Planetary surfaces,shaped by billions of years of geologic evolution,display numerous impact craters whose distribution of size,density,and spatial arrangement reveals the celestial body's history.Identifying thes...Planetary surfaces,shaped by billions of years of geologic evolution,display numerous impact craters whose distribution of size,density,and spatial arrangement reveals the celestial body's history.Identifying these craters is essential for planetary science and is currently mainly achieved with deep learning-driven detection algorithms.However,because impact crater characteristics are substantially affected by the geologic environment,surface materials,and atmospheric conditions,the performance of deep learning models can be inconsistent between celestial bodies.In this paper,we first examine how the surface characteristics of the Moon,Mars,and Earth,along with the differences in their impact crater features,affect model performance.Then,we compare crater detection across celestial bodies by analyzing enhanced convolutional neural networks and U-shaped Convolutional Neural Network-based models to highlight how geology,data,and model design affect accuracy and generalization.Finally,we address current deep learning challenges,suggest directions for model improvement,such as multimodal data fusion and cross-planet learning and list available impact crater databases.This review can provide necessary technical support for deep space exploration and planetary science,as well as new ideas and directions for future research on automatic detection of impact craters on celestial body surfaces and on planetary geology.展开更多
Benzotriazole UV stabilizers (BT-UVs) have attracted concems due to their ubiquitous occurrence in the aquatic environment,and their bioaccumulative and toxic properties.However,little is known about their aquatic env...Benzotriazole UV stabilizers (BT-UVs) have attracted concems due to their ubiquitous occurrence in the aquatic environment,and their bioaccumulative and toxic properties.However,little is known about their aquatic environmental degradation behavior.In this study,photodegradation of a representative of BT-UVs,2-(2-hydroxy-5-methylphenyl) benzotriazole (UV-P),was investigated under simulated sunlight irradiation.Results show that UV-P photodegrades slower under neutral conditions (neutral form) than under acidic or alkaline conditions (cationic and anionic forms).Indirect photodegradation is a dominant elimination pathway of UV-P in coastal seawaters.Dissolved organic matter (DOM) from seawaters accelerate the photodegradation rates mainly through excited triplet DOM (3DOM*),and the roles of singlet oxygen and hydroxyl radical are negligible in the matrixes.DOM from seawaters impacted by mariculture exhibits higher steady-state concentration of 3DOM*([3DOM*]) relative to those from pristine seawaters,leading to higher photosensitizing effects on the photodegradation.Halide ions inhibit the DOM-sensitized photodegradation of UV-P by decreasing [3DOM*].Photodegradation half-lives of UV-P are estimated to range from 24.38 to 49.66 hr in field water bodies of the Yellow River estuary.These results are of importance for assessing environmental fate and risk UV-P in coastal water bodies.展开更多
Understanding protein corona composition is essential for evaluating their potential applications in biomedicine.Relative protein abundance(RPA),accounting for the total proteins in the corona,is an important paramete...Understanding protein corona composition is essential for evaluating their potential applications in biomedicine.Relative protein abundance(RPA),accounting for the total proteins in the corona,is an important parameter for describing the protein corona.For the first time,we comprehensively predicted the RPA of multiple proteins on the protein corona.First,we used multiple machine learning algorithms to predict whether a protein adsorbs to a nanoparticle,which is dichotomous prediction.Then,we selected the top 3 performing machine learning algorithms in dichotomous prediction to predict the specific value of RPA,which is regression prediction.Meanwhile,we analyzed the advantages and disadvantages of different machine learning algorithms for RPA prediction through interpretable analysis.Finally,we mined important features about the RPA prediction,which provided effective suggestions for the preliminary design of protein corona.The service for the prediction of RPA is available at http://www.bioai-lab.com/PC_ML.展开更多
Background:Pressure ulcers(PUs)are a major clinical problem that constitutes a tremendous economic burden on healthcare systems.Deep tissue injury(DTI)is a unique serious type of pressure ulcer that arises in skeletal...Background:Pressure ulcers(PUs)are a major clinical problem that constitutes a tremendous economic burden on healthcare systems.Deep tissue injury(DTI)is a unique serious type of pressure ulcer that arises in skeletal muscle tissue.DTI arises in part because skeletal muscle tissues are more susceptible than skin to external compression.Unfortunately,few effective therapies are currently available for muscle injury.Basic fibroblast growth factor(bFGF),a potent mitogen and survival factor for various cells,plays a crucial role in the regulation of muscle development and homeostasis.The main purpose of this study was to test whether local administration of bFGF could accelerate muscle regeneration in a rat DTI model.Methods:Male Sprague Dawley(SD)rats(age 12 weeks)were individually housed in plastic cages and a DTI PU model was induced according to methods described before.Animals were randomly divided into three groups:a normal group,a PU group treated with saline,and a PU group treated with bFGF(10μg/0.1 ml)subcutaneously near the wound.Results:We found that application of bFGF accelerated the rate of wound closure and promoted cell proliferation and tissue angiogenesis.In addition,compared to saline administration,bFGF treatment prevented collagen deposition,a measure of fibrosis,and up-regulated the myogenic marker proteins MyHC and myogenin,suggesting bFGF promoted injured muscle regeneration.Moreover,bFGF treatment increased levels of myogenesis-related proteins p-Akt and p-mTOR.Conclusions:Our findings show that bFGF accelerated injured skeletal muscle regeneration through activation of the PI3K/Akt/mTOR signaling pathway and suggest that administration of bFGF is a potential therapeutic strategy for the treatment of skeletal muscle injury in PUs.展开更多
An intelligent and efficient methodology is needed owning to the continuous increase of global municipal solid waste(MSW).This is because the common methods of manual and semi-mechanical screenings not only consume la...An intelligent and efficient methodology is needed owning to the continuous increase of global municipal solid waste(MSW).This is because the common methods of manual and semi-mechanical screenings not only consume large amount of manpower and material resources but also accelerate virus community transmission.As the categories of MSW are diverse considering their compositions,chemical reactions,and processing procedures,etc.,resulting in low efficiencies in MSW sorting using the traditional methods.Deep machine learning can help MSW sorting becoming into a smarter and more efficient mode.This study for the first time applied MSWNet in MSW sorting,a ResNet-50 with transfer learning.The method of cyclical learning rate was taken to avoid blind finding,and tests were repeated until accidentally encountering a good value.Measures of visualization were also considered to make the MSWNet model more transparent and accountable.Results showed transfer learning enhanced the efficiency of training time(from 741 s to 598.5 s),and improved the accuracy of recognition performance(from 88.50%to 93.50%);MSWNet showed a better performance in MSW classsification in terms of sensitivity(93.50%),precision(93.40%),F1-score(93.40%),accuracy(93.50%)and AUC(92.00%).The findings of this study can be taken as a reference for building the model MSW classification by deep learning,quantifying a suitable learning rate,and changing the data from high dimensions to two dimensions.展开更多
基金funded by the National Natural Science Foundation of China(12363009 and 12103020)Natural Science Foundation of Jiangxi Province(20224BAB211011)+1 种基金Youth Talent Project of Science and Technology Plan of Ganzhou(2022CXRC9191 and 2023CYZ26970)Jiangxi Province Graduate Innovation Special Funds Project(YC2024-S529 and YC2023-S672).
文摘Planetary surfaces,shaped by billions of years of geologic evolution,display numerous impact craters whose distribution of size,density,and spatial arrangement reveals the celestial body's history.Identifying these craters is essential for planetary science and is currently mainly achieved with deep learning-driven detection algorithms.However,because impact crater characteristics are substantially affected by the geologic environment,surface materials,and atmospheric conditions,the performance of deep learning models can be inconsistent between celestial bodies.In this paper,we first examine how the surface characteristics of the Moon,Mars,and Earth,along with the differences in their impact crater features,affect model performance.Then,we compare crater detection across celestial bodies by analyzing enhanced convolutional neural networks and U-shaped Convolutional Neural Network-based models to highlight how geology,data,and model design affect accuracy and generalization.Finally,we address current deep learning challenges,suggest directions for model improvement,such as multimodal data fusion and cross-planet learning and list available impact crater databases.This review can provide necessary technical support for deep space exploration and planetary science,as well as new ideas and directions for future research on automatic detection of impact craters on celestial body surfaces and on planetary geology.
基金supported by the National Key R&D Program of China(No.2018YFC1801604)the National Natural Science Foundation of China(No.21661142001)
文摘Benzotriazole UV stabilizers (BT-UVs) have attracted concems due to their ubiquitous occurrence in the aquatic environment,and their bioaccumulative and toxic properties.However,little is known about their aquatic environmental degradation behavior.In this study,photodegradation of a representative of BT-UVs,2-(2-hydroxy-5-methylphenyl) benzotriazole (UV-P),was investigated under simulated sunlight irradiation.Results show that UV-P photodegrades slower under neutral conditions (neutral form) than under acidic or alkaline conditions (cationic and anionic forms).Indirect photodegradation is a dominant elimination pathway of UV-P in coastal seawaters.Dissolved organic matter (DOM) from seawaters accelerate the photodegradation rates mainly through excited triplet DOM (3DOM*),and the roles of singlet oxygen and hydroxyl radical are negligible in the matrixes.DOM from seawaters impacted by mariculture exhibits higher steady-state concentration of 3DOM*([3DOM*]) relative to those from pristine seawaters,leading to higher photosensitizing effects on the photodegradation.Halide ions inhibit the DOM-sensitized photodegradation of UV-P by decreasing [3DOM*].Photodegradation half-lives of UV-P are estimated to range from 24.38 to 49.66 hr in field water bodies of the Yellow River estuary.These results are of importance for assessing environmental fate and risk UV-P in coastal water bodies.
基金supported by the National Natural Science Foundation of China(nos.62i01100 and 62262015).
文摘Understanding protein corona composition is essential for evaluating their potential applications in biomedicine.Relative protein abundance(RPA),accounting for the total proteins in the corona,is an important parameter for describing the protein corona.For the first time,we comprehensively predicted the RPA of multiple proteins on the protein corona.First,we used multiple machine learning algorithms to predict whether a protein adsorbs to a nanoparticle,which is dichotomous prediction.Then,we selected the top 3 performing machine learning algorithms in dichotomous prediction to predict the specific value of RPA,which is regression prediction.Meanwhile,we analyzed the advantages and disadvantages of different machine learning algorithms for RPA prediction through interpretable analysis.Finally,we mined important features about the RPA prediction,which provided effective suggestions for the preliminary design of protein corona.The service for the prediction of RPA is available at http://www.bioai-lab.com/PC_ML.
基金This study was supported by research grants from the Zhejiang Provincial Natural Science Funding(LY14H150008)the National Natural Science Funding of China(81372064,81472165,and 81572237)+2 种基金the Zhejiang Provincial Program of Medical and Health Science(2014KYA131)the Wenzhou Program of Science and Technology(Y20140003)the State Key Basic Research Development Program(2012CB518105)
文摘Background:Pressure ulcers(PUs)are a major clinical problem that constitutes a tremendous economic burden on healthcare systems.Deep tissue injury(DTI)is a unique serious type of pressure ulcer that arises in skeletal muscle tissue.DTI arises in part because skeletal muscle tissues are more susceptible than skin to external compression.Unfortunately,few effective therapies are currently available for muscle injury.Basic fibroblast growth factor(bFGF),a potent mitogen and survival factor for various cells,plays a crucial role in the regulation of muscle development and homeostasis.The main purpose of this study was to test whether local administration of bFGF could accelerate muscle regeneration in a rat DTI model.Methods:Male Sprague Dawley(SD)rats(age 12 weeks)were individually housed in plastic cages and a DTI PU model was induced according to methods described before.Animals were randomly divided into three groups:a normal group,a PU group treated with saline,and a PU group treated with bFGF(10μg/0.1 ml)subcutaneously near the wound.Results:We found that application of bFGF accelerated the rate of wound closure and promoted cell proliferation and tissue angiogenesis.In addition,compared to saline administration,bFGF treatment prevented collagen deposition,a measure of fibrosis,and up-regulated the myogenic marker proteins MyHC and myogenin,suggesting bFGF promoted injured muscle regeneration.Moreover,bFGF treatment increased levels of myogenesis-related proteins p-Akt and p-mTOR.Conclusions:Our findings show that bFGF accelerated injured skeletal muscle regeneration through activation of the PI3K/Akt/mTOR signaling pathway and suggest that administration of bFGF is a potential therapeutic strategy for the treatment of skeletal muscle injury in PUs.
基金This work was financially supported by the China Scholarship Council(No.202206260111)the Research Project of Shanghai Chengtou Group Co.,Ltd.(China)(CTKY-LGZX-2020-005-02).
文摘An intelligent and efficient methodology is needed owning to the continuous increase of global municipal solid waste(MSW).This is because the common methods of manual and semi-mechanical screenings not only consume large amount of manpower and material resources but also accelerate virus community transmission.As the categories of MSW are diverse considering their compositions,chemical reactions,and processing procedures,etc.,resulting in low efficiencies in MSW sorting using the traditional methods.Deep machine learning can help MSW sorting becoming into a smarter and more efficient mode.This study for the first time applied MSWNet in MSW sorting,a ResNet-50 with transfer learning.The method of cyclical learning rate was taken to avoid blind finding,and tests were repeated until accidentally encountering a good value.Measures of visualization were also considered to make the MSWNet model more transparent and accountable.Results showed transfer learning enhanced the efficiency of training time(from 741 s to 598.5 s),and improved the accuracy of recognition performance(from 88.50%to 93.50%);MSWNet showed a better performance in MSW classsification in terms of sensitivity(93.50%),precision(93.40%),F1-score(93.40%),accuracy(93.50%)and AUC(92.00%).The findings of this study can be taken as a reference for building the model MSW classification by deep learning,quantifying a suitable learning rate,and changing the data from high dimensions to two dimensions.
