A5101736200- Bioinformatics and Genomic Networks
- Computational Drug Discovery Methods
- Machine Learning in Bioinformatics
- Gene Regulatory Network Analysis
- Gene expression and cancer classification
- Genomics and Phylogenetic Studies
- Cancer-related molecular mechanisms research
- Protein Structure and Dynamics
- Viral Infectious Diseases and Gene Expression in Insects
- Epigenetics and DNA Methylation
- Machine Learning in Healthcare
- MicroRNA in disease regulation
- Cancer Genomics and Diagnostics
- Artificial Intelligence in Healthcare
- Genetics, Bioinformatics, and Biomedical Research
- Cholinesterase and Neurodegenerative Diseases
- RNA and protein synthesis mechanisms
- Genomics and Chromatin Dynamics
- vaccines and immunoinformatics approaches
- Algorithms and Data Compression
- Brain Tumor Detection and Classification
- Cell death mechanisms and regulation
- Genomic variations and chromosomal abnormalities
- Single-cell and spatial transcriptomics
- Cholangiocarcinoma and Gallbladder Cancer Studies
Huzhou Central Hospital
2024
Huzhou University
2024
Shanghai Center for Brain Science and Brain-Inspired Technology
2018-2024
Shanghai Institute for Science of Science
2018-2024
Fudan University
2018-2024
Zhejiang University
2019
Tongji University
2012-2016
Chinese Academy of Sciences
2005-2015
Shanghai Institutes for Biological Sciences
2012-2015
Shanghai University
2010-2014
Phosphorylation is the most studied post-translational modification, which crucial for multiple biological processes. Recently, many efforts have been taken to develop computational predictors phosphorylation site prediction, but of them are based on feature selection and discriminative classification. Thus, it useful a novel highly accurate predictor that can unveil intricate patterns automatically protein sites.In this study we present DeepPhos, deep learning architecture prediction...
Abstract Motivation: Reconstruction of gene regulatory networks (GRNs) is utmost interest to biologists and vital for understanding the complex mechanisms within cell. Despite various methods developed reconstruction GRNs from expression profiles, they are notorious high false positive rate owing noise inherited in data, especially dataset with a large number genes but small samples. Results: In this work, we present novel method, namely NARROMI, improve accuracy GRN inference by combining...
Abstract Background Type 1 diabetes (T1D) is a complex disease and harmful to human health, most of the existing biomarkers are mainly measure phenotype after onset (or drastic deterioration). Until now, there no effective biomarker which can predict upcoming pre-disease state) before or deterioration. Further, detail molecular mechanism for such deterioration disease, e.g ., driver genes causal network still unclear. Methods In this study, we detected early-warning signals T1D its leading...
Abstract Motivation: MicroRNAs (miRNAs) are short non-coding RNAs that play important roles in post-transcriptional regulations as well other biological processes. Recently, accumulating evidences indicate miRNAs extensively involved cancer. However, it is a big challenge to identify which related cancer considering the complex processes tumors, where one miRNA may target hundreds or even thousands of genes and gene regulate multiple miRNAs. Despite integrative analysis matched expression...
Despite the explosion in numbers of cancer genomic studies, metastasis is still major cause mortality. In breast cancer, approximately one-fifth metastatic patients survive 5 years. Therefore, detecting at a high risk developing distant first diagnosis critical for effective treatment strategy. We hereby present novel systems biology approach to identify driver mutations escalating based on both exome and RNA sequencing our collected 78 normal-paired cancers. Unlike occurring commonly...
Brain age gap (BAG) is a valuable biomarker for evaluating brain healthy status and detecting age-associated cognitive degeneration. However, the genetic architecture of BAG underlying mechanisms are poorly understood. Here, we estimate from magnetic resonance imaging with improved accuracy using our proposed adversarial convolution network (ACN), followed by applying ACN model to an elder cohort UK Biobank. The heritability significantly enriched in regulatory regions implicated glial...
Fusarium graminearum is the pathogenic agent of head blight (FHB), which a destructive disease on wheat and barley, thereby causing huge economic loss health problems to human by contaminating foods. Identifying genes can shed light pathogenesis underlying interaction between F. its plant host. However, it difficult detect for this pathogen time-consuming expensive molecular biological experiments in lab. On other hand, computational methods provide an alternative way solve problem. Since...
The identification of interactions between drugs and proteins plays key roles in understanding mechanisms underlying drug actions can lead to new design strategies. Here, we present a novel statistical approach, namely PDTD (Predicting Drug Targets with Domains), predict potential target based on derived protein domains. known those that have similar therapeutic effects allow us infer domains which turn leads drug–protein interactions. Benchmarking shows our proposed methodology outperforms...
Amiloride-sensitive epithelial Na(+) channels (ENaC) regulate fluid balance in the alveoli and are regulated by oxidative stress. Since glutathione (GSH) is predominant antioxidant lungs, we proposed that changes redox potential (Eh) would alter cell signaling have an effect on ENaC open probability (Po). In present study, used single channel patch-clamp recordings to examine of stress, via direct application disulfide (GSSG), activity. We found a linear decrease activity as GSH/GSSG Eh...
Abstract The gut microbiota plays a vital role in human health, and significant effort has been made to predict phenotypes, especially diseases, with the as promising indicator or predictor machine learning (ML) methods. However, accuracy is impacted by lot of factors when predicting host phenotypes metagenomic data, e.g. small sample size, class imbalance, high-dimensional features, etc. To address these challenges, we propose MicroHDF, an interpretable deep framework where cascade layers...
Increasing evidence has suggested that microRNAs (miRNAs) played critical roles in cancer development by acting as a tumor suppressor or tumor-promoting genes. However, the role of microRNA-330-3p (miR-330-3p) hepatocellular carcinoma (HCC) is still unknown. This study aimed to investigate expression and miR-330-3p hepatocarcinogenesis.A total 30 human tissues adjacent normal were obtained from patients. Quantitative Real Time-Polymerase Chain Reaction (qRT-PCR) assay was carried out measure...
Adverse drug reactions (ADRs) are the leading factors of attrition in development and post-market withdrawal. The identification potential ADRs can help prevent failure discovery improve efficiency. Furthermore, elucidating possible for known drugs better understand mechanism actions even find new indications old drugs. Unfortunately, only some well-studied available our knowledge about is far from complete. Recently, with more structural omics data available, computational approaches have...
In this study, we propose a new method to predict hairpins in proteins and its evaluation based on the support vector machine. Different from previous methods, feature representation scheme auto covariance is adopted. We also investigate two structure properties of (protein secondary residue conformation propensity), examine their effects prediction. Moreover, employ an ensemble classifier approach majority voting improve prediction accuracy hairpins. Experimental results dataset 1926...
Microarray technology is a useful tool for monitoring the expression levels of thousands genes simultaneously. Recently, mixture modeling has been used to extract signatures from gene profiles. In general, two separate steps are utilized estimate number classes and model parameters, respectively. However, such method often time-consuming leads suboptimal solutions. this paper, we therefore apply one-step approach, namely Rival Penalized Expectation-Maximization (RPEM) algorithm, analyze...
A novel hybrid genetic algorithm (GA)/radial basis function neural network (RBFNN) technique, which selects features from the protein sequences and trains RBF simultaneously, is proposed in this paper. Experimental results show that GA/RBFNN system outperforms BLAST HMMer. Keywords: classification, ga/rbfnn method, feature selection
Understanding the molecular mechanism that underlies differentiation of neural stem cells (NSCs) is vital to develop regenerative medicines for neurological disorders. In our previous work, Rho-GDI-γ was found be able prompt neuronal when it down regulated. However, unclear how regulates this process. Therefore, a novel systems biology approach presented here identify putative signalling pathways regulated by during NSC differentiation, and these can provide insights into mechanisms....
The timely and accurate diagnosis of Alzheimer's Disease (AD) is important for preventing the progress irreversible disease. Recently, various types imaging techniques, e.g. Magnetic Resonance Imaging (MRI) Positron Emission Tomography (PET), have been widely used AD. Despite their usefulness, image data generated are high-dimensional noisy which make it difficult to give diagnosis. In this paper, we propose a novel feature selection approach detect informative features from MRI data,...
Abstract The integration of expression quantitative trait loci (eQTLs) and genome-wide association study (GWAS) findings to identify causal genes aids in elucidating the biological mechanisms discovery potential drug targets underlying complex traits. This can be achieved by Mendelian randomization (MR), but date, most MR studies investigating contribution brain phenotypes have been conducted on heterogeneous tissues not specific cell types, thus limiting our knowledge at cellular level. In...
The papers in this special issue were presented at the Chinese Control Conference (CCC2015), which was successfully held Hangzhou, China, during July 28 to 30, 2015. conference has provided an opportunity for scientists and researchers from different backgrounds present their latest works on data mining systems biology.