3, respectively) through mosaic strategy. In this study, we construct DNA by linking the antigens mH1 mH3 via internal ribosome entry sites then wrap with deoxycholic...
Abstract Background Multiple sclerosis (MS) is a central nervous system disease with high disability rate. Modern molecular biology techniques have identified number of key genes and diagnostic markers to MS, but the etiology pathogenesis MS remain unknown. Results In this study, integration three peripheral blood mononuclear cell (PBMC) microarray datasets one T cells dataset allowed comprehensive network pathway analyses biological functions MS-related genes. Differential expression...
Lung segmentation is usually the first step of lung CT image analysis and plays an important role in disease diagnosis. We propose efficient end-to-end fully convolutional neural network to segment lungs with different diseases images. introduce a multi-instance loss conditional adversary order solve problem for more severe pathological conditions. Our method capable solving under normal, moderate conditions, which validated on 3 public benchmark datasets diseases.
We propose a proactive dynamic network slicing scheme that utilizes deep-learning based short-term traffic prediction approach for 5G transport networks. The demonstration shows utilization efficiency improvement from 46.33% to 71.53% under the evaluated scenario.
Performance or efficiency evaluation is of great importance for effective supply chain management, especially in the context sustainable development and platform economy. In existing literature, two-stage network data envelopment analysis (DEA) has been widely used evaluation. Although DEA usually assumes systems resolve inherent conflicts between two stages, e.g. supplier manufacturer a two-echelon chain, relation to traditional 'black box' remains unclear. Moreover, coordination effect...