Construction of gene regulatory networks(GRNs)is essential for elucidating the regulatory mechanisms underlying metabolic pathways,biological processes,and complex traits.In this study,we developed and evaluated machi...Construction of gene regulatory networks(GRNs)is essential for elucidating the regulatory mechanisms underlying metabolic pathways,biological processes,and complex traits.In this study,we developed and evaluated machine learning,deep learning,and hybrid approaches for constructing GRNs by integrating prior knowledge and large-scale transcriptomic data from Arabidopsis thaliana,poplar,and maize.Among these,hybrid models that combined convolutional neural networks and machine learning consistently outperformed traditional machine learning and statistical methods,achieving over 95%accuracy on the holdout test datasets.These models not only identified a greater number of known transcription factors regulating the lignin biosynthesis pathway but also demonstrated higher precision in ranking key master regulators such as MYB46 and MYB83,as well as many upstream regulators,including members of the VND,NST,and SND families,at the top of candidate lists.To address the challenge of limited training data in non-model species,we implemented transfer learning,enabling cross-species GRN inference by applying models trained on well-characterized and data-rich species to another species with limited data.This strategy enhanced model performance and demonstrated the feasibility of knowledge transfer across species.Overall,our findings underscore the effectiveness of hybrid and transfer learning approaches in GRN prediction,offering a scalable framework for elucidating regulatory mechanisms in both model and non-model plant systems.展开更多
OBJECTIVE To investigate the role of chemokine CCL2 in leaning memory in rats and the mechanism of hippocampal neuronal apoptosis.METHODS Stereotaxic technique was used in this study to infuse CCL2(0.5,5 and50 ng) int...OBJECTIVE To investigate the role of chemokine CCL2 in leaning memory in rats and the mechanism of hippocampal neuronal apoptosis.METHODS Stereotaxic technique was used in this study to infuse CCL2(0.5,5 and50 ng) into bilateral hippocampus,sham group was received the equal volume of sterile saline.Morris water maze(MWM) was employed to assess the learning and memory ability of rats.Quantitative real-time PCR(RT-PCR) was used to detect the relative expression of caspase 3,Bax and Bcl-2 in hippocampus.RESULTS The results of the place navigation task showed that compared to the sham group(18.66±0.82) s,the latency in each model groups [24.18±1.08,25.99±1.96,(28.67±1.47) s] were significantly extended(P<0.05) while the swimming speed have no difference.In probe trial,the crossing times of each model groups [2.86±0.59,2.89 ±0.39,(2.50±0.37) s] were shorter than sham group(4.50±0.76) s(P<0.05).The result of RT-PCR showed that the relative expression of caspase 3 in CCL2 5 ng group(1.275±0.078)and CCL2 50 ng groups(1.283±0.043) in higher than sham group(1.000±0.000),as the same as Bax(1.107±0.028,1.096±0.015).Yet the relative expression of Bcl-2 has no significant difference among groups.CONCLUSION CCL2 may impaired learning and memory in rats in dose-dependent manner.The effect to induce hippocampal neuronal apoptosis may mediated by caspase 3 activation and Bax regulation.展开更多
The role of the thalamus in highlevel cognitive function such as learning and memory remains poorly understood.Here we systematically examined the role of paraventricular thalamus(PVT) in associative learning.We train...The role of the thalamus in highlevel cognitive function such as learning and memory remains poorly understood.Here we systematically examined the role of paraventricular thalamus(PVT) in associative learning.We trained mice with olfactory conditioning task in which different olfactory cues were associated with different outcomes includes reward,punishment or nothing.Both fiber photometry and single-unit recordings revealed that PVT were robustly activated by a variety of behaviorally significant events including reinforcing stimuli and their predicting cues,as well as omission of the expected reward.PVT responses are proportional to the stimulus intensity and modulated by changes in homeostatic state or behavioral context.Optogenetic inhibition of the PVT responses suppresses appetitive or aversive associative learning and reward extinction.Our findings demonstrate that the PVT gates associative learning by providing a dynamic representation of stimulus salience.展开更多
Electrochemical energy storage systems(ESSs)are crucial for grid stability and renewable energy integration,yet their increasing scale and complexity exacerbate safety risks such as thermal runaway and fire.To address...Electrochemical energy storage systems(ESSs)are crucial for grid stability and renewable energy integration,yet their increasing scale and complexity exacerbate safety risks such as thermal runaway and fire.To address these challenges,we propose an integrated fault diagnosis framework that combines natural language processing,deep learning,and safety engineering.A global ESS fault log was compiled and augmented with synthetic cases generated by large language models,ensuring both diversity and balanced representation.Fault information extracted from unstructured reports was analyzed via Bow-Tie and failure mode analyses to identify evolution pathways and key risk factors.For classification,we introduce a self-attention augmented convolutional neural network with a dynamic learning rate,which effectively captures subtle features and long-range dependencies.Our model achieves an accuracy of 94.93%and a macro F1-score of 0.9427,outperforming conventional benchmarks.Beyond classification,the framework links each identified fault to a complete process solution,including preventive measures,emergency responses,and consequence analysis,thereby reducing downtime and enhancing system resilience.In addition,keyword networks and hierarchical clustering reveal hidden associations among fault categories,providing actionable insights for targeted preventive strategies.This work establishes a robust and practical pathway for real-time monitoring,intelligent diagnosis,and proactive risk management in ESSs.展开更多
While healthcare providers have used computer-aided programs since the 1950s,artificial intelligence(AI)in health promotion has only recently flourished,driven by advances in large language models(LLMs),discriminative...While healthcare providers have used computer-aided programs since the 1950s,artificial intelligence(AI)in health promotion has only recently flourished,driven by advances in large language models(LLMs),discriminative machine learning,and multimodal foundation models.Fueled by growing data and computing power,AI now excels in drug development,diagnostic support,and AI-assisted surgery.展开更多
基金the McIntire Stennis,NIFA,USDA,the Michigan Sequencing Academic Partnership for Public Health Innovation and Response(MI-SAP-558 PHIRE)from the Michigan Department of Health and Human Services(MDHHS)the NSF Plant Genome Program[1703007]support from a Department of Energy funded project(DE-SC0023011).
摘要Construction of gene regulatory networks(GRNs)is essential for elucidating the regulatory mechanisms underlying metabolic pathways,biological processes,and complex traits.In this study,we developed and evaluated machine learning,deep learning,and hybrid approaches for constructing GRNs by integrating prior knowledge and large-scale transcriptomic data from Arabidopsis thaliana,poplar,and maize.Among these,hybrid models that combined convolutional neural networks and machine learning consistently outperformed traditional machine learning and statistical methods,achieving over 95%accuracy on the holdout test datasets.These models not only identified a greater number of known transcription factors regulating the lignin biosynthesis pathway but also demonstrated higher precision in ranking key master regulators such as MYB46 and MYB83,as well as many upstream regulators,including members of the VND,NST,and SND families,at the top of candidate lists.To address the challenge of limited training data in non-model species,we implemented transfer learning,enabling cross-species GRN inference by applying models trained on well-characterized and data-rich species to another species with limited data.This strategy enhanced model performance and demonstrated the feasibility of knowledge transfer across species.Overall,our findings underscore the effectiveness of hybrid and transfer learning approaches in GRN prediction,offering a scalable framework for elucidating regulatory mechanisms in both model and non-model plant systems.
基金National Natural Science Foundation of China(81360192,81660213).
摘要OBJECTIVE To investigate the role of chemokine CCL2 in leaning memory in rats and the mechanism of hippocampal neuronal apoptosis.METHODS Stereotaxic technique was used in this study to infuse CCL2(0.5,5 and50 ng) into bilateral hippocampus,sham group was received the equal volume of sterile saline.Morris water maze(MWM) was employed to assess the learning and memory ability of rats.Quantitative real-time PCR(RT-PCR) was used to detect the relative expression of caspase 3,Bax and Bcl-2 in hippocampus.RESULTS The results of the place navigation task showed that compared to the sham group(18.66±0.82) s,the latency in each model groups [24.18±1.08,25.99±1.96,(28.67±1.47) s] were significantly extended(P<0.05) while the swimming speed have no difference.In probe trial,the crossing times of each model groups [2.86±0.59,2.89 ±0.39,(2.50±0.37) s] were shorter than sham group(4.50±0.76) s(P<0.05).The result of RT-PCR showed that the relative expression of caspase 3 in CCL2 5 ng group(1.275±0.078)and CCL2 50 ng groups(1.283±0.043) in higher than sham group(1.000±0.000),as the same as Bax(1.107±0.028,1.096±0.015).Yet the relative expression of Bcl-2 has no significant difference among groups.CONCLUSION CCL2 may impaired learning and memory in rats in dose-dependent manner.The effect to induce hippocampal neuronal apoptosis may mediated by caspase 3 activation and Bax regulation.
摘要The role of the thalamus in highlevel cognitive function such as learning and memory remains poorly understood.Here we systematically examined the role of paraventricular thalamus(PVT) in associative learning.We trained mice with olfactory conditioning task in which different olfactory cues were associated with different outcomes includes reward,punishment or nothing.Both fiber photometry and single-unit recordings revealed that PVT were robustly activated by a variety of behaviorally significant events including reinforcing stimuli and their predicting cues,as well as omission of the expected reward.PVT responses are proportional to the stimulus intensity and modulated by changes in homeostatic state or behavioral context.Optogenetic inhibition of the PVT responses suppresses appetitive or aversive associative learning and reward extinction.Our findings demonstrate that the PVT gates associative learning by providing a dynamic representation of stimulus salience.
基金supported by the National Key R&D Program of China(No.2022YFE0207400)the National Natural Science Foundation of China(No.52306284)the Anhui Provincial Natural Science Foundation(No.2308085QE173).
摘要Electrochemical energy storage systems(ESSs)are crucial for grid stability and renewable energy integration,yet their increasing scale and complexity exacerbate safety risks such as thermal runaway and fire.To address these challenges,we propose an integrated fault diagnosis framework that combines natural language processing,deep learning,and safety engineering.A global ESS fault log was compiled and augmented with synthetic cases generated by large language models,ensuring both diversity and balanced representation.Fault information extracted from unstructured reports was analyzed via Bow-Tie and failure mode analyses to identify evolution pathways and key risk factors.For classification,we introduce a self-attention augmented convolutional neural network with a dynamic learning rate,which effectively captures subtle features and long-range dependencies.Our model achieves an accuracy of 94.93%and a macro F1-score of 0.9427,outperforming conventional benchmarks.Beyond classification,the framework links each identified fault to a complete process solution,including preventive measures,emergency responses,and consequence analysis,thereby reducing downtime and enhancing system resilience.In addition,keyword networks and hierarchical clustering reveal hidden associations among fault categories,providing actionable insights for targeted preventive strategies.This work establishes a robust and practical pathway for real-time monitoring,intelligent diagnosis,and proactive risk management in ESSs.
基金supported by the National Science and Technology Innovation 2030 of China-Major Projects(2022ZD0214100)the National Natural Science Foundation of China(82571696)+2 种基金Guangzhou Municipal School(College)-Enterprise Joint Funding Project(2024A03J0214)Guangzhou Science and Technology Plan Project(2025A03J3929)supported by Guangzhou Key Clinical Specialty(Clinical Medical Research Institute).
摘要While healthcare providers have used computer-aided programs since the 1950s,artificial intelligence(AI)in health promotion has only recently flourished,driven by advances in large language models(LLMs),discriminative machine learning,and multimodal foundation models.Fueled by growing data and computing power,AI now excels in drug development,diagnostic support,and AI-assisted surgery.