A5114929890- Bioinformatics and Genomic Networks
- Gene expression and cancer classification
- Genetic Associations and Epidemiology
- Alzheimer's disease research and treatments
- Machine Learning in Bioinformatics
- Topological and Geometric Data Analysis
- Computational Drug Discovery Methods
- Advanced Neuroimaging Techniques and Applications
- Advanced X-ray and CT Imaging
- Radiomics and Machine Learning in Medical Imaging
- Mosquito-borne diseases and control
- Functional Brain Connectivity Studies
- Advanced Graph Neural Networks
- Topic Modeling
- COVID-19 diagnosis using AI
- Viral Infections and Vectors
- Neuroinflammation and Neurodegeneration Mechanisms
- HIV Research and Treatment
- Genomics and Rare Diseases
- Vector-borne infectious diseases
- Artificial Intelligence in Games
- Natural Language Processing Techniques
- Virology and Viral Diseases
Harbin Engineering University
2020-2024
Huazhong Agricultural University
2021-2023
Shanghai Zhangjiang Laboratory
2023
State Council of the People's Republic of China
2020
Advancing the domain of biomedical investigation, integrated multi-omics data have shown exceptional performance in elucidating complex human diseases. However, as variety omics information expands, precisely perceiving informativeness intra- and inter-omics becomes challenging due to intricate interrelations, thus presenting significant challenges integration data. To address this, we introduce a novel approach, referred TEMINET. This approach enhances diagnostic prediction by leveraging an...
Like humans, Large Language Models (LLMs) struggle to generate high-quality long-form text that adheres strict requirements in a single pass. This challenge is unsurprising, as successful human writing, according the Cognitive Writing Theory, complex cognitive process involving iterative planning, translating, reviewing, and monitoring. Motivated by these principles, we aim equip LLMs with human-like writing capabilities through CogWriter, novel training-free framework transforms LLM...
Abstract Background Integrating multi-omics data is emerging as a critical approach in enhancing our understanding of complex diseases. Innovative computational methods capable managing high-dimensional and heterogeneous datasets are required to unlock the full potential such rich diverse data. Methods We propose Multi-Omics integration framework with auxiliary Classifiers-enhanced AuToencoders (MOCAT) utilize intra- inter-omics information comprehensively. Additionally, attention mechanisms...
Abstract Advancing the domain of biomedical investigation, integrated multi-omics data have shown exceptional performance in elucidating complex human diseases. However, as variety omics information expands, precisely perceiving informativeness intra- and inter-omics becomes challenging due to intricate interrelations, thus posing significant obstacles integration. To address this, we introduce a novel integration approach, referred TEMINET. This approach enhances diagnostic prediction by...
Abstract Background Although genetic risk factors and network-level neuroimaging abnormalities have shown effects on cognitive performance brain atrophy in Alzheimer’s disease (AD), little is understood about how apolipoprotein E (APOE) ε4 allele, the best-known for AD, affect connectivity before onset of symptomatic AD. This study aims to investigate APOE from perspective multimodal connectome. Results Here, we propose a novel network modeling framework quantification method based...
Abstract Multi-omics integration has demonstrated promising performance in complex disease prediction. However, existing research typically focuses on maximizing prediction accuracy, while often neglecting the essential task of discovering meaningful biomarkers. This issue is particularly important biomedicine, as molecules interact rather than function individually to influence outcomes. To this end, we propose a two-phase framework named GREMI assist multi-omics classification and...
Alzheimer’s disease (AD) is the main cause of dementia worldwide, and genetic mechanism which not yet fully understood. Much evidence has accumulated over past decade to suggest that after first large-scale genome-wide association studies (GWAS) were conducted, problem “missing heritability” in AD still a great challenge. Epistasis been considered as one causes AD, largely ignored human genetics. The focus current epistasis usually on single nucleotide polymorphisms (SNPs) have significant...
West Nile virus is a severe zoonotic pathogen that can cause central nervous system symptoms in humans and horses, fatal for birds, chickens other poultry. With no specific drugs or vaccines available, antibody-based therapy promising treatment. This study aims to develop neutralizing antibodies against assess their cross-protective potential Japanese encephalitis virus. The therapeutic efficacy of these was evaluated using mouse model, humanized version the monoclonal antibody generated...
Objective.The characterization of functional brain network is crucial to understanding the neural mechanisms associated with Alzheimer's disease (AD) and mild cognitive impairment (MCI). Some studies have shown that graph theoretical analysis could reveal changes disease-related networks by thresholding edge weights. But choice threshold depends on ambiguous conditions, which leads lack interpretability. Recently, persistent homology (PH) was proposed record persistence topological features...
Multi-omics integration has demonstrated promising performance in complex disease prediction. However, existing research typically focuses on maximizing prediction accuracy, while often neglecting the essential task of discovering meaningful biomarkers. This issue is particularly important biomedicine, as molecules interact rather than function individually to influence outcomes. To this end, we propose a two-phase framework named GREMI assist multi-omics classification and explanation. In...
Background: We aimed to explore the chest CT features of different clinical types COVID-19 pneumonia based on a Chinese multicenter dataset using an artificial intelligence (AI) system. Methods: A total 164 patients confirmed were retrospectively enrolled from 6 hospitals. All divided into mild type (136 cases) and severe (28 according their manifestations. The severity score quantitative calculated by AI detection evaluation system with correction radiologists. imaging analyzed. Findings:...
Alzheimer's disease (AD) is an age-related neurological disease, which closely associated with hippocampus, and subdividing the hippocampus into voxels can capture subtle signals that are easily missed by region of interest (ROI) methods. Therefore, studying interpretable associations between better understand effect voxel set on AD. In this study, analyzing hippocampal data, we propose a novel method based clustering genetic random forest to identify important voxels. Specifically, divide...
As an efficient method, genome-wide association study (GWAS) is used to identify the between genetic variation and pathological phenotypes, many significant variations founded by GWAS are closely associated with human diseases. However, it not enough mine only a single marker effect on complex biological phenotypes. Mining highly correlated nucleotide polymorphisms (SNP) more meaningful for of Alzheimer's disease (AD). In this paper, we two frequent pattern mining (FPM) framework, FP-Growth...
Abstract Background Integrating multi-omics data is emerging as a critical approach in enhancing our understanding of complex diseases. Innovative computational methods capable managing high-dimensional and heterogeneous datasets are required to unlock the full potential such rich diverse data. Methods We propose Multi-Omics integration framework with auxiliary Classifiers-enhanced AuToencoders (MOCAT), for comprehensive utilization both intra- inter-omics information. Additionally,...
Background: We sought to determine whether the age distribution can affect clinical or computed tomography (CT) features of patients with Corona Virus Disease 2019 (COVID-19 ). Methods: The and CT data 185 confirmed COVID-19 were retrospectively analyzed, these in different groups(≤30 years old group (28 cases), 31~50 (90 cases) >50 (67 cases)) compared by χ2 Fisher exact probability method Kruskal-Wallis rank sum test, Mann-Whitney test. Findings: C-Reactive Protein (CRP) (39.94±55.10 mg/L)...
Abstract Background: Brain image genetics provides enormous opportunities for examining the effects of geneticvariations on brain. Many studies have shown that structure, function, and abnormality (e.g., thoserelated to Alzheimer's disease) brain are heritable. However, which genetic variations contribute thesephenotypic changes is not completely clear. Advances in neuroimaging led us obtaindetailed anatomy genome-wide information. These data offer new identify such as single nucleotide...
Abstract Background: Brain image genetics provides enormous opportunities for examining the effects of genetic variations on brain. Many studies have shown that structure, function, and abnormality (e.g., those related to Alzheimer's disease) brain are heritable. However, which contribute these phenotypic changes is not completely clear. Advances in neuroimaging led us obtain detailed anatomy genome-wide information. These data offer new identify such as single nucleotide polymorphisms (...
Abstract Background: Testosterone is an important hormone affecting human growth and development. Recent studies have shown that testosterone related to immune regulation. Infection with Zika virus (ZIKV) can cause testicular damage decrease secretion. However, whether plays a function in the pathogenesis of ZIKV still unclear. The main objective this study was understand role central nervous system injury inflammation induced by ZIKV. Methods: In work, mouse model used evaluate infection....