A5001619694- Genomics and Phylogenetic Studies
- Machine Learning in Bioinformatics
- Genome Rearrangement Algorithms
- RNA and protein synthesis mechanisms
- Algorithms and Data Compression
- Computational Drug Discovery Methods
- Chromosomal and Genetic Variations
- Bioinformatics and Genomic Networks
- Advanced biosensing and bioanalysis techniques
- Single-cell and spatial transcriptomics
- Gene expression and cancer classification
- Genomics and Chromatin Dynamics
- Advanced Neural Network Applications
- Protein Structure and Dynamics
- MicroRNA in disease regulation
- Cancer-related molecular mechanisms research
- Medical Image Segmentation Techniques
- Antimicrobial Peptides and Activities
- Extracellular vesicles in disease
- Advanced Biosensing Techniques and Applications
- Cancer Genomics and Diagnostics
- vaccines and immunoinformatics approaches
- RNA Research and Splicing
- Image Processing Techniques and Applications
- Biochemical and Structural Characterization
Shenzhen Institutes of Advanced Technology
2020-2025
Chinese Academy of Sciences
2020-2025
Shenzhen University
2021-2025
Shenzhen Technology University
2024-2025
University of South Carolina
2015-2024
University of Miami
2024
Guangdong Provincial People's Hospital
2024
Sylvester Comprehensive Cancer Center
2024
Central South University
2023
Tianjin University
2013-2022
Although Hi-C technology is one of the most popular tools for studying 3D genome organization, due to sequencing cost, resolution datasets are coarse and cannot be used link distal regulatory elements their target genes. Here we develop HiCPlus, a computational approach based on deep convolutional neural network, infer high-resolution interaction matrices from low-resolution data. We demonstrate that HiCPlus can impute highly similar original ones, while only using 1/16 reads. show models...
It is necessary and essential to discovery protein function from the novel primary sequences. Wet lab experimental procedures are not only time-consuming, but also costly, so predicting structure reliably based on amino acid sequence has significant value. TATA-binding (TBP) a kind of DNA binding protein, which plays key role in transcription regulation. Our study proposed an automatic approach for identifying proteins efficiently, accurately, conveniently. This method would guide special...
Protein-protein interactions (PPIs) are central to a lot of biological processes. Many algorithms and methods have been developed predict PPIs protein interaction networks. However, the application most existing is limited since they difficult compute rely on large number homologous proteins marks partners. In this paper, we propose novel sequence-based approach with multivariate mutual information (MMI) feature representation, for predicting via Random Forest (RF).Our method constructs...
Cell-penetrating peptides (CPPs) are short (5–30 amino acids) that can enter almost any cell without significant damage. On account of their high delivery efficiency, CPPs promising candidates for gene therapy and cancer treatment. Accordingly, techniques correctly predict anticipated to accelerate CPP applications in future therapeutics. Recently, computational methods have been reportedly successful predicting CPPs. Unfortunately, the predictive performance existing is not satisfactory...
Many recent efforts have been made for the development of machine learning-based methods fast and accurate phosphorylation site prediction. Currently, a majority well-performing are based on hybrid information to build prediction models, such as evolutionary information, disorder so on. Unfortunately, this type suffers two major limitations: one is that it would not be much help protein in case no obvious homology detected; other computing complicated time-consuming, which probably limits...
The rapid accumulation of whole-genome data has renewed interest in the study using gene-order for phylogenetic analyses and ancestral reconstruction. Current software web servers typically do not support duplication loss events along with rearrangements. MLGOMLGO (Maximum Likelihood Gene-Order Analysis) is a tool reconstruction phylogeny and/or genomes from data. based on likelihood computation shows advantages over existing methods terms accuracy, scalability flexibility. To best our...
Antiviral peptides (AVPs) have been experimentally verified to block virus into host cells, which antiviral activity with decapeptide amide. Therefore, utilization of validated is a potential alternative strategy for targeting medically important viruses. In this article, we propose dual-channel deep neural network ensemble method analyzing variable-length peptides. The LSTM channel can capture long-term dependencies effectively studying original sequence data. CONV build dynamic the local...
Drug-side effect association contains the information on marketed medicines and their recorded adverse drug reactions. Traditional experimental method is time consuming expensive. All associations of drugs side-effects are seen as a bipartite network. Therefore, many computational approaches have been developed to deal with this problem, which used predict new potential associations. However, lots methods did not consider multiple kernel learning (MKL) algorithm, can integrate sources...
Identification of protein-protein interactions (PPIs) is a difficult and important problem in biology. Since experimental methods for predicting PPIs are both expensive time-consuming, many computational have been developed to predict interaction networks, which can be used complement approaches. However, these limitations overcome. They need large number homology proteins or literature applied their method. In this paper, we propose novel matrix-based protein sequence representation...
Gene regulatory network (GRN) is the important mechanism of maintaining life process, controlling biochemical reaction and regulating compound level, which plays an role in various organisms systems. Reconstructing GRN can help us to understand molecular reveal essential rules a large number biological processes reactions organisms. Various outstanding reconstruction algorithms use specific assumptions that affect prediction accuracy, order deal with uncertainty processing. In study why...
Relationship of accurate associations between non-coding RNAs and diseases could be great help in the treatment human biomedical research. However, traditional technology is only applied on one type RNA or a specific disease, experimental method time-consuming expensive. More computational tools have been proposed to detect new based known ncRNA disease information. Due ncRNAs (circRNAs, miRNAs lncRNAs) having close relationship with progression various diseases, it critical for developing...
Targeted drugs have been applied to the treatment of cancer on a large scale, and some patients certain therapeutic effects. It is time-consuming task detect drug-target interactions (DTIs) through biochemical experiments. At present, machine learning (ML) has widely in large-scale drug screening. However, there are few methods for multiple information fusion. We propose kernel-based triple collaborative matrix factorization (MK-TCMF) method predict DTIs. The kernel matrices (contain...
Abstract Inferring gene regulatory networks (GRNs) based on expression profiles is able to provide an insight into a number of cellular phenotypes from the genomic level and reveal essential laws underlying various life phenomena. Different bulk data, single-cell transcriptomic data embody cell-to-cell variance diverse biological information, such as tissue characteristics, transformation cell types, etc. GRNs offers unprecedented advantages for making profound study phenotypes, revealing...
Detecting potential associations between drugs and diseases plays an indispensable role in drug development, which has also become a research hotspot recent years. Compared with traditional methods, some computational approaches have the advantages of fast speed low cost, greatly accelerate progress predicting drug-disease association. In this study, we propose novel similarity-based method low-rank matrix decomposition based on multi-graph regularization. On basis factorization L2...