Channelization typically realized by digital filter banks is an important topic in high frequency(HF) communication and software defined radios(SDR) areas. Channelization has a rigorous requirement for the characteris...Channelization typically realized by digital filter banks is an important topic in high frequency(HF) communication and software defined radios(SDR) areas. Channelization has a rigorous requirement for the characteristic of frequency response, e.g., steep transitional band and sharp decay. To address this issue, we investigated the feasibility and implementation of applying fast filter bank(FFB) in channelization in this paper. We analyzed the butterfly structure of FFB similar with fast Fourier transform(FFT), in which prototype sub-filters are cascaded to achieve a low complexity. Hence, it is suitable for designing filter bank with steep transitional band and sharp decay in stop-band. Moreover, we designed a pipelined structure of FFB to achieve a balance between area and performance. Design example shows that FFB has lower computational complexity compared with the other filter banks.展开更多
A multistandard software-defined radio base station must perform non-uniform channelization of multiplexed frequency bands. Non-uniform channelization accounts for a significant portion of the digital signal processin...A multistandard software-defined radio base station must perform non-uniform channelization of multiplexed frequency bands. Non-uniform channelization accounts for a significant portion of the digital signal processing workload in the base station receiver and can be difficult to realize in a physical implementation. In non-uniform channelization methods based on generalized DFT filter banks, large prototype filter orders are a significant issue for implementation. In this paper, a multistage filter design is applied to two different non-uniform generalized DFT-based channelizers in order to reduce their filter orders. To evaluate the approach, a TETRA and TEDS base station is used. Experimental results show that the new multistage design reduces both the number of coefficients and operations and leads to a more feasible design and practical physical implementation.展开更多
Channel straightening in a naturally meandering river is a common historical trigger of channel incision which typically results in stream bank destabilization. Several of the larger river systems in the upland portio...Channel straightening in a naturally meandering river is a common historical trigger of channel incision which typically results in stream bank destabilization. Several of the larger river systems in the upland portion of the Yazoo River Basin have subjected channelization resulting in profound changes in the physical and geomorphological characteristics of these systems. Fish were sampled using electroshocking gear and hoop nets to evaluate the impact of stream bank destabilization and loss of habitat heterogeneity resulting from channelization on fish communities. While distinct differences in the fish communities were evident, only the Skuna appeared to have characteristics of a damaged system. More than 95% of the biomass was comprised of species reaching an adult length of less than 300 mm. The lotic omnivorous fishes that dominated the biomass from Skuna are often associated with smaller streams rather than rivers. Furthermore, 72% of the catch consisted of fish preferring littoral zone habitats. The shallow depth and lack of woody debris in Skuna provided a selective advantage for smaller species of fish that could use shoreline habitats as protection from the current. Based on results from the Skuna River, channel straightening that leads to channel incision, bank failure and over widening provide habitats too shallow to support a community of fishes typical of northern Mississippi riverine system. This information may be useful in making comparison of damaged riverine ecosystems and assist managers in determining impairment and success in the TMDL （Total Maximum Daily Load） process.展开更多
Ischemia–reperfusion injury is a common pathophysiological mechanism in retinal degeneration.PANoptosis is a newly defined integral form of regulated cell death that combines the key features of pyroptosis,apoptosis,...Ischemia–reperfusion injury is a common pathophysiological mechanism in retinal degeneration.PANoptosis is a newly defined integral form of regulated cell death that combines the key features of pyroptosis,apoptosis,and necroptosis.Oligomerization of mitochondrial voltage-dependent anion channel 1 is an important pathological event in regulating cell death in retinal ischemia–reperfusion injury.However,its role in PANoptosis remains largely unknown.In this study,we demonstrated that voltage-dependent anion channel 1 oligomerization-mediated mitochondrial dysfunction was associated with PANoptosis in retinal ischemia–reperfusion injury.Inhibition of voltage-dependent anion channel 1 oligomerization suppressed mitochondrial dysfunction and PANoptosis in retinal cells subjected to ischemia–reperfusion injury.Mechanistically,mitochondria-derived reactive oxygen species played a central role in the voltagedependent anion channel 1-mediated regulation of PANoptosis by promoting PANoptosome assembly.Moreover,inhibiting voltage-dependent anion channel 1 oligomerization protected against PANoptosis in the retinas of rats subjected to ischemia–reperfusion injury.Overall,our findings reveal the critical role of voltage-dependent anion channel 1 oligomerization in regulating PANoptosis in retinal ischemia–reperfusion injury,highlighting voltage-dependent anion channel 1 as a promising therapeutic target.展开更多
Numerous pathological states of the nervous system involve alterations in neuronal excitability and synaptic dysfunction,which depend on the function of ion channels.Due to their critical involvement in health and dis...Numerous pathological states of the nervous system involve alterations in neuronal excitability and synaptic dysfunction,which depend on the function of ion channels.Due to their critical involvement in health and disease,the search for new compounds that modulate these proteins is still relevant.Traditional medicine has long been a rich source of neuroactive compounds.For example,the indigenous Mapuche people have used the leaves and bark of the Drimys winteri tree for centuries to treat various diseases.Consequently,several studies have investigated the biological effects of compounds in Drimys winteri,highlighting sesquiterpenes such asα-humulene,drimenin,polygodial,andα-,β-,γ-eudesmol.However,there is currently no literature review focusing on the ability of these sesquiterpenes to modulate ion channels.This review summarizes the current knowledge about neuroactive compounds found in Drimys winteri,with special emphasis on their direct actions on neuronal ion channels.Several Drimys winteri sesquiterpenes modulate a diverse array of neuronal ion channels,including transient receptor potential channels,gamma-aminobutyric acid A receptors,nicotinic acetylcholine receptors,and voltage-dependent Ca^(2+)and Na^(+)channels.Interestingly,the modulation of these molecular targets by Drimys winteri sesquiterpenes correlates with their therapeutic actions.The promiscuous pharmacological profile of Drimys winteri sesquiterpenes suggests they modulate multiple protein targets in vivo,making them potentially useful for treating complex,multifactorial diseases.Further studies at the molecular level may aid in developing multitargeted drugs with enhanced therapeutic effects.展开更多
本文分析了单北斗时钟同步源背景下的授时配置方案,制定了时钟同步对接和传递方案,结合现网提出了光传送网络(Optical Transport Network,OTN)1588v2改造方案,包括技术和硬件改造方案,并通过实施案例验证了方案的有效性,同时提出了北斗...本文分析了单北斗时钟同步源背景下的授时配置方案,制定了时钟同步对接和传递方案,结合现网提出了光传送网络(Optical Transport Network,OTN)1588v2改造方案,包括技术和硬件改造方案,并通过实施案例验证了方案的有效性,同时提出了北斗智能多路分配系统优化思路。展开更多
The utilization and storage of CO_(2) emissions from oil production and consumption in the upstream oil industry will contribute to sustainable development.CO_(2) flooding is the key technology for the upstream oil in...The utilization and storage of CO_(2) emissions from oil production and consumption in the upstream oil industry will contribute to sustainable development.CO_(2) flooding is the key technology for the upstream oil industry to transition to sustainable development.However,there is a significant challenge in achieving high recovery and storage efficiency in unconventional reservoirs,particularly in underde-veloped countries.Numerous studies have indicated that the limited sweep range caused by premature gas channeling of CO_(2) is a crucial bottleneck that hinders the enhancement of recovery,storage efficiency and safety.This review provides a comprehensive summary of the research and technical advancements regarding the front sweep characteristics of CO_(2) during migration.It particularly focuses on the char-acteristics,applicable stages,and research progress of different technologies used for regulating CO_(2) flooding sweep.Finally,based on the current application status and development trends,the review offers insights into the future research direction for these technologies.It is concluded that the front migration characteristics of CO_(2) play a crucial role in determining the macroscopic sweep range.The focus of future research lies in achieving cross-scale correlation and information coupling of CO_(2) migration processes.Currently,the influence weight of permeability,injection speed,pressure and other parameters on the characteristics of‘fingering-gas channeling’is still not well clear.There is an urgent need to establish prediction model and early warning mechanism that considers multi-parameters and cross-scale gas channeling degrees,in order to create effective strategies for prevention and control.There are currently three technologies available for sweep regulation:flow field intervention,mobility reduction,and gas channeling plugging.To expand the sweep effectively,it is important to systematically integrate these technologies based on their regulation characteristics and applicable stages.This can be achieved by constructing an intelligent synergistic hierarchical segmented regulation technology known as‘flow field intervention+mobility regulation+channel plugging chemically’.This work is expected to provide valuable insights for achieving conformance control of CO_(2)-EOR and safe storage of CO_(2).展开更多
Along with the proliferating research interest in semantic communication(Sem Com),joint source channel coding(JSCC)has dominated the attention due to the widely assumed existence in efficiently delivering information ...Along with the proliferating research interest in semantic communication(Sem Com),joint source channel coding(JSCC)has dominated the attention due to the widely assumed existence in efficiently delivering information semantics.Nevertheless,this paper challenges the conventional JSCC paradigm and advocates for adopting separate source channel coding(SSCC)to enjoy a more underlying degree of freedom for optimization.We demonstrate that SSCC,after leveraging the strengths of the Large Language Model(LLM)for source coding and Error Correction Code Transformer(ECCT)complemented for channel coding,offers superior performance over JSCC.Our proposed framework also effectively highlights the compatibility challenges between Sem Com approaches and digital communication systems,particularly concerning the resource costs associated with the transmission of high-precision floating point numbers.Through comprehensive evaluations,we establish that assisted by LLM-based compression and ECCT-enhanced error correction,SSCC remains a viable and effective solution for modern communication systems.In other words,separate source channel coding is still what we need.展开更多
Complementary inverter is the basic unit for logic circuits,but the inverters based on full oxide thin-film transistors(TFTs)are still very limited.The next challenge is to realize complementary inverters using homoge...Complementary inverter is the basic unit for logic circuits,but the inverters based on full oxide thin-film transistors(TFTs)are still very limited.The next challenge is to realize complementary inverters using homogeneous oxide semiconduc-tors.Herein,we propose the design of complementary inverter based on full ZnO TFTs.Li-N dual-doped ZnO(ZnO:(Li,N))acts as the p-type channel and Al-doped ZnO(ZnO:Al)serves as the n-type channel for fabrication of TFTs,and then the complemen-tary inverter is produced with p-and n-type ZnO TFTs.The homogeneous ZnO-based complementary inverter has typical volt-age transfer characteristics with the voltage gain of 13.34 at the supply voltage of 40 V.This work may open the door for the development of oxide complementary inverters for logic circuits.展开更多
The rapid expansion of railways,especially High-Speed Railways(HSRs),has drawn considerable interest from both academic and industrial sectors.To meet the future vision of smart rail communications,the rail transport ...The rapid expansion of railways,especially High-Speed Railways(HSRs),has drawn considerable interest from both academic and industrial sectors.To meet the future vision of smart rail communications,the rail transport industry must innovate in key technologies to ensure high-quality transmissions for passengers and railway operations.These systems must function effectively under high mobility conditions while prioritizing safety,ecofriendliness,comfort,transparency,predictability,and reliability.On the other hand,the proposal of 6 G wireless technology introduces new possibilities for innovation in communication technologies,which may truly realize the current vision of HSR.Therefore,this article gives a review of the current advanced 6 G wireless communication technologies for HSR,including random access and switching,channel estimation and beamforming,integrated sensing and communication,and edge computing.The main application scenarios of these technologies are reviewed,as well as their current research status and challenges,followed by an outlook on future development directions.展开更多
CO_(2)flooding enhanced oil recovery(CO_(2)-EOR)represents a significant technology in the low permeability reservoir.With the fractures and heterogeneity in low permeability reservoirs,CO_(2)-EOR is susceptible to pe...CO_(2)flooding enhanced oil recovery(CO_(2)-EOR)represents a significant technology in the low permeability reservoir.With the fractures and heterogeneity in low permeability reservoirs,CO_(2)-EOR is susceptible to pessimistic gas channeling.Consequently,there is a need to develop conformance control materials that can be used in CO_(2)-EOR.Herein,to address the challenges of low strength and poor stability of polymer gel in high temperature and low permeability reservoirs,a new organic/metal ion composite crosslinking polymer gel(AR-Gel)is reported,which is formed by low hydrolysis and medium to high molecular weight polymer(CX-305),organic crosslinking agent(phenolic resin),and aluminium citrate(AI(Ⅲ)).The crosslinking of AI(Ⅲ)with carboxyl group and organic/metal ion double crosslinking can construct a more complex and stable polymer gel structure on the basis of traditional chemical crosslinking,to cope with the harsh conditions such as high temperature.The structure-activity relationship of AR-Gel was revealed by rheology behavior and micro-morphology.The applicability of AR-Gel in reservoir was investigated,as was its strength and stability in supercritical CO_(2).The anti-gas channeling and enhanced oil recovery of AR-Gel were investigated using low permeability fractured cores,and the field process parameters were provided.The gel can be used to meet supercritical CO_(2)reservoirs at 110℃and 20,000 mg/L salinity,with long-term stability over 60 days.The plugging rate of AR-Gel for fractured co re was 97%,with subsequent CO_(2)flooding re sulting in an enhanced oil recovery by 34.5%.ARGel can effectively control CO_(2)gas channeling and enhanced oil recovery.It offers a new material with high strength and temperature resistance,which is particularly beneficial in the CO_(2)flooding for the conformance control of oil field.展开更多
The central nervous system, information integration center of the body, is mainly composed of neurons and glial cells. The neuron is one of the most basic and important structural and functional units of the central n...The central nervous system, information integration center of the body, is mainly composed of neurons and glial cells. The neuron is one of the most basic and important structural and functional units of the central nervous system, with sensory stimulation and excitation conduction functions. Astrocytes and microglia belong to the glial cell family, which is the main source of cytokines and represents the main defense system of the central nervous system. Nerve cells undergo neurotransmission or gliotransmission, which regulates neuronal activity via the ion channels, receptors, or transporters expressed on nerve cell membranes. Ion channels, composed of large transmembrane proteins, play crucial roles in maintaining nerve cell homeostasis. These channels are also important for control of the membrane potential and in the secretion of neurotransmitters. A variety of cellular functions and life activities, including functional regulation of the central nervous system, the generation and conduction of nerve excitation, the occurrence of receptor potential, heart pulsation, smooth muscle peristalsis, skeletal muscle contraction, and hormone secretion, are closely related to ion channels associated with passive transmembrane transport. Two types of ion channels in the central nervous system, potassium channels and calcium channels, are closely related to various neurological disorders, including Alzheimer's disease, Parkinson's disease, and epilepsy. Accordingly, various drugs that can affect these ion channels have been explored deeply to provide new directions for the treatment of these neurological disorders. In this review, we focus on the functions of potassium and calcium ion channels in different nerve cells and their involvement in neurological disorders such as Parkinson's disease, Alzheimer's disease, depression, epilepsy, autism, and rare disorders. We also describe several clinical drugs that target potassium or calcium channels in nerve cells and could be used to treat these disorders. We concluded that there are few clinical drugs that can improve the pathology these diseases by acting on potassium or calcium ions. Although a few novel ion-channelspecific modulators have been discovered, meaningful therapies have largely not yet been realized. The lack of target-specific drugs, their requirement to cross the blood–brain barrier, and their exact underlying mechanisms all need further attention. This review aims to explain the urgent problems that need research progress and provide comprehensive information aiming to arouse the research community's interest in the development of ion channel-targeting drugs and the identification of new therapeutic targets for that can increase the cure rate of nervous system diseases and reduce the occurrence of adverse reactions in other systems.展开更多
Adaptor signature,a new primitive that alleviates the scalability issue of blockchain to some extent,has been widely adopted in the off-chain payment channel and atomic swap.As an extension of standard digital signatu...Adaptor signature,a new primitive that alleviates the scalability issue of blockchain to some extent,has been widely adopted in the off-chain payment channel and atomic swap.As an extension of standard digital signature,adaptor signature can bind the release of a complete digital signature with the exchange of a secret value.Existing constructions of adaptor signatures are mainly based on Schnorr or ECDSA signature algorithms,which suffer low signing efficiency and long signature length.In this paper,to address these issues,we propose a new construction of adaptor signature using randomized EdDSA,which has Schnorr-like structure with higher signing efficiency and shorter signature length.We prove the required security properties,including unforgeability,witness extractability and pre-signature adaptability,of the new adaptor signature scheme in the random oracle model.We conduct a comparative analysis with an ECDSA-based adaptor signature scheme to demonstrate the effectiveness and feasibility of our new proposal.展开更多
Vestibular Migraine (VM) is a common neurological disorder characterized by recurrent episodes of vertigo and migraine symptoms. The pathogenesis of VM is complex and involves multiple genetic and environmental factor...Vestibular Migraine (VM) is a common neurological disorder characterized by recurrent episodes of vertigo and migraine symptoms. The pathogenesis of VM is complex and involves multiple genetic and environmental factors. Recent studies have suggested that the pathogenesis of vestibular migraine may be associated with variations in the CACNA1A gene, which is an important gene target for controlling calcium ion channels. Such variations may further affect the functions of the vestibular nervous system, thereby causing a series of vestibular nervous system-related symptoms. This article will summarize the genetic association studies of vestibular migraine, vestibular function studies, and research on how to establish relevant animal models to illustrate the possible association between CACNA1A variations and the pathogenesis of VM, providing new ideas for clarifying the pathogenesis of VM.展开更多
In low-light environments,captured images often exhibit issues such as insufficient clarity and detail loss,which significantly degrade the accuracy of subsequent target recognition tasks.To tackle these challenges,th...In low-light environments,captured images often exhibit issues such as insufficient clarity and detail loss,which significantly degrade the accuracy of subsequent target recognition tasks.To tackle these challenges,this study presents a novel low-light image enhancement algorithm that leverages virtual hazy image generation through dehazing models based on statistical analysis.The proposed algorithm initiates the enhancement process by transforming the low-light image into a virtual hazy image,followed by image segmentation using a quadtree method.To improve the accuracy and robustness of atmospheric light estimation,the algorithm incorporates a genetic algorithm to optimize the quadtree-based estimation of atmospheric light regions.Additionally,this method employs an adaptive window adjustment mechanism to derive the dark channel prior image,which is subsequently refined using morphological operations and guided filtering.The final enhanced image is reconstructed through the hazy image degradation model.Extensive experimental evaluations across multiple datasets verify the superiority of the designed framework,achieving a peak signal-to-noise ratio(PSNR)of 17.09 and a structural similarity index(SSIM)of 0.74.These results indicate that the proposed algorithm not only effectively enhances image contrast and brightness but also outperforms traditional methods in terms of subjective and objective evaluation metrics.展开更多
Precipitation via thermal treatments is among the most effective approaches to strengthening and is widely applied in the Al industry. Thermal treatments combined with deformation are capable of finely regulating the ...Precipitation via thermal treatments is among the most effective approaches to strengthening and is widely applied in the Al industry. Thermal treatments combined with deformation are capable of finely regulating the process of precipitation and distribution of precipitates. Deformation-induced defects exert significant impacts on the precipitation and already present precipitates, which however is often overlooked. In this study, the interactions between deformation and precipitation/precipitates, and their impacts on mechanical properties were systematically investigated in the solution-treated (ST) Al-0.61Mg-1.17Si-0.5Cu (wt.%), processed by multi-pass equal channel angular pressing (ECAP) and thermal treatments. Novel deformation-mediated cyclic evolution of precipitates is discovered: ST→ (1,2 passes: deformation induced precipitation) Guinier Preston (GP) zones→ (An250/30) Q’ and L phases→ (3-pass: deformation induced fragmentation/resolution) spherical precipitates→ (4-pass: deformation induced further fragmentation/resolution) GP zones. On this basis, we extend the quasi-binary phase diagram of Al-Mg_(2)Si along deformation as the third dimension and construct an innovative defect phase diagram for the Al-Mg-Si-based system. To testify to the effect of deformation-mediated cyclic evolution of precipitation/precipitates on the optimum mechanical properties, peak-aging treatments were performed in samples of ST and 3-pass states. Based on the microscopic characterizations, a distinctive mechanism of peak-aging strengthening is proposed. Notably in the 3-pass ECAPed and peak-aged sample the dominant strengthening phases become the L precipitates that thrived from the segmented and spherical L phases, rather than β’’ precipitates in the solely peak-aged ST sample. Our work provides a feasible example for exploring the combined processing technique of multi-step deformation and thermal treatments, to optimize the mechanical properties.展开更多
Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Class...Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Classifier(GPT2-ICC),which effectively distinguishing ion channels from a test set containing approximately 239 times more non-ion-channel proteins.GPT2-ICC integrates representation learning with a large language model(LLM)-based classifier,enabling highly accurate identification of potential ion channels.Several potential ion channels were predicated from the unannotated human proteome,further demonstrating GPT2-ICC’s generalization ability.This study marks a significant advancement in artificial-intelligence-driven ion channel research,highlighting the adaptability and effectiveness of combining representation learning with LLMs to address the challenges of imbalanced protein sequence data.Moreover,it provides a valuable computational tool for uncovering previously uncharacterized ion channels.展开更多
This study numerically examines the heat and mass transfer characteristics of two ternary nanofluids via converging and diverg-ing channels.Furthermore,the study aims to assess two ternary nanofluids combinations to d...This study numerically examines the heat and mass transfer characteristics of two ternary nanofluids via converging and diverg-ing channels.Furthermore,the study aims to assess two ternary nanofluids combinations to determine which configuration can provide better heat and mass transfer and lower entropy production,while ensuring cost efficiency.This work bridges the gap be-tween academic research and industrial feasibility by incorporating cost analysis,entropy generation,and thermal efficiency.To compare the velocity,temperature,and concentration profiles,we examine two ternary nanofluids,i.e.,TiO_(2)+SiO_(2)+Al_(2)O_(3)/H_(2)O and TiO_(2)+SiO_(2)+Cu/H_(2)O,while considering the shape of nanoparticles.The velocity slip and Soret/Dufour effects are taken into consideration.Furthermore,regression analysis for Nusselt and Sherwood numbers of the model is carried out.The Runge-Kutta fourth-order method with shooting technique is employed to acquire the numerical solution of the governed system of ordinary differential equations.The flow pattern attributes of ternary nanofluids are meticulously examined and simulated with the fluc-tuation of flow-dominating parameters.Additionally,the influence of these parameters is demonstrated in the flow,temperature,and concentration fields.For variation in Eckert and Dufour numbers,TiO_(2)+SiO_(2)+Al_(2)O_(3)/H_(2)O has a higher temperature than TiO_(2)+SiO_(2)+Cu/H_(2)O.The results obtained indicate that the ternary nanofluid TiO_(2)+SiO_(2)+Al_(2)O_(3)/H_(2)O has a higher heat transfer rate,lesser entropy generation,greater mass transfer rate,and lower cost than that of TiO_(2)+SiO_(2)+Cu/H_(2)O ternary nanofluid.展开更多
Cardiotoxicity is a critical issue in drug development that poses serious health risks,including potentially fatal arrhythmias.The human ether-à-go-go related gene(hERG)potassium channel,as one of the primary tar...Cardiotoxicity is a critical issue in drug development that poses serious health risks,including potentially fatal arrhythmias.The human ether-à-go-go related gene(hERG)potassium channel,as one of the primary targets of cardiotoxicity,has garnered widespread attention.Traditional cardiotoxicity testing methods are expensive and time-consuming,making computational virtual screening a suitable alternative.In this study,we employed machine learning techniques utilizing molecular fingerprints and descriptors to predict the cardiotoxicity of compounds,with the aim of improving prediction accuracy and efficiency.We used four types of molecular fingerprints and descriptors combined with machine learning and deep learning algorithms,including Gaussian naive Bayes(NB),random forest(RF),support vector machine(SVM),K-nearest neighbors(KNN),eXtreme gradient boosting(XGBoost),and Transformer models,to build predictive models.Our models demonstrated advanced predictive performance.The best machine learning model,XGBoost Morgan,achieved an accuracy(ACC)value of 0.84,and the deep learning model,Transformer_Morgan,achieved the best ACC value of 0.85,showing a high ability to distinguish between toxic and non-toxic compounds.On an external independent validation set,it achieved the best area under the curve(AUC)value of 0.93,surpassing ADMETlab3.0,Cardpred,and CardioDPi.In addition,we explored the integration of molecular descriptors and fingerprints to enhance model performance and found that ensemble methods,such as voting and stacking,provided slight improvements in model stability.Furthermore,the SHapley Additive exPlanations(SHAP)explanations revealed the relationship between benzene rings,fluorine-containing groups,NH groups,oxygen in ether groups,and cardiotoxicity,highlighting the importance of these features.This study not only improved the predictive accuracy of cardiotoxicity models but also promoted a more reliable and scientifically interpretable method for drug safety assessment.Using computational methods,this study facilitates a more efficient drug development process,reduces costs,and improves the safety of new drug candidates,ultimately benefiting medical and public health.展开更多
Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and text...Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 61601477, and 61601480
文摘Channelization typically realized by digital filter banks is an important topic in high frequency(HF) communication and software defined radios(SDR) areas. Channelization has a rigorous requirement for the characteristic of frequency response, e.g., steep transitional band and sharp decay. To address this issue, we investigated the feasibility and implementation of applying fast filter bank(FFB) in channelization in this paper. We analyzed the butterfly structure of FFB similar with fast Fourier transform(FFT), in which prototype sub-filters are cascaded to achieve a low complexity. Hence, it is suitable for designing filter bank with steep transitional band and sharp decay in stop-band. Moreover, we designed a pipelined structure of FFB to achieve a balance between area and performance. Design example shows that FFB has lower computational complexity compared with the other filter banks.
文摘A multistandard software-defined radio base station must perform non-uniform channelization of multiplexed frequency bands. Non-uniform channelization accounts for a significant portion of the digital signal processing workload in the base station receiver and can be difficult to realize in a physical implementation. In non-uniform channelization methods based on generalized DFT filter banks, large prototype filter orders are a significant issue for implementation. In this paper, a multistage filter design is applied to two different non-uniform generalized DFT-based channelizers in order to reduce their filter orders. To evaluate the approach, a TETRA and TEDS base station is used. Experimental results show that the new multistage design reduces both the number of coefficients and operations and leads to a more feasible design and practical physical implementation.
文摘Channel straightening in a naturally meandering river is a common historical trigger of channel incision which typically results in stream bank destabilization. Several of the larger river systems in the upland portion of the Yazoo River Basin have subjected channelization resulting in profound changes in the physical and geomorphological characteristics of these systems. Fish were sampled using electroshocking gear and hoop nets to evaluate the impact of stream bank destabilization and loss of habitat heterogeneity resulting from channelization on fish communities. While distinct differences in the fish communities were evident, only the Skuna appeared to have characteristics of a damaged system. More than 95% of the biomass was comprised of species reaching an adult length of less than 300 mm. The lotic omnivorous fishes that dominated the biomass from Skuna are often associated with smaller streams rather than rivers. Furthermore, 72% of the catch consisted of fish preferring littoral zone habitats. The shallow depth and lack of woody debris in Skuna provided a selective advantage for smaller species of fish that could use shoreline habitats as protection from the current. Based on results from the Skuna River, channel straightening that leads to channel incision, bank failure and over widening provide habitats too shallow to support a community of fishes typical of northern Mississippi riverine system. This information may be useful in making comparison of damaged riverine ecosystems and assist managers in determining impairment and success in the TMDL （Total Maximum Daily Load） process.
基金supported by the National Natural Science Foundation of China,Nos.82172196(to KX),82372507(to KX)the Natural Science Foundation of Hunan Province,China,No.2023JJ40804(to QZ)the Key Laboratory of Emergency and Trauma(Hainan Medical University)of the Ministry of Education,China,No.KLET-202210(to QZ)。
文摘Ischemia–reperfusion injury is a common pathophysiological mechanism in retinal degeneration.PANoptosis is a newly defined integral form of regulated cell death that combines the key features of pyroptosis,apoptosis,and necroptosis.Oligomerization of mitochondrial voltage-dependent anion channel 1 is an important pathological event in regulating cell death in retinal ischemia–reperfusion injury.However,its role in PANoptosis remains largely unknown.In this study,we demonstrated that voltage-dependent anion channel 1 oligomerization-mediated mitochondrial dysfunction was associated with PANoptosis in retinal ischemia–reperfusion injury.Inhibition of voltage-dependent anion channel 1 oligomerization suppressed mitochondrial dysfunction and PANoptosis in retinal cells subjected to ischemia–reperfusion injury.Mechanistically,mitochondria-derived reactive oxygen species played a central role in the voltagedependent anion channel 1-mediated regulation of PANoptosis by promoting PANoptosome assembly.Moreover,inhibiting voltage-dependent anion channel 1 oligomerization protected against PANoptosis in the retinas of rats subjected to ischemia–reperfusion injury.Overall,our findings reveal the critical role of voltage-dependent anion channel 1 oligomerization in regulating PANoptosis in retinal ischemia–reperfusion injury,highlighting voltage-dependent anion channel 1 as a promising therapeutic target.
基金supported by ANID-FONDECYT 1200908(to JF),ANID-FONDECYT 1211082 and 1250856(to GEY)by the Millennium Nucleus for the Study of Pain NCN19_038(Mi Nu SPain)(to GEY)funded by the ANID scholarship 21201176。
文摘Numerous pathological states of the nervous system involve alterations in neuronal excitability and synaptic dysfunction,which depend on the function of ion channels.Due to their critical involvement in health and disease,the search for new compounds that modulate these proteins is still relevant.Traditional medicine has long been a rich source of neuroactive compounds.For example,the indigenous Mapuche people have used the leaves and bark of the Drimys winteri tree for centuries to treat various diseases.Consequently,several studies have investigated the biological effects of compounds in Drimys winteri,highlighting sesquiterpenes such asα-humulene,drimenin,polygodial,andα-,β-,γ-eudesmol.However,there is currently no literature review focusing on the ability of these sesquiterpenes to modulate ion channels.This review summarizes the current knowledge about neuroactive compounds found in Drimys winteri,with special emphasis on their direct actions on neuronal ion channels.Several Drimys winteri sesquiterpenes modulate a diverse array of neuronal ion channels,including transient receptor potential channels,gamma-aminobutyric acid A receptors,nicotinic acetylcholine receptors,and voltage-dependent Ca^(2+)and Na^(+)channels.Interestingly,the modulation of these molecular targets by Drimys winteri sesquiterpenes correlates with their therapeutic actions.The promiscuous pharmacological profile of Drimys winteri sesquiterpenes suggests they modulate multiple protein targets in vivo,making them potentially useful for treating complex,multifactorial diseases.Further studies at the molecular level may aid in developing multitargeted drugs with enhanced therapeutic effects.
基金National Key Research and Development Program of China(No.2023YFB4104204)National Natural Science Foundation of China(No.U23B2090).
文摘The utilization and storage of CO_(2) emissions from oil production and consumption in the upstream oil industry will contribute to sustainable development.CO_(2) flooding is the key technology for the upstream oil industry to transition to sustainable development.However,there is a significant challenge in achieving high recovery and storage efficiency in unconventional reservoirs,particularly in underde-veloped countries.Numerous studies have indicated that the limited sweep range caused by premature gas channeling of CO_(2) is a crucial bottleneck that hinders the enhancement of recovery,storage efficiency and safety.This review provides a comprehensive summary of the research and technical advancements regarding the front sweep characteristics of CO_(2) during migration.It particularly focuses on the char-acteristics,applicable stages,and research progress of different technologies used for regulating CO_(2) flooding sweep.Finally,based on the current application status and development trends,the review offers insights into the future research direction for these technologies.It is concluded that the front migration characteristics of CO_(2) play a crucial role in determining the macroscopic sweep range.The focus of future research lies in achieving cross-scale correlation and information coupling of CO_(2) migration processes.Currently,the influence weight of permeability,injection speed,pressure and other parameters on the characteristics of‘fingering-gas channeling’is still not well clear.There is an urgent need to establish prediction model and early warning mechanism that considers multi-parameters and cross-scale gas channeling degrees,in order to create effective strategies for prevention and control.There are currently three technologies available for sweep regulation:flow field intervention,mobility reduction,and gas channeling plugging.To expand the sweep effectively,it is important to systematically integrate these technologies based on their regulation characteristics and applicable stages.This can be achieved by constructing an intelligent synergistic hierarchical segmented regulation technology known as‘flow field intervention+mobility regulation+channel plugging chemically’.This work is expected to provide valuable insights for achieving conformance control of CO_(2)-EOR and safe storage of CO_(2).
基金supported in part by the National Key Research and Development Program of China under Grant No.2024YFE0200600the Zhejiang Provincial Natural Science Foundation of China under Grant No.LR23F010005the Huawei Cooperation Project under Grant No.TC20240829036。
文摘Along with the proliferating research interest in semantic communication(Sem Com),joint source channel coding(JSCC)has dominated the attention due to the widely assumed existence in efficiently delivering information semantics.Nevertheless,this paper challenges the conventional JSCC paradigm and advocates for adopting separate source channel coding(SSCC)to enjoy a more underlying degree of freedom for optimization.We demonstrate that SSCC,after leveraging the strengths of the Large Language Model(LLM)for source coding and Error Correction Code Transformer(ECCT)complemented for channel coding,offers superior performance over JSCC.Our proposed framework also effectively highlights the compatibility challenges between Sem Com approaches and digital communication systems,particularly concerning the resource costs associated with the transmission of high-precision floating point numbers.Through comprehensive evaluations,we establish that assisted by LLM-based compression and ECCT-enhanced error correction,SSCC remains a viable and effective solution for modern communication systems.In other words,separate source channel coding is still what we need.
基金supported by Zhejiang Provincial Natural Science Foundation of China(No.LZ24E020001).
文摘Complementary inverter is the basic unit for logic circuits,but the inverters based on full oxide thin-film transistors(TFTs)are still very limited.The next challenge is to realize complementary inverters using homogeneous oxide semiconduc-tors.Herein,we propose the design of complementary inverter based on full ZnO TFTs.Li-N dual-doped ZnO(ZnO:(Li,N))acts as the p-type channel and Al-doped ZnO(ZnO:Al)serves as the n-type channel for fabrication of TFTs,and then the complemen-tary inverter is produced with p-and n-type ZnO TFTs.The homogeneous ZnO-based complementary inverter has typical volt-age transfer characteristics with the voltage gain of 13.34 at the supply voltage of 40 V.This work may open the door for the development of oxide complementary inverters for logic circuits.
基金National Natural Science Foundation of China(U2468201,62122012,62221001).
文摘The rapid expansion of railways,especially High-Speed Railways(HSRs),has drawn considerable interest from both academic and industrial sectors.To meet the future vision of smart rail communications,the rail transport industry must innovate in key technologies to ensure high-quality transmissions for passengers and railway operations.These systems must function effectively under high mobility conditions while prioritizing safety,ecofriendliness,comfort,transparency,predictability,and reliability.On the other hand,the proposal of 6 G wireless technology introduces new possibilities for innovation in communication technologies,which may truly realize the current vision of HSR.Therefore,this article gives a review of the current advanced 6 G wireless communication technologies for HSR,including random access and switching,channel estimation and beamforming,integrated sensing and communication,and edge computing.The main application scenarios of these technologies are reviewed,as well as their current research status and challenges,followed by an outlook on future development directions.
基金project was supported by the Fund of State Key Laboratory of Deep Oil and Gas,China University of Petroleum(East China)(No.SKLDOG2024-ZYRC-06)Key Program of National Natural Science Foundation of China(52130401)+1 种基金National Natural Science Foundation of China(52104055,52374058)Shandong Provincial Natural Science Foundation,China(ZR2021ME171,ZR2024YQ043)。
文摘CO_(2)flooding enhanced oil recovery(CO_(2)-EOR)represents a significant technology in the low permeability reservoir.With the fractures and heterogeneity in low permeability reservoirs,CO_(2)-EOR is susceptible to pessimistic gas channeling.Consequently,there is a need to develop conformance control materials that can be used in CO_(2)-EOR.Herein,to address the challenges of low strength and poor stability of polymer gel in high temperature and low permeability reservoirs,a new organic/metal ion composite crosslinking polymer gel(AR-Gel)is reported,which is formed by low hydrolysis and medium to high molecular weight polymer(CX-305),organic crosslinking agent(phenolic resin),and aluminium citrate(AI(Ⅲ)).The crosslinking of AI(Ⅲ)with carboxyl group and organic/metal ion double crosslinking can construct a more complex and stable polymer gel structure on the basis of traditional chemical crosslinking,to cope with the harsh conditions such as high temperature.The structure-activity relationship of AR-Gel was revealed by rheology behavior and micro-morphology.The applicability of AR-Gel in reservoir was investigated,as was its strength and stability in supercritical CO_(2).The anti-gas channeling and enhanced oil recovery of AR-Gel were investigated using low permeability fractured cores,and the field process parameters were provided.The gel can be used to meet supercritical CO_(2)reservoirs at 110℃and 20,000 mg/L salinity,with long-term stability over 60 days.The plugging rate of AR-Gel for fractured co re was 97%,with subsequent CO_(2)flooding re sulting in an enhanced oil recovery by 34.5%.ARGel can effectively control CO_(2)gas channeling and enhanced oil recovery.It offers a new material with high strength and temperature resistance,which is particularly beneficial in the CO_(2)flooding for the conformance control of oil field.
基金supported by the National Natural Science Foundation of China,Nos.81901098(to TC),82201668(to HL)Fujian Provincial Health Technology Project,No.2021QNA072(to HL)。
文摘The central nervous system, information integration center of the body, is mainly composed of neurons and glial cells. The neuron is one of the most basic and important structural and functional units of the central nervous system, with sensory stimulation and excitation conduction functions. Astrocytes and microglia belong to the glial cell family, which is the main source of cytokines and represents the main defense system of the central nervous system. Nerve cells undergo neurotransmission or gliotransmission, which regulates neuronal activity via the ion channels, receptors, or transporters expressed on nerve cell membranes. Ion channels, composed of large transmembrane proteins, play crucial roles in maintaining nerve cell homeostasis. These channels are also important for control of the membrane potential and in the secretion of neurotransmitters. A variety of cellular functions and life activities, including functional regulation of the central nervous system, the generation and conduction of nerve excitation, the occurrence of receptor potential, heart pulsation, smooth muscle peristalsis, skeletal muscle contraction, and hormone secretion, are closely related to ion channels associated with passive transmembrane transport. Two types of ion channels in the central nervous system, potassium channels and calcium channels, are closely related to various neurological disorders, including Alzheimer's disease, Parkinson's disease, and epilepsy. Accordingly, various drugs that can affect these ion channels have been explored deeply to provide new directions for the treatment of these neurological disorders. In this review, we focus on the functions of potassium and calcium ion channels in different nerve cells and their involvement in neurological disorders such as Parkinson's disease, Alzheimer's disease, depression, epilepsy, autism, and rare disorders. We also describe several clinical drugs that target potassium or calcium channels in nerve cells and could be used to treat these disorders. We concluded that there are few clinical drugs that can improve the pathology these diseases by acting on potassium or calcium ions. Although a few novel ion-channelspecific modulators have been discovered, meaningful therapies have largely not yet been realized. The lack of target-specific drugs, their requirement to cross the blood–brain barrier, and their exact underlying mechanisms all need further attention. This review aims to explain the urgent problems that need research progress and provide comprehensive information aiming to arouse the research community's interest in the development of ion channel-targeting drugs and the identification of new therapeutic targets for that can increase the cure rate of nervous system diseases and reduce the occurrence of adverse reactions in other systems.
基金supported by the National Key R&D Program of China(2022YFB2701500)the National Natural Science Foundation of China(62272385,62311540156)+2 种基金Shaanxi Distinguished Youth Project(2022JC-47)the Key Research and Development Program of Shaanxi(2021ZDLGY06-04)Major Program of Shandong Provincial Natural Science Foundation for the Fundamental Research(ZR2022ZD03).
文摘Adaptor signature,a new primitive that alleviates the scalability issue of blockchain to some extent,has been widely adopted in the off-chain payment channel and atomic swap.As an extension of standard digital signature,adaptor signature can bind the release of a complete digital signature with the exchange of a secret value.Existing constructions of adaptor signatures are mainly based on Schnorr or ECDSA signature algorithms,which suffer low signing efficiency and long signature length.In this paper,to address these issues,we propose a new construction of adaptor signature using randomized EdDSA,which has Schnorr-like structure with higher signing efficiency and shorter signature length.We prove the required security properties,including unforgeability,witness extractability and pre-signature adaptability,of the new adaptor signature scheme in the random oracle model.We conduct a comparative analysis with an ECDSA-based adaptor signature scheme to demonstrate the effectiveness and feasibility of our new proposal.
文摘Vestibular Migraine (VM) is a common neurological disorder characterized by recurrent episodes of vertigo and migraine symptoms. The pathogenesis of VM is complex and involves multiple genetic and environmental factors. Recent studies have suggested that the pathogenesis of vestibular migraine may be associated with variations in the CACNA1A gene, which is an important gene target for controlling calcium ion channels. Such variations may further affect the functions of the vestibular nervous system, thereby causing a series of vestibular nervous system-related symptoms. This article will summarize the genetic association studies of vestibular migraine, vestibular function studies, and research on how to establish relevant animal models to illustrate the possible association between CACNA1A variations and the pathogenesis of VM, providing new ideas for clarifying the pathogenesis of VM.
基金supported by the Natural Science Foundation of Shandong Province(nos.ZR2023MF047,ZR2024MA055 and ZR2023QF139)the Enterprise Commissioned Project(nos.2024HX104 and 2024HX140)+1 种基金the China University Industry-University-Research Innovation Foundation(nos.2021ZYA11003 and 2021ITA05032)the Science and Technology Plan for Youth Innovation of Shandong's Universities(no.2019KJN012).
文摘In low-light environments,captured images often exhibit issues such as insufficient clarity and detail loss,which significantly degrade the accuracy of subsequent target recognition tasks.To tackle these challenges,this study presents a novel low-light image enhancement algorithm that leverages virtual hazy image generation through dehazing models based on statistical analysis.The proposed algorithm initiates the enhancement process by transforming the low-light image into a virtual hazy image,followed by image segmentation using a quadtree method.To improve the accuracy and robustness of atmospheric light estimation,the algorithm incorporates a genetic algorithm to optimize the quadtree-based estimation of atmospheric light regions.Additionally,this method employs an adaptive window adjustment mechanism to derive the dark channel prior image,which is subsequently refined using morphological operations and guided filtering.The final enhanced image is reconstructed through the hazy image degradation model.Extensive experimental evaluations across multiple datasets verify the superiority of the designed framework,achieving a peak signal-to-noise ratio(PSNR)of 17.09 and a structural similarity index(SSIM)of 0.74.These results indicate that the proposed algorithm not only effectively enhances image contrast and brightness but also outperforms traditional methods in terms of subjective and objective evaluation metrics.
基金supported by the National Natural Science Foundation of China(Grant Nos.U22A20187,52171007,52371111,and 52371177).
文摘Precipitation via thermal treatments is among the most effective approaches to strengthening and is widely applied in the Al industry. Thermal treatments combined with deformation are capable of finely regulating the process of precipitation and distribution of precipitates. Deformation-induced defects exert significant impacts on the precipitation and already present precipitates, which however is often overlooked. In this study, the interactions between deformation and precipitation/precipitates, and their impacts on mechanical properties were systematically investigated in the solution-treated (ST) Al-0.61Mg-1.17Si-0.5Cu (wt.%), processed by multi-pass equal channel angular pressing (ECAP) and thermal treatments. Novel deformation-mediated cyclic evolution of precipitates is discovered: ST→ (1,2 passes: deformation induced precipitation) Guinier Preston (GP) zones→ (An250/30) Q’ and L phases→ (3-pass: deformation induced fragmentation/resolution) spherical precipitates→ (4-pass: deformation induced further fragmentation/resolution) GP zones. On this basis, we extend the quasi-binary phase diagram of Al-Mg_(2)Si along deformation as the third dimension and construct an innovative defect phase diagram for the Al-Mg-Si-based system. To testify to the effect of deformation-mediated cyclic evolution of precipitation/precipitates on the optimum mechanical properties, peak-aging treatments were performed in samples of ST and 3-pass states. Based on the microscopic characterizations, a distinctive mechanism of peak-aging strengthening is proposed. Notably in the 3-pass ECAPed and peak-aged sample the dominant strengthening phases become the L precipitates that thrived from the segmented and spherical L phases, rather than β’’ precipitates in the solely peak-aged ST sample. Our work provides a feasible example for exploring the combined processing technique of multi-step deformation and thermal treatments, to optimize the mechanical properties.
基金funded by grants from the National Key Research and Development Program of China(Grant Nos.:2022YFE0205600 and 2022YFC3400504)the National Natural Science Foundation of China(Grant Nos.:82373792 and 82273857)the Fundamental Research Funds for the Central Universities,China,and the East China Normal University Medicine and Health Joint Fund,China(Grant No.:2022JKXYD07001).
文摘Current experimental and computational methods have limitations in accurately and efficiently classifying ion channels within vast protein spaces.Here we have developed a deep learning algorithm,GPT2 Ion Channel Classifier(GPT2-ICC),which effectively distinguishing ion channels from a test set containing approximately 239 times more non-ion-channel proteins.GPT2-ICC integrates representation learning with a large language model(LLM)-based classifier,enabling highly accurate identification of potential ion channels.Several potential ion channels were predicated from the unannotated human proteome,further demonstrating GPT2-ICC’s generalization ability.This study marks a significant advancement in artificial-intelligence-driven ion channel research,highlighting the adaptability and effectiveness of combining representation learning with LLMs to address the challenges of imbalanced protein sequence data.Moreover,it provides a valuable computational tool for uncovering previously uncharacterized ion channels.
基金supported by DST-FIST(Government of India)(Grant No.SR/FIST/MS-1/2017/13)and Seed Money Project(Grant No.DoRDC/733).
文摘This study numerically examines the heat and mass transfer characteristics of two ternary nanofluids via converging and diverg-ing channels.Furthermore,the study aims to assess two ternary nanofluids combinations to determine which configuration can provide better heat and mass transfer and lower entropy production,while ensuring cost efficiency.This work bridges the gap be-tween academic research and industrial feasibility by incorporating cost analysis,entropy generation,and thermal efficiency.To compare the velocity,temperature,and concentration profiles,we examine two ternary nanofluids,i.e.,TiO_(2)+SiO_(2)+Al_(2)O_(3)/H_(2)O and TiO_(2)+SiO_(2)+Cu/H_(2)O,while considering the shape of nanoparticles.The velocity slip and Soret/Dufour effects are taken into consideration.Furthermore,regression analysis for Nusselt and Sherwood numbers of the model is carried out.The Runge-Kutta fourth-order method with shooting technique is employed to acquire the numerical solution of the governed system of ordinary differential equations.The flow pattern attributes of ternary nanofluids are meticulously examined and simulated with the fluc-tuation of flow-dominating parameters.Additionally,the influence of these parameters is demonstrated in the flow,temperature,and concentration fields.For variation in Eckert and Dufour numbers,TiO_(2)+SiO_(2)+Al_(2)O_(3)/H_(2)O has a higher temperature than TiO_(2)+SiO_(2)+Cu/H_(2)O.The results obtained indicate that the ternary nanofluid TiO_(2)+SiO_(2)+Al_(2)O_(3)/H_(2)O has a higher heat transfer rate,lesser entropy generation,greater mass transfer rate,and lower cost than that of TiO_(2)+SiO_(2)+Cu/H_(2)O ternary nanofluid.
基金supported by National Key Research and Development Project,China(Grant No.:2021YFA1500403).
文摘Cardiotoxicity is a critical issue in drug development that poses serious health risks,including potentially fatal arrhythmias.The human ether-à-go-go related gene(hERG)potassium channel,as one of the primary targets of cardiotoxicity,has garnered widespread attention.Traditional cardiotoxicity testing methods are expensive and time-consuming,making computational virtual screening a suitable alternative.In this study,we employed machine learning techniques utilizing molecular fingerprints and descriptors to predict the cardiotoxicity of compounds,with the aim of improving prediction accuracy and efficiency.We used four types of molecular fingerprints and descriptors combined with machine learning and deep learning algorithms,including Gaussian naive Bayes(NB),random forest(RF),support vector machine(SVM),K-nearest neighbors(KNN),eXtreme gradient boosting(XGBoost),and Transformer models,to build predictive models.Our models demonstrated advanced predictive performance.The best machine learning model,XGBoost Morgan,achieved an accuracy(ACC)value of 0.84,and the deep learning model,Transformer_Morgan,achieved the best ACC value of 0.85,showing a high ability to distinguish between toxic and non-toxic compounds.On an external independent validation set,it achieved the best area under the curve(AUC)value of 0.93,surpassing ADMETlab3.0,Cardpred,and CardioDPi.In addition,we explored the integration of molecular descriptors and fingerprints to enhance model performance and found that ensemble methods,such as voting and stacking,provided slight improvements in model stability.Furthermore,the SHapley Additive exPlanations(SHAP)explanations revealed the relationship between benzene rings,fluorine-containing groups,NH groups,oxygen in ether groups,and cardiotoxicity,highlighting the importance of these features.This study not only improved the predictive accuracy of cardiotoxicity models but also promoted a more reliable and scientifically interpretable method for drug safety assessment.Using computational methods,this study facilitates a more efficient drug development process,reduces costs,and improves the safety of new drug candidates,ultimately benefiting medical and public health.
基金Shenzhen Institute of Artificial Intelligence and Robotics for Society,Grant/Award Number:AC01202201003-02GuangDong Basic and Applied Basic Research Foundation,Grant/Award Number:2024A1515010252Longgang District Shenzhen's“Ten Action Plan”for Supporting Innovation Projects,Grant/Award Number:LGKCSDPT2024002。
文摘Audio-visual scene classification(AVSC)poses a formidable challenge owing to the intricate spatial-temporal relationships exhibited by audio-visual signals,coupled with the complex spatial patterns of objects and textures found in visual images.The focus of recent studies has predominantly revolved around extracting features from diverse neural network structures,inadvertently neglecting the acquisition of semantically meaningful regions and crucial components within audio-visual data.The authors present a feature pyramid attention network(FPANet)for audio-visual scene understanding,which extracts semantically significant characteristics from audio-visual data.The authors’approach builds multi-scale hierarchical features of sound spectrograms and visual images using a feature pyramid representation and localises the semantically relevant regions with a feature pyramid attention module(FPAM).A dimension alignment(DA)strategy is employed to align feature maps from multiple layers,a pyramid spatial attention(PSA)to spatially locate essential regions,and a pyramid channel attention(PCA)to pinpoint significant temporal frames.Experiments on visual scene classification(VSC),audio scene classification(ASC),and AVSC tasks demonstrate that FPANet achieves performance on par with state-of-the-art(SOTA)approaches,with a 95.9 F1-score on the ADVANCE dataset and a relative improvement of 28.8%.Visualisation results show that FPANet can prioritise semantically meaningful areas in audio-visual signals.
