近几年来,深度学习无所不在,赋能于各个领域.尤其是人工智能与传统科学的结合(AI for science,AI4Science)引发广泛关注.在AI4Science领域,利用人工智能算法求解PDEs(AI4PDEs)已成为计算力学研究的焦点.AI4PDEs的核心是将数据与方程相融...近几年来,深度学习无所不在,赋能于各个领域.尤其是人工智能与传统科学的结合(AI for science,AI4Science)引发广泛关注.在AI4Science领域,利用人工智能算法求解PDEs(AI4PDEs)已成为计算力学研究的焦点.AI4PDEs的核心是将数据与方程相融合,并且几乎可以求解任何偏微分方程问题,由于其融合数据的优势,相较于传统算法,其计算效率通常提升数万倍.因此,本文全面综述了AI4PDEs的研究,总结了现有AI4PDEs算法、理论,并讨论了其在固体力学中的应用,包括正问题和反问题,展望了未来研究方向,尤其是必然会出现的计算力学大模型.现有AI4PDEs算法包括基于物理信息神经网络(physicsinformed neural network,PINNs)、深度能量法(deep energy methods,DEM)、算子学习(operator learning),以及基于物理神经网络算子(physics-informed neural operator,PINO).AI4PDEs在科学计算中有许多应用,本文聚焦于固体力学,正问题包括线弹性、弹塑性,超弹性、以及断裂力学;反问题包括材料参数,本构,缺陷的识别,以及拓朴优化.AI4PDEs代表了一种全新的科学模拟方法,通过利用大量数据在特定问题上提供近似解,然后根据具体的物理方程进行微调,避免了像传统算法那样从头开始计算,因此AI4PDEs是未来计算力学大模型的雏形,能够大大加速传统数值算法.我们相信,利用人工智能助力科学计算不仅仅是计算领域的未来重要方向,同时也是计算力学的未来,即是智能计算力学。展开更多
Idiopathic pulmonary fibrosis(IPF)is a progressive lung disease and its incidence rate is rapidly rising.However,effective therapies for the treatment of IPF are still lacking.Phosphodiesterase 4(PDE4)inhibitors were ...Idiopathic pulmonary fibrosis(IPF)is a progressive lung disease and its incidence rate is rapidly rising.However,effective therapies for the treatment of IPF are still lacking.Phosphodiesterase 4(PDE4)inhibitors were reported to be potential anti-fibrotic agents.Herein,structure-based hit-to-lead optimization of natural isoaurostatin(8.98μmol/L)resulted in several potent inhibitors of PDE4 with half maximal inhibitory concentration(IC_(50))values ranging from 35 nmol/L to 126 nmol/L.Co-crystal structures revealed that isoaurostatin compounds exhibited different binding patterns from the classic PDE4 inhibitor rolipram and the analogues would favor to be Z configurations other than the corresponding E isomers.Finally,lead 2–9 showed remarkable in vitro/in vivo anti-fibrotic effects indicating its potential as a novel anti-IPF agent.展开更多
Icariin is a pure compound derived from Epimedium brevicornu Maxim,and it helps the regulation of male reproduction.Nevertheless,the role and underlying mechanisms of Icariin in mediating male germ cell development re...Icariin is a pure compound derived from Epimedium brevicornu Maxim,and it helps the regulation of male reproduction.Nevertheless,the role and underlying mechanisms of Icariin in mediating male germ cell development remain to be clarified.Here,we have demonstrated that Icariin promoted proliferation and DNA synthesis of mouse spermatogonial stem cells(SSCs).Furthermore,surface plasmon resonance iron(SPRi)and molecular docking(MOE)assays revealed that phosphodiesterase 5A(PDE5A)was an important target of Icariin in mouse SSCs.Mechanically,Icariin decreased the expression level of PDE5A.Interestingly,hydrogen peroxides(H2O2)enhanced the expression level of phosphorylation H2A.X(p-H2A.X),whereas Icariin diminished the expression level of p-H2A.X and DNA damage caused by H2O2 in mouse SSCs.Finally,our in vivo animal study indicated that Icariin protected male reproduction.Collectively,these results implicate that Icariin targets PDE5A to regulate mouse SSC viability and DNA damage and improves male reproductive capacity.This study thus sheds new insights into molecular mechanisms underlying the fate decisions of mammalian SSCs and offers a scientific basis for the clinical application of Icariin in male reproduction.展开更多
This paper investigates the issue of fault-tolerant control for swarm systems subject to switched graphs,actuator faults and obstacles.A geometric-based partial differential equation(PDE)framework is proposed to unify...This paper investigates the issue of fault-tolerant control for swarm systems subject to switched graphs,actuator faults and obstacles.A geometric-based partial differential equation(PDE)framework is proposed to unify collision-free trajectory generation and fault-tolerant control.To deal with the fault-induced force imbalances,the Riemannian metric is proposed to coordinate nominal controllers and the global one.Then,Riemannianbased trajectory length optimization is solved by gradient's dynamic model-heat flow PDE,under which a feasible trajectory satisfying motion constraints is achieved to guide the faulty system.Such virtual control force emerges autonomously through this metric adjustments.Further,the tracking error is rigorously proven to be exponential boundedness.Simulation results confirm the validity of these theoretical findings.展开更多
We propose a novel type of nonlinear solver acceleration for systems of nonlinear partial differential equations(PDEs)that is based on online/adaptive learning.It is applied in the context of multiphase flow in porous...We propose a novel type of nonlinear solver acceleration for systems of nonlinear partial differential equations(PDEs)that is based on online/adaptive learning.It is applied in the context of multiphase flow in porous media.The proposed method rely on four pillars:(i)dimensionless numbers as input parameters for the machine learning model,(ii)simplified numerical model(two-dimensional)for the offline training,(iii)dynamic control of a nonlinear solver tuning parameter(numerical relaxation),(iv)and online learning for time real-improvement of the machine learning model.This strategy decreases the number of nonlinear iterations by dynamically modifying a single global parameter,the relaxation factor,and by adaptively learning the attributes of each numerical model on-the-run.Furthermore,this work performs a sensitivity study in the dimensionless parameters(machine learning features),assess the efficacy of various machine learning models,demonstrate a decrease in nonlinear iterations using our method in more intricate,realistic three-dimensional models,and fully couple a machine learning model into an open-source multiphase flow simulator achieving up to 85%reduction in computational time.展开更多
In a recent publication in Nature,Zhou and colleagues identified cyclic guanosine monophosphate(cGMP),a canonical phosphodiesterase 5(PDE5)substrate,as a key modulator of dendritic cell(DC)interstitial motility throug...In a recent publication in Nature,Zhou and colleagues identified cyclic guanosine monophosphate(cGMP),a canonical phosphodiesterase 5(PDE5)substrate,as a key modulator of dendritic cell(DC)interstitial motility through Rho kinase(ROCK)-dependent modulation of myosin-II activity.展开更多
文摘近几年来,深度学习无所不在,赋能于各个领域.尤其是人工智能与传统科学的结合(AI for science,AI4Science)引发广泛关注.在AI4Science领域,利用人工智能算法求解PDEs(AI4PDEs)已成为计算力学研究的焦点.AI4PDEs的核心是将数据与方程相融合,并且几乎可以求解任何偏微分方程问题,由于其融合数据的优势,相较于传统算法,其计算效率通常提升数万倍.因此,本文全面综述了AI4PDEs的研究,总结了现有AI4PDEs算法、理论,并讨论了其在固体力学中的应用,包括正问题和反问题,展望了未来研究方向,尤其是必然会出现的计算力学大模型.现有AI4PDEs算法包括基于物理信息神经网络(physicsinformed neural network,PINNs)、深度能量法(deep energy methods,DEM)、算子学习(operator learning),以及基于物理神经网络算子(physics-informed neural operator,PINO).AI4PDEs在科学计算中有许多应用,本文聚焦于固体力学,正问题包括线弹性、弹塑性,超弹性、以及断裂力学;反问题包括材料参数,本构,缺陷的识别,以及拓朴优化.AI4PDEs代表了一种全新的科学模拟方法,通过利用大量数据在特定问题上提供近似解,然后根据具体的物理方程进行微调,避免了像传统算法那样从头开始计算,因此AI4PDEs是未来计算力学大模型的雏形,能够大大加速传统数值算法.我们相信,利用人工智能助力科学计算不仅仅是计算领域的未来重要方向,同时也是计算力学的未来,即是智能计算力学。
基金supported by the Natural Science Foundation of China(Nos.22277019,82150204,22307031,22377023,22077143,and 82003594)Key Project of Guangdong Natural Science Foundation(No.2016A030311033)+2 种基金Fundamental Research Funds for Hainan University(Nos.KYQD(ZR)-21031,KYQD(ZR)-21108,KYQD(ZR)-23003,and XTCX2022JKA01)Guangdong Provincial Key Laboratory of Construction Foundation(No.2023B1212060022)Science Foundation of Hainan Province(Nos.KJRC2023B10,824YXQN420,and 324MS018)。
文摘Idiopathic pulmonary fibrosis(IPF)is a progressive lung disease and its incidence rate is rapidly rising.However,effective therapies for the treatment of IPF are still lacking.Phosphodiesterase 4(PDE4)inhibitors were reported to be potential anti-fibrotic agents.Herein,structure-based hit-to-lead optimization of natural isoaurostatin(8.98μmol/L)resulted in several potent inhibitors of PDE4 with half maximal inhibitory concentration(IC_(50))values ranging from 35 nmol/L to 126 nmol/L.Co-crystal structures revealed that isoaurostatin compounds exhibited different binding patterns from the classic PDE4 inhibitor rolipram and the analogues would favor to be Z configurations other than the corresponding E isomers.Finally,lead 2–9 showed remarkable in vitro/in vivo anti-fibrotic effects indicating its potential as a novel anti-IPF agent.
基金supported by the grants from the National Nature Science Foundation of China(No.32170862)Developmental Biology and Breeding(No.2022XKQ0205)+2 种基金the Research Team for Reproduction Health and Translational Medicine of Hunan Normal University(No.2023JC101)Graduate Scientific Research Innovation Project of Hunan Province(No.CX2022520)Shanghai Key Laboratory of Reproductive Medicine(2022SKLRM01).
文摘Icariin is a pure compound derived from Epimedium brevicornu Maxim,and it helps the regulation of male reproduction.Nevertheless,the role and underlying mechanisms of Icariin in mediating male germ cell development remain to be clarified.Here,we have demonstrated that Icariin promoted proliferation and DNA synthesis of mouse spermatogonial stem cells(SSCs).Furthermore,surface plasmon resonance iron(SPRi)and molecular docking(MOE)assays revealed that phosphodiesterase 5A(PDE5A)was an important target of Icariin in mouse SSCs.Mechanically,Icariin decreased the expression level of PDE5A.Interestingly,hydrogen peroxides(H2O2)enhanced the expression level of phosphorylation H2A.X(p-H2A.X),whereas Icariin diminished the expression level of p-H2A.X and DNA damage caused by H2O2 in mouse SSCs.Finally,our in vivo animal study indicated that Icariin protected male reproduction.Collectively,these results implicate that Icariin targets PDE5A to regulate mouse SSC viability and DNA damage and improves male reproductive capacity.This study thus sheds new insights into molecular mechanisms underlying the fate decisions of mammalian SSCs and offers a scientific basis for the clinical application of Icariin in male reproduction.
基金supported in part by the National Natural Science Foundation of China under Grant 62303144,62020106003,U22A2044in part by the Zhejiang Provincial Natural Science Foundation of China under Grant LQ23F030013.
文摘This paper investigates the issue of fault-tolerant control for swarm systems subject to switched graphs,actuator faults and obstacles.A geometric-based partial differential equation(PDE)framework is proposed to unify collision-free trajectory generation and fault-tolerant control.To deal with the fault-induced force imbalances,the Riemannian metric is proposed to coordinate nominal controllers and the global one.Then,Riemannianbased trajectory length optimization is solved by gradient's dynamic model-heat flow PDE,under which a feasible trajectory satisfying motion constraints is achieved to guide the faulty system.Such virtual control force emerges autonomously through this metric adjustments.Further,the tracking error is rigorously proven to be exponential boundedness.Simulation results confirm the validity of these theoretical findings.
基金MUFFINS,MUltiphase Flow-induced Fluid-flexible structure InteractioN in Subsea applications(EP/P033180/1)the PREMIERE programme grant(EP/T000414/1)SMARTRES,Smart assessment,management and optimization of urban geothermal resources(NE/X005607/1).
文摘We propose a novel type of nonlinear solver acceleration for systems of nonlinear partial differential equations(PDEs)that is based on online/adaptive learning.It is applied in the context of multiphase flow in porous media.The proposed method rely on four pillars:(i)dimensionless numbers as input parameters for the machine learning model,(ii)simplified numerical model(two-dimensional)for the offline training,(iii)dynamic control of a nonlinear solver tuning parameter(numerical relaxation),(iv)and online learning for time real-improvement of the machine learning model.This strategy decreases the number of nonlinear iterations by dynamically modifying a single global parameter,the relaxation factor,and by adaptively learning the attributes of each numerical model on-the-run.Furthermore,this work performs a sensitivity study in the dimensionless parameters(machine learning features),assess the efficacy of various machine learning models,demonstrate a decrease in nonlinear iterations using our method in more intricate,realistic three-dimensional models,and fully couple a machine learning model into an open-source multiphase flow simulator achieving up to 85%reduction in computational time.
基金supported by the National Natural Science Foundation of China(grant number:32000799)Key Research and Development Program of Zhejiang Province(grant number:2025C02058).
文摘In a recent publication in Nature,Zhou and colleagues identified cyclic guanosine monophosphate(cGMP),a canonical phosphodiesterase 5(PDE5)substrate,as a key modulator of dendritic cell(DC)interstitial motility through Rho kinase(ROCK)-dependent modulation of myosin-II activity.
