Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
19,032
result(s) for
"Guo, Song"
Sort by:
Edge learning for distributed big data analytics : theory, algorithms, and system design
\"\"Traditionally, to develop these intelligent services and applications, big data are stored and processed in a centralized model. However, with the proliferation of edge devices and edge data, traditional centralized learning frameworks are required to upload all training data from different sources to a remote data server, which incurs significant communication overhead, service latency, as well as security and privacy issues. Therefore, it is urgent to shift model training and inference from the cloud to the edge, which is the essential idea of edge learning. Edge Learning is a fusion of big data, edge computing, and machine learning, and it is an enabling technology for edge intelligence. This book presents the basic knowledge of training machine learning models, key challenges and issues in edge learning, and comprehensive techniques from three aspects, i.e., fundamental theory, edge learning algorithms, and system design issues in edge learning. We believe that this book will stimulate fruitful discussions, inspire further research ideas, and attract researchers and developers from both academia and industry in this field\"-- Provided by publisher.
Book
LightEyes: A Lightweight Fundus Segmentation Network for Mobile Edge Computing
Fundus is the only structure that can be observed without trauma to the human body. By analyzing color fundus images, the diagnosis basis for various diseases can be obtained. Recently, fundus image segmentation has witnessed vast progress with the development of deep learning. However, the improvement of segmentation accuracy comes with the complexity of deep models. As a result, these models show low inference speeds and high memory usages when deploying to mobile edges. To promote the deployment of deep fundus segmentation models to mobile devices, we aim to design a lightweight fundus segmentation network. Our observation comes from the fact that high-resolution representations could boost the segmentation of tiny fundus structures, and the classification of small fundus structures depends more on local features. To this end, we propose a lightweight segmentation model called LightEyes. We first design a high-resolution backbone network to learn high-resolution representations, so that the spatial relationship between feature maps can be always retained. Meanwhile, considering high-resolution features means high memory usage; for each layer, we use at most 16 convolutional filters to reduce memory usage and decrease training difficulty. LightEyes has been verified on three kinds of fundus segmentation tasks, including the hard exudate, the microaneurysm, and the vessel, on five publicly available datasets. Experimental results show that LightEyes achieves highly competitive segmentation accuracy and segmentation speed compared with state-of-the-art fundus segmentation models, while running at 1.6 images/s Cambricon-1A speed and 51.3 images/s GPU speed with only 36k parameters.
Journal Article
Hall of Fame among Pro-inflammatory Cytokines: Interleukin-6 Gene and Its Transcriptional Regulation Mechanisms
Pro-inflammatory cytokines that are generated by immune system cells and mediate many kinds of immune responses are kinds of endogenous polypeptides. They are also the effectors of the autoimmune system. It is generally accepted that interleukin (IL)-4, IL-6, IL-9, IL-17, and tumor necrosis factor-α are pro-inflammatory cytokines; however, IL-6 becomes a protagonist among them since it predominately induces pro-inflammatory signaling and regulates massive cellular processes. It has been ascertained that IL-6 is associated with a large number of diseases with inflammatory background, such as anemia of chronic diseases, angiogenesis acute-phase response, bone metabolism, cartilage metabolism, and multiple cancers. Despite great progress in the relative field, the targeted regulation of IL-6 response for therapeutic benefits remains incompletely to be understood. Therefore, it is conceivable that understanding mechanisms of IL-6 from the perspective of gene regulation can better facilitate to determine the pathogenesis of the disease, providing more solid scientific basis for clinical treatment translation. In this review, we summarize the candidate genes that have been implicated in clinical target therapy from the perspective of gene transcription regulation.
Journal Article
Research Progress of Small Molecule Fluorescent Probes for Detecting Hypochlorite
Hypochlorous acid (HOCl) generates from the reaction between hydrogen peroxide and chloride ions via myeloperoxidase (MPO)-mediated in vivo. As very important reactive oxygen species (ROS), hypochlorous acid (HOCl)/hypochlorite (OCl−) play a crucial role in a variety of physiological and pathological processes. However, excessive or misplaced production of HOCl/OCl− can cause variety of tissue damage and human diseases. Therefore, rapid, sensitive, and selective detection of OCl− is very important. In recent years, the fluorescent probe method for detecting hypochlorous acid has been developed rapidly due to its simple operation, low toxicity, high sensitivity, and high selectivity. In this review, the progress of recently discovered fluorescent probes for the detection of hypochlorous acid was summarized with the aim to provide useful information for further design of better fluorescent probes.
Journal Article
Artificial intelligence alphafold model for molecular biology and drug discovery: a machine-learning-driven informatics investigation
AlphaFold model has reshaped biological research. However, vast unstructured data in the entire AlphaFold field requires further analysis to fully understand the current research landscape and guide future exploration. Thus, this scientometric analysis aimed to identify critical research clusters, track emerging trends, and highlight underexplored areas in this field by utilizing machine-learning-driven informatics methods. Quantitative statistical analysis reveals that the AlphaFold field is enjoying an astonishing development trend (Annual Growth Rate = 180.13%) and global collaboration (International Co-authorship = 33.33%). Unsupervised clustering algorithm, time series tracking, and global impact assessment point out that Cluster 3 (Artificial Intelligence-Powered Advancements in AlphaFold for Structural Biology) has the greatest influence (Average Citation = 48.36 ± 184.98). Additionally, regression curve and hotspot burst analysis highlight “structure prediction” (s = 12.40, R
2
= 0.9480,
p
= 0.0051), “artificial intelligence” (s = 5.00, R
2
= 0.8096,
p
= 0.0375), “drug discovery” (s = 1.90, R
2
= 0.7987,
p
= 0.0409), and “molecular dynamics” (s = 2.40, R
2
= 0.8000,
p
= 0.0405) as core hotspots driving the research frontier. More importantly, the Walktrap algorithm further reveals that “structure prediction, artificial intelligence, molecular dynamics” (Relevance Percentage[RP] = 100%, Development Percentage[DP] = 25.0%), “sars-cov-2, covid-19, vaccine design” (RP = 97.8%, DP = 37.5%), and “homology modeling, virtual screening, membrane protein” (RP = 89.9%, DP = 26.1%) are closely intertwined with the AlphaFold model but remain underexplored, which implies a broad exploration space. In conclusion, through the machine-learning-driven informatics methods, this scientometric analysis offers an objective and comprehensive overview of global AlphaFold research, identifying critical research clusters and hotspots while prospectively pointing out underexplored critical areas.
Journal Article
Agrobacterium-Mediated Transformation of Tree Fruit Crops: Methods, Progress, and Challenges
Genetic engineering based on
-mediated transformation has been a desirable tool to manipulate single or multiple genes of existing genotypes of woody fruit crops, for which conventional breeding is a difficult and lengthy process due to heterozygosity, sexual incompatibility, juvenility, or a lack of natural sources. To date, successful transformation has been reported for many fruit crops. We review the major progress in genetic transformation of these fruit crops made in the past 5 years, emphasizing reproducible transformation protocols as well as the strategies that have been tested in fruit crops. While direct transformation of scion cultivars was mostly used for fruit quality improvement, biotic and abiotic tolerance, and functional gene analysis, transgrafting on genetically modified (GM) rootstocks showed a potential to produce non-GM fruit products. More recently, genome editing technology has demonstrated a potential for gene(s) manipulation of several fruit crops. However, substantial efforts are still needed to produce plants from gene-edited cells, for which tremendous challenge remains in the context of either cell's recalcitrance to regeneration or inefficient gene-editing due to their polyploidy. We propose that effective transient transformation and efficient regeneration are the key for future utilization of genome editing technologies for improvement of fruit crops.
Journal Article
Expression of a maize SOC1 gene enhances soybean yield potential through modulating plant growth and flowering
Yield enhancement is a top priority for soybean (
Glycine max
Merr.) breeding.
SUPPRESSOR OF OVEREXPRESSION OF CONSTANS 1
(
SOC1
) is a major integrator in flowering pathway, and it is anticipated to be capable of regulating soybean reproductive stages through its interactions with other MADS-box genes. Thus, we produced transgenic soybean for a constitutive expression of a maize
SOC1
(
ZmSOC1
). T
1
transgenic plants, in comparison with the nontransgenic plants, showed early flowering, reduced height of mature plants, and no significant impact on grain quality. The transgenic plants also had a 13.5–23.2% of higher grain weight per plant than the nontransgenic plants in two experiments. Transcriptome analysis in the leaves of 34-day old plants revealed 58 differentially expressed genes (DEGs) responding to the expression of the
ZmSOC1
, of which the upregulated
FRUITFULL
MADS-box gene, as well as the transcription factor
VASCULAR PLANT ONE-ZINC FINGER1
, contributed to the promoted flowering. The downregulated gibberellin receptor GID1B could play a major role in reducing the plant height. The remaining DEGs suggested broader effects on the other unmeasured traits (e.g., photosynthesis efficiency and abiotic tolerance), which could contribute to yield increase. Overall, modulating expression of
SOC1
in soybean provides a novel and promising approach to regulate plant growth and reproductive development and thus has a potential either to enhance grain yield or to change plant adaptability.
Journal Article
Roles of Selenoproteins in Brain Function and the Potential Mechanism of Selenium in Alzheimer’s Disease
Selenium (Se) and its compounds have been reported to have great potential in the prevention and treatment of Alzheimer’s disease (AD). However, little is known about the functional mechanism of Se in these processes, limiting its further clinical application. Se exerts its biological functions mainly through selenoproteins, which play vital roles in maintaining optimal brain function. Therefore, selenoproteins, especially brain function-associated selenoproteins, may be involved in the pathogenesis of AD. Here, we analyze the expression and distribution of 25 selenoproteins in the brain and summarize the relationships between selenoproteins and brain function by reviewing recent literature and information contained in relevant databases to identify selenoproteins (GPX4, SELENOP, SELENOK, SELENOT, GPX1, SELENOM, SELENOS, and SELENOW) that are highly expressed specifically in AD-related brain regions and closely associated with brain function. Finally, the potential functions of these selenoproteins in AD are discussed, for example, the function of GPX4 in ferroptosis and the effects of the endoplasmic reticulum (ER)-resident protein SELENOK on Ca 2+ homeostasis and receptor-mediated synaptic functions. This review discusses selenoproteins that are closely associated with brain function and the relevant pathways of their involvement in AD pathology to provide new directions for research on the mechanism of Se in AD.
Journal Article
Role of TNF–TNF Receptor 2 Signal in Regulatory T Cells and Its Therapeutic Implications
Tumor necrosis factor α (TNFα) is a pleiotropic cytokine which signals through TNF receptor 1 (TNFR1) and TNF receptor 2 (TNFR2). Emerging evidence has demonstrated that TNFR1 is ubiquitously expressed on almost all cells, while TNFR2 exhibits a limited expression, predominantly on regulatory T cells (Tregs). In addition, the signaling pathway by sTNF
TNFR1 mainly triggers pro-inflammatory pathways, and mTNF binding to TNFR2 usually initiates immune modulation and tissue regeneration. TNFα plays a critical role in upregulation or downregulation of Treg activity. Deficiency in TNFR2 signaling is significant in various autoimmune diseases. An ideal therapeutic strategy for autoimmune diseases would be to selectively block the sTNF/TNFR1 signal through the administration of sTNF inhibitors, or using TNFR1 antagonists while keeping the TNFR2 signaling pathway intact. Another promising strategy would be to rely on TNFR2 agonists which could drive the expansion of Tregs and promote tissue regeneration. Design of these therapeutic strategies targeting the TNFR1 or TNFR2 signaling pathways holds promise for the treatment of diverse inflammatory and degenerative diseases.
Journal Article