A5047622922- Genomics and Phylogenetic Studies
- Machine Learning in Bioinformatics
- Topic Modeling
- Cancer-related gene regulation
- Gut microbiota and health
- Epigenetics and DNA Methylation
- Neuroendocrine Tumor Research Advances
- Metabolomics and Mass Spectrometry Studies
- Circular RNAs in diseases
- Multimodal Machine Learning Applications
- Enzyme function and inhibition
- IgG4-Related and Inflammatory Diseases
- Bioinformatics and Genomic Networks
- RNA modifications and cancer
- Gene expression and cancer classification
- Microbial Community Ecology and Physiology
- MicroRNA in disease regulation
- COVID-19 diagnosis using AI
- Natural Language Processing Techniques
- Cancer-related molecular mechanisms research
- Machine Learning in Healthcare
- Insect Resistance and Genetics
- Misinformation and Its Impacts
- Phytochemical compounds biological activities
- Liver physiology and pathology
University of Tübingen
2020-2024
Capital University
2024
Beijing Friendship Hospital
2024
Capital Medical University
2024
Bernstein Center for Computational Neuroscience Tübingen
2023
Liuzhou General Hospital
2017
Abstract Motivation Metagenomic projects often involve large numbers of sequencing datasets (totaling hundreds gigabytes data). Thus, computational preprocessing and analysis are usually performed on a server. The results such analyses then explored interactively. One approach is to use MEGAN, an interactive program that allows comparison metagenomic datasets. Previous releases have required the user first download computed data from server, increasingly time-consuming process. Here, we...
The epithelial immunomodulation and regeneration are intrinsic critical events against inflammatory bowel disease (IBD). MiR-7 is well documented as a promising regulator in the development of various diseases including diseases. This study aimed to assess effect miR-7 intestinal cells (IECs) IBD. MiR-7def mice were given dextran sulfate sodium (DSS) induce enteritis model. infiltration was measured by FCM immunofluorescence assay. 5′deletion assay EMSA assays performed regulatory mechanism...
Abstract Transformer-based language models are successfully used to address massive text-related tasks. DNA methylation is an important epigenetic mechanism, and its analysis provides valuable insights into gene regulation biomarker identification. Several deep learning–based methods have been proposed identify methylation, each seeks strike a balance between computational effort accuracy. Here, we introduce MuLan-Methyl, learning framework for predicting sites, which based on 5 popular...
AbstractNeuroblastoma, the most common childhood solid tumor, originates from primitive sympathetic nervous system cells. Epoxyazadiradione (EAD) is a limonoid derived Azadirachta indica, belonging to family Meliaceae. In this study, we isolated EAD indica seed and studied anti-cancer potential against neuroblastoma. Herein, demonstrated significant efficacy neuroblastoma by suppressing cell proliferation, enhancing rate of apoptosis cycle arrest at SubG0 G2/M phases. enhanced pro-apoptotic...
Comments on social media are very diverse, in terms of content, style and vocabulary, which make generating comments much more challenging than other existing natural language generation (NLG) tasks. Besides, since different user has expression habits, it is necessary to take the user's profile into consideration when comments. In this paper, we introduce task automatic personalized comment (AGPC) for media. Based tens thousands users' real corresponding profiles weibo, propose Personalized...
The current COVID-19 pandemic, caused by the rapid worldwide spread of SARS-CoV-2 virus, is having severe consequences for human health and world economy. virus affects different individuals differently, with many infected patients showing only mild symptoms, others critical illness. To lessen impact epidemic, one problem to determine which factors play an important role in a patient’s progression disease. Here, we construct enhanced structured dataset from more than source, using natural...
Abstract Transformer-based language models are successfully used to address massive text-related tasks. DNA methylation is an important epigenetic mechanism and its analysis provides valuable insights into gene regulation biomarker identification. Several deep learning-based methods have been proposed identify each seeks strike a balance between computational effort accuracy. Here, we introduce MuLan-Methyl, deep-learning framework for predicting sites, which based on five popular...
A microbial community maintains its ecological dynamics via metabolite crosstalk. Hence, knowledge of the metabolome, alongside populace, would help us understand functionality a and also predict how it will change in atypical conditions. Methods that employ low-cost metagenomic sequencing data can metabolic potential community, is, ability to produce or utilize specific metabolites. These, turn, potentially serve as markers biochemical pathways are associated with different communities. We...
Abstract Motivation Metagenomics is the study of microbiomes using DNA sequencing. A microbiome consists an assemblage microbes that associated with a ‘theater activity’ (ToA). An important question is, to what degree does taxonomic and functional content former depend on (details the) latter? Here, we investigate related technical question: Given and/or profile estimated from metagenomic sequencing data, how predict ToA? We present deep-learning approach this question. use both profiles as...
Background: To investigate factors associated with COVID-19 infection, hospital admission and disease relapse in patients IgG4-related (IgG4-RD).Methods: Physician-reported IgG4-RD were included this retrospective study. Using multivariable logistic regression analysis to determine for primary outcome (COVID-19-related relapse) secondary (COVID-19 infection admission). Covariates age, sex, body mass index, smoking status, comorbidities, clinical features treatment strategies.Results: Among...
DNA methylation is an epigenetic mechanism for regulating gene expression, and it plays important role in many biological processes. While sites can be identified using laboratory techniques, much work being done on developing computational approaches machine learning. Here, we present a deep-learning algorithm determining the 5-methylcytosine status of sequence. We propose ensemble framework that treats self-attention score as explicit feature added to encoder layer generated by fine-tuned...
DNA 5-methylcytosine modification has been widely studied in mammals and plays an important role epigenetics. Several computational methods exist that determine the methylation state of a sequence centered at possible site. Here, we introduce novel deep-learning framework, MR-DNA, predicts single nucleotide located gene promoter region. The idea is to adapt named-entity recognition approach methylation-site prediction incorporate biological rules during model construction. MR-DNA stacked...
Abstract Motivation Metagenomics is the study of microbiomes using DNA sequencing. A microbiome consists an assemblage microbes that associated with a “theater activity” (ToA). To what degree does taxonomic and functional content former depend on (details the) latter? More technically, given and/or profile estimated from metagenomic sequencing data, how to predict ToA? Here we present deep learning approach this question. We use both profiles as input. apply node2vec embed hierarchical into...
Motivation Metagenomic projects of large sequencing datasets (totaling hundreds gigabytes data). Thus, computational preprocessing and analysis are usually performed on a server rather than personal computer. The results such analyses then explored interactively. One approach is to use MEGAN, an interactive program that allows comparison metagenomic datasets. Previous releases MEGAN have required the user first download computed data from server, increasingly time-consuming process. Here we...
Abstract The current COVID-19 pandemic, caused by the rapid world-wide spread of SARS-CoV-2 virus, is having severe consequences for human health and world economy. virus effects individuals quite differently, with many infected patients showing only mild symptoms, others critical illness. To lessen impact one important question which factors predict death a patient? Here, we construct an enhanced dataset processing two existing databases (from Kaggle WHO) using natural language methods to...
Abstract A microbial community maintains its ecological dynamics via metabolite crosstalk. Hence knowledge of the metabolome, alongside populace, would help us understand functionality a and also predict how it will change in atypical conditions. Methods that employ low-cost metagenomic sequencing data can metabolic potential community, is, ability to produce or utilize specific metabolites. These, turn, potentially serve as markers biochemical pathways are associated with different...
Comments on social media are very diverse, in terms of content, style and vocabulary, which make generating comments much more challenging than other existing natural language generation~(NLG) tasks. Besides, since different user has expression habits, it is necessary to take the user's profile into consideration when comments. In this paper, we introduce task automatic generation personalized comment~(AGPC) for media. Based tens thousands users' real corresponding profiles weibo, propose...