A5100369544- Genomics and Phylogenetic Studies
- RNA and protein synthesis mechanisms
- Single-cell and spatial transcriptomics
- Privacy-Preserving Technologies in Data
- Radiomics and Machine Learning in Medical Imaging
- Gene expression and cancer classification
- Artificial Intelligence in Healthcare and Education
- Extracellular vesicles in disease
- COVID-19 diagnosis using AI
- Cancer Genomics and Diagnostics
- Genomics and Chromatin Dynamics
- AI in cancer detection
- Machine Learning in Bioinformatics
- Molecular Biology Techniques and Applications
- Inflammasome and immune disorders
- Cryptography and Data Security
- Oral microbiology and periodontitis research
- Cancer-related molecular mechanisms research
- Cell death mechanisms and regulation
- Chromosomal and Genetic Variations
- Medical Imaging and Analysis
- Dental Radiography and Imaging
- Phagocytosis and Immune Regulation
- Molecular Sensors and Ion Detection
- Invertebrate Immune Response Mechanisms
King Abdullah University of Science and Technology
2020-2025
Army Medical University
2024
Hong Kong University of Science and Technology
2024
University of Hong Kong
2024
Shanxi University
2022-2024
Tianjin Foreign Studies University
2024
Third Affiliated Hospital of Sun Yat-sen University
2023
Sun Yat-sen University
2023
Kootenay Association for Science & Technology
2023
Shanghai Sunshine Rehabilitation Center
2023
COVID-19 has caused a global pandemic and become the most urgent threat to entire world. Tremendous efforts resources have been invested in developing diagnosis, prognosis treatment strategies combat disease. Although nucleic acid detection mainly used as gold standard confirm this RNA virus-based disease, it shown that such strategy high false negative rate, especially for patients early stage, thus CT imaging applied major diagnostic modality confirming positive COVID-19. Despite various,...
Abstract Spatial transcriptomics technologies are used to profile transcriptomes while preserving spatial information, which enables high-resolution characterization of transcriptional patterns and reconstruction tissue architecture. Due the existence low-resolution spots in recent technologies, uncovering cellular heterogeneity is crucial for disentangling cell types, many related methods have been proposed. Here, we benchmark 18 existing resolving a deconvolution task with 50 real-world...
Modern machine learning models toward various tasks with omic data analysis give rise to threats of privacy leakage patients involved in those datasets. Here, we proposed a secure and privacy-preserving method (PPML-Omics) by designing decentralized differential private federated algorithm. We applied PPML-Omics analyze from three sequencing technologies addressed the concern major under representative deep models. examined breaches depth through attack experiments demonstrated that could...
Deep learning (DL) has shown explosive growth in its application to bioinformatics and demonstrated thrillingly promising power mine the complex relationship hidden large-scale biological biomedical data.A number of comprehensive reviews have been published on such applications, ranging from high-level with future perspectives those mainly serving as tutorials.These provided an excellent introduction guideline for applications DL bioinformatics, covering multiple types machine (ML) problems,...
Chitinase-3–like protein 1 (CHI3L1) is primarily secreted by activated astrocytes in the brain and known as a reliable biomarker for inflammatory central nervous system (CNS) conditions such neurodegeneration autoimmune disorders like neuromyelitis optica (NMO). NMO an astrocyte disease caused autoantibodies targeting astroglial aquaporin 4 (AQP4) leads to vision loss, motor deficits, cognitive decline. In this study examining CHI3L1’s biological function neuroinflammation, we found that...
While the abilities of language models are thoroughly evaluated in areas like general domains and biomedicine, academic chemistry remains less explored. Chemical QA tools also play a crucial role both education research by effectively translating complex chemical information into an understandable format. Addressing this gap, we introduce ScholarChemQA, large-scale dataset constructed from papers. Specifically, questions paper titles with question mark, multi-choice answers reasoned out...
Abstract With the fast‐growing and evolving omics data, demand for streamlined adaptable tools to handle bioinformatics analysis continues grow. In response this need, Automated Bioinformatics Analysis (AutoBA) is introduced, an autonomous AI agent designed explicitly fully automated multi‐omic analyses based on large language models (LLMs). AutoBA simplifies analytical process by requiring minimal user input while delivering detailed step‐by‐step plans various tasks. AutoBA's unique...
Hydrogen sulfide (H2S) is one of the typical reactive sulfur species, which exhibits an important role in regulating both physiological and pathological processes. Recent studies indicate that H2S also serves as a key signaling molecule broad range regulatory processes plants. However, situ imaging detection levels plant tissues remains challenge. In this work, NIR fluorescent probe (HBTP-H2S) was synthesized to achieve living tissues. HBTP-H2S exhibited high sensitivity toward with large...
Abstract Tremendous efforts have been made to improve diagnosis and treatment of COVID-19, but knowledge on long-term complications is limited. In particular, a large portion survivors has respiratory complications, currently, experienced radiologists state-of-the-art artificial intelligence systems are not able detect many abnormalities from follow-up computerized tomography (CT) scans COVID-19 survivors. Here we propose Deep-LungParenchyma-Enhancing (DLPE), computer-aided detection (CAD)...
Abstract Brain metastasis (BM) frequently occurs in advanced non-small cell lung cancer (NSCLC) and is associated with poor clinical prognosis. Due to the location of metastatic lesions, surgical resection limited chemotherapy ineffective because existence blood brain barrier (BBB). Therefore, it essential enhance our understanding about underlying mechanisms NSCLC. In present study, we explored RNA-Seq data cells from GEO database, extracted RNA collected primary NSCLC tumors as well paired...
Introduction Brain-computer interfaces (BCIs) have the potential in providing neurofeedback for stroke patients to improve motor rehabilitation. However, current BCIs often only detect general intentions and lack precise information needed complex movement execution, mainly due insufficient execution features EEG signals. Methods This paper presents a sequential learning model incorporating Graph Isomorphic Network (GIN) that processes sequence of graph-structured data derived from EMG...
Abstract With the flourishing of spatial omics technologies, alignment and stitching slices becomes indispensable to decipher a holistic view 3D molecular profile. However, existing methods are unpractical process large-scale image-based dataset due extreme time consumption unsatisfactory accuracy. Here we propose SANTO, coarse-to-fine method targeting tasks for omics. SANTO firstly rapidly supplies reasonable positions two identifies overlap region. Then, refines by considering patterns....
Periodontitis is a prevalent and irreversible chronic inflammatory disease both in developed developing countries, affects about 20–50% of the global population. The tool for automatically diagnosing periodontitis highly demanded to screen at-risk people its early detection could prevent onset tooth loss, especially local communities health care settings with limited dental professionals. In medical field, doctors need understand trust decisions made by computational models interpretable...
Abstract Motivation Unveiling the heterogeneity in tissues is crucial to explore cell–cell interactions and cellular targets of human diseases. Spatial transcriptomics (ST) supplies spatial gene expression profile which has revolutionized our biological understanding, but variations cell-type proportions each spot with dozens cells would confound downstream analysis. Therefore, deconvolution ST been an indispensable step a technical challenge toward higher-resolution panorama tissues....
Abstract Protein aggregation is critical to various biological and pathological processes. Besides, it also an important property in biotherapeutic development. However, experimental methods profile protein are costly labor‐intensive, driving the need for more efficient computational alternatives. In this study, we introduce “AggNet,” a novel deep learning framework based on language model ESM2 AlphaFold2, which utilizes physicochemical, evolutionary, structural information discriminate...
Spatially-resolved transcriptomics (SRT) technologies now allow exploration of gene expression with spatial context. Recent advances achieving subcellular resolution provide richer data but also introduce challenges, such as aggregating spots into individual cells, which is a task distinct from traditional deconvolution. Existing methods often grid SRT predefined squares, unrealistic for accurately capturing cellular boundaries. We propose method, STP, that integrates nuclei-stained images...
Dexamethasone (Dex) has been widely used as a potent anti-inflammatory, antishock, and immunosuppressive agent. However, high dose or long-term use of Dex is accompanied by side effects including skeletal muscle atrophy, whose underlying mechanisms remain incompletely understood. A number microRNAs (miRNAs) have shown to play key roles in atrophy. Previous studies showed significantly increased miR-322 expression Dex-treated C2C12 myotubes. In our study, the glucocorticoid receptor (GR) was...
Abstract Revoking personal private data is one of the basic human rights. However, such right often overlooked or infringed upon due to increasing collection and use patient for model training. In order secure patients’ be forgotten, we proposed a solution by using auditing guide forgetting process, where means determining whether dataset has been used train requires information query forgotten from target model. We unified these two tasks introducing an approach called knowledge...
Abstract Triple negative breast cancer (TNBC) represents the most malignant subtype of cancer, and yet our understanding about its unique biology remains elusive. We have conducted a comparative computational analysis transcriptomic data TNBC non-TNBC (NTNBC) tissue samples from TCGA database, focused on genes involved in neural functions. Our main discoveries are: (1) while both subtypes involve functions, has substantially more up-regulated than NTNBC, suggesting that is complex NTNBC; (2)...