A5051184139- Bioinformatics and Genomic Networks
- Computational Drug Discovery Methods
- Biomedical Text Mining and Ontologies
- Metabolomics and Mass Spectrometry Studies
- Machine Learning in Bioinformatics
- Plant Molecular Biology Research
- Gene expression and cancer classification
- Cancer-related molecular mechanisms research
- Traditional Chinese Medicine Studies
- Plant Stress Responses and Tolerance
- Machine Learning in Healthcare
- Prostate Cancer Treatment and Research
- Catalytic Processes in Materials Science
- Ferroptosis and cancer prognosis
- Vehicle emissions and performance
- Advanced Combustion Engine Technologies
- Topic Modeling
- Pharmacological Effects of Natural Compounds
- Circular RNAs in diseases
- MicroRNA in disease regulation
- Plant Gene Expression Analysis
- Photosynthetic Processes and Mechanisms
- RNA modifications and cancer
- Natural Language Processing Techniques
- AI in cancer detection
Southeast University
2025
Beijing Jiaotong University
2015-2024
Tianjin University of Traditional Chinese Medicine
2020-2024
Shanghai Pudong New Area Gongli Hospital
2024
Liaocheng University
2024
Beijing Academy of Artificial Intelligence
2024
Second Military Medical University
2024
Ministry of Education
2024
Tennessee Technological University
2018-2023
Second Hospital of Tianjin Medical University
2015-2023
Recently, the pharmaceutical industry has heavily emphasized phenotypic drug discovery (PDD), which relies primarily on knowledge about phenotype changes associated with diseases. Traditional Chinese medicine (TCM) provides a massive amount of information natural products and clinical symptoms they are used to treat, observable disease phenotypes that crucial for diagnosis treatment. Curating TCM their relationships herbs diseases will provide both candidate leads screening directions...
Although electric vehicles (EVs) are becoming a promising alternative for ground transportation, the issue of limited battery energy hinders its market penetration. Accurate prediction electrical consumption along given route would significantly relieve drivers' anxieties and build their confidence in EVs. A high-fidelity estimation relies on an accurate velocity forecast. To this end, article proposes novel hybrid deterministic-stochastic methodology that utilizes inputs encompassing...
Zinc finger proteins are widely involved and play an important role in plant growth abiotic stress. In this research, MdZAT5, a gene encoding C2H2-type zinc protein, was cloned investigated. The MdZAT5 highly expressed flower tissues by qRT-PCR analyses GUS staining. Promoter analysis showed that contained multiple response elements, the expression levels of were induced various stress treatments. Overexpression apple calli positively regulated anthocyanin accumulation activating expressions...
Abstract Objectives Herbal prescription recommendation (HPR) is a hot topic and challenging issue in field of clinical decision support traditional Chinese medicine (TCM). However, almost all previous HPR methods have not adhered to the principles syndrome differentiation treatment planning TCM, which has resulted suboptimal performance difficulties application real-world scenarios. Materials Methods We emphasize synergy among diagnosis procedure TCM settings propose PresRecST model,...
The discovery of disease-causing genes is a critical step towards understanding the nature disease and determining possible cure for it. In recent years, many computational methods to identify have been proposed. However, making full use disease-related (e.g., symptoms) gene-related gene ontology protein-protein interactions) information improve performance prediction still an issue. Here, we develop heterogeneous disease-gene-related network (HDGN) embedding representation framework (called...
Abstract Abscisic acid is involved in the regulation of cold stress response, but its molecular mechanism remains to be elucidated. In this study, we demonstrated that APETALA2/ethylene responsive factor (AP2/ERF) family protein MdABI4 positively regulates abscisic acid-mediated tolerance apple. We found interacts with MdICE1, a key regulatory and enhances transcriptional function MdICE1 on downstream target gene MdCBF1, thus improving tolerance. The jasmonate-ZIM domain (JAZ) proteins...
Continual learning usually assumes the incoming data are fully labeled, which might not be applicable in real applications. In this work, we consider semi-supervised continual (SSCL) that incrementally learns from partially labeled data. Observing existing methods lack ability to continually exploit unlabeled data, propose deep Online Replay with Discriminator Consistency (ORDisCo) interdependently learn a classifier conditional generative adversarial network (GAN), passes learned...
Abstract Understanding the mechanisms of candidate drugs play an important role in drug discovery. The activating/inhibiting between and targets are major types drugs. Owing to complexity drug–target (DT) data scarcity, modelling this problem based on deep learning methods accurately predict DT remains a considerable challenge. Here, by considering network pharmacology, we propose multi-view model, DrugAI, which combines four modules, i.e. graph neural for drugs, convolutional targets,...
The most common cause of death from prostate cancer (PCa) is metastases. There an increasing body evidence that microRNAs play important role in the development PCa by regulating target genes involved tumor metastasis. Here, we identified expression miR-486-5p was decreased metastatic C4-2 cells compared to non-metastatic LNCaP cells. Further validation clinical samples showed significantly tissues localized tissues. Functional studies demonstrated increased can suppress cell migration and...
Less than 40% of the nitrogen (N) fertilizer applied to soil is absorbed by crops. Thus, improving N use efficiency crops critical for agricultural development. However, underlying regulation these processes remains largely unknown, particularly in woody plants. By conducting yeast two-hybrid assays, we identified one interacting protein MdMYB88 and MdMYB124 apple (Malus × domestica), namely BTB TAZ domain 2 (MdBT2). Ubiquitination stabilization analysis revealed that MdBT2 ubiquitinates...
Jasmonic acid (JA) plays an important role in regulating leaf senescence. However, the molecular mechanisms of senescence apple (Malus domestica) remain elusive. In this study, we found that MdZAT10, a C2H2-type zinc finger transcription factor (TF) apple, markedly accelerates and increases expression senescence-related genes. To explore how MdZAT10 promotes senescence, carried out liquid chromatography/mass spectrometry screening. We MdABI5 physically interacts with MdZAT10. MdABI5,...
Abstract Target identification is one of the crucial tasks in drug research and development, as it aids uncovering action mechanism herbs/drugs discovering new therapeutic targets. Although multiple algorithms herb target prediction have been proposed, due to incompleteness clinical knowledge limitation unsupervised models, accurate for targets still faces huge challenges data models. To address this, we proposed a deep learning-based framework termed HTINet2, which designed three key...
Traditional Chinese medicine (TCM) has played an indispensable role in clinical diagnosis and treatment. Based on a patient’s symptom phenotypes, computation-based prescription recommendation methods can recommend personalized TCM using machine learning artificial intelligence technologies. However, owing to the complexity individuation of current cannot obtain good performance. Meanwhile, it is very difficult conduct effective representation for unrecorded terms existing knowledge base. In...
Traditional Chinese Medicine (TCM) has received increasing attention as a complementary approach or alternative to modern medicine. However, experimental methods for identifying novel targets of TCM herbs heavily relied on the current available herb-compound-target relationships. In this work, we present an Herb-Target Interaction Network (HTINet) approach, network integration pipeline herb-target prediction mainly relying symptom related associations. HTINet focuses capturing...
Chinese medicine (CM) was extensively used to treat COVID-19 in China. We aimed evaluate the real-world effectiveness of add-on semi-individualized CM during outbreak. A retrospective cohort 1788 adult confirmed patients were recruited from 2235 consecutive linked records retrieved five hospitals Wuhan 15 January 13 March 2020. The mortality users and non-users compared by inverse probability weighted hazard ratio (HR) propensity score matching. Change biomarkers between groups, frequency...
Knowledge Graph Embedding (KGE) methods have achieved great success in predicting missing links knowledge graphs, a task also known as Completion (KGC). Under this task, the Reciprocal Rank (RR) of ground-truth items serve key indicator for evaluating method’s performance. However, most existing studies overlooked inconsistency between ranking metric, RR, and optimization objective functions, resulting sub-optimal KGC To address issue, we propose framework called KGCRR by designing novel...