A5100363203- Bioinformatics and Genomic Networks
- Cancer-related molecular mechanisms research
- RNA modifications and cancer
- Genomics and Phylogenetic Studies
- Gene expression and cancer classification
- Topic Modeling
- Machine Learning in Bioinformatics
- Natural Language Processing Techniques
- Computational Drug Discovery Methods
- Molecular Biology Techniques and Applications
- RNA and protein synthesis mechanisms
- MicroRNA in disease regulation
- Advanced Graph Neural Networks
- Single-cell and spatial transcriptomics
- Biometric Identification and Security
- Circular RNAs in diseases
- Invertebrate Immune Response Mechanisms
- Text Readability and Simplification
- Aquaculture disease management and microbiota
- Advanced Image Processing Techniques
- Biomedical Text Mining and Ontologies
- Dyeing and Modifying Textile Fibers
- Research in Cotton Cultivation
- Algorithms and Data Compression
- Complexity and Algorithms in Graphs
Sanya University
2025
Hainan University
2022-2025
Sun Yat-sen University
2022-2025
Shanghai University of Electric Power
2024
Harbin Institute of Technology
2017-2024
China Pharmaceutical University
2024
Aoyama Gakuin University
2024
Shenzhen Institute of Information Technology
2018-2024
Jinzhou Medical University
2024
Shanghai Electric (China)
2024
Text generation has become one of the most important yet challenging tasks in natural language processing (NLP). The resurgence deep learning greatly advanced this field by neural models, especially paradigm pretrained models (PLMs). In paper, we present an overview major advances achieved topic PLMs for text generation. As preliminaries, general task definition and briefly describe mainstream architectures core content, discuss how to adapt existing model different input data satisfy...
Multi-modal pre-training models have been intensively explored to bridge vision and language in recent years. However, most of them explicitly model the cross-modal interaction between image-text pairs, by assuming that there exists strong semantic correlation text image modalities. Since this assumption is often invalid real-world scenarios, we choose implicitly for large-scale multi-modal pre-training, which focus Chinese project `WenLan' led our team. Specifically, with weak over propose...
Significant progress has been made in self-supervised image denoising (SSID) the recent few years. However, most methods focus on dealing with spatially independent noise, and they have little practicality real-world sRGB images correlated noise. Although pixel-shuffle downsampling suggested for breaking noise correlation, it breaks original information of images, which limits performance. In this paper, we propose a novel perspective to solve problem, i.e., seeking adaptive supervision...
Abstract Metagenomic binning is an essential technique for genome-resolved characterization of uncultured microorganisms in various ecosystems but hampered by the low efficiency tools adequately recovering metagenome-assembled genomes (MAGs). Here, we introduce BASALT ( B inning A cross a S eries ssemb l ies T oolkit) and refinement short- long-read sequencing data. employs multiple binners with thresholds to produce initial bins, then utilizes neural networks identify core sequences remove...
Recent studies have demonstrated that specificity is an important characterization of texts potentially beneficial for a range applications such as multi-document news summarization and analysis science journalism. The feasibility automatically predicting sentence from rich set features has also been confirmed in prior work. In this paper we present practical system which exploits only require minimum processing trained semi-supervised manner. Our outperforms the state-of-the-art method does...
With the construction and promotion of Ubiquitous Power Internet Things (UPIoT), it is an increasingly urgent challenge to comprehensively improve recognition accuracy gasinsulated switchgear (GIS) partial discharge (PD), incorporate model into UPIoT intelligent terminals supported by edge computing in embedded systems.Therefore, this paper proposes a novel MobileNets convolutional neural network (MCNN) identify GIS PD patterns.We first construct pattern classification datasets means...
The alignment of long-read RNA sequencing reads is non-trivial due to high errors and complicated gene structures. We propose deSALT, a tailored two-pass approach, which constructs graph-based skeletons infer exons uses them generate spliced reference sequences produce refined alignments. deSALT addresses several difficult technical issues, such as small errors, break through bottlenecks long RNA-seq read alignment. Benchmarks demonstrate that has greater ability accurate homogeneous...
Abstract Motivation In recent years, there has been a breakthrough in protein structure prediction, and the AlphaFold2 model of DeepMind team improved accuracy prediction to atomic level. Currently, deep learning-based function models usually extract features from sequences combine them with protein–protein interaction networks achieve good results. However, for newly sequenced proteins that are not network, such cannot make effective predictions. To address this, this article proposes...
Concurrent use of multiple drugs can lead to unexpected adverse drug reactions. The interaction between be confirmed by routine in vitro and clinical trials. However, it is difficult test the drug-drug interactions widely effectively before enter market. Therefore, prediction has become one research priorities biomedical field. In recent years, researchers have been using deep learning predict exploiting structural features graph theory, achieved a series achievements. A model SmileGNN...
Microscopic images are widely used in basic biomedical research, disease diagnosis and medical discovery. Obtaining high-quality in-focus microscopy has been a cornerstone of the microscopy. However, obtained by microscopes often out-of-focus, resulting poor performance research diagnosis.
Abstract Motivation Synthetic lethality (SL) is a form of genetic interaction that can selectively kill cancer cells without damaging normal cells. Exploiting this mechanism gaining popularity in the field targeted therapy and anticancer drug development. Due to limitations identifying SL interactions from laboratory experiments, an increasing number research groups are devising computational prediction methods guide discovery potential pairs. Although existing have attempted capture...
Abstract Antigen-specific T cell receptor-engineered (TCR-T) based immunotherapy has proven to be an effective method combat cancer. In recent years, cross-talk between the innate and adaptive immune systems may requisite optimize sustained antigen-specific immunity, stimulator of interferon genes (STING) is a promising therapeutic target for cancer immunotherapy. The level expression or presentation antigen in tumor cells affects recognition killing by TCR-T. This study aimed at...
To ensure US patients realize the public health benefit of a robust, competitive market for biosimilar products, Food and Drug Administration (FDA) is focused on improving efficiency development approvals. As comparative clinical studies can be costly time consuming, FDA currently conducting research to inform agency's thinking critical aspects use pharmacodynamic (PD) biomarkers demonstrate biosimilarity, which either streamline or negate need studies. A biological product that highly...
The growing maturity of single-cell RNA-sequencing (scRNA-seq) technology allows us to explore the heterogeneity tissues, organisms, and complex diseases at cellular level. In data analysis, clustering calculation is very important. However, high dimensionality scRNA-seq data, ever-increasing number cells, unavoidable technical noise bring great challenges calculations. Motivated by good performance contrastive learning in multiple domains, we propose ScCCL, a novel self-supervised method...
Swine wastewater is considered one of the major pollution sources antibiotic resistance to environment. In this study, elimination antibiotic-resistant bacteria (ARB) and genes (ARGs) through various treatment processes, including ultraviolet (UV), O3, their combined in biotreated swine was investigated. The combination modes UV O3 were optimized, mechanisms underlying ARG removal explored by assessing destruction intracellular ARGs (i-ARGs) extracellular (e-ARGs). results indicated that...
Cardiovascular disease has become a common ailment that endangers human health, having garnered widespread attention due to its high prevalence, recurrence rate, and sudden death risk. Ginseng possesses functions such as invigorating vital energy, enhancing vein recovery, promoting body fluid blood nourishment, calming the nerves, improving cognitive function. It is widely utilized in treatment of various heart conditions, including palpitations, chest pain, failure, other ailments. Although...
Rubber particles (RPs) are specialized organelles for the biosynthesis and storage of natural rubber in rubber-producing plants. However, mechanisms underlying biogenesis development RPs remain unclear. In this study, two latex-specific cis-prenyltransferases (CPTs), TkCPT1 TkCPT2, were identified Taraxacum kok-saghyz, with almost identical orthologues retained across other species. For first time, Tkcpt1 single Tkcpt1/2 double mutants successfully generated using CRISPR/Cas9 system. was...