Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insigh...Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insights for disease intervention and pharmaceutical research.Current advanced AI-based technologies automatically generate robust representations of microbes and diseases,enabling effective MDI predictions.However,these models continue to face significant challenges.A major issue is their reliance on complex feature extractors and classifiers,which substantially diminishes the models’generalizability.To address this,we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs.Initially,we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation.Secondly,we employ decoupled representation learning technology,compelling the graph neural network(GNN)to independently learn the weights for each feature subspace,thus enhancing its expressive power.Finally,we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN,reducing information loss due to occlusion.Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models.This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research.Code and data are accessible at:https://github.com/shmildsj/MDI-IFDRL.展开更多
An average human ejaculate contains over 100 million sperm, but only a few succeed in accomplishing the journey to an egg by migration through the female reproductive tract. Among these few sperm, only one participate...An average human ejaculate contains over 100 million sperm, but only a few succeed in accomplishing the journey to an egg by migration through the female reproductive tract. Among these few sperm, only one participates in fertilization. There might be an ingenious molecular mechanism to ensure that the very best sperm fertilize an egg. However, recent gene disruption experiments in mice have revealed that many factors previously described as important for fertilization are largely dispensable. One could argue that the fertilization mechanism is made robust against gene disruptions. However, this is not likely, as there are already six different gene-disrupted mouse lines （Calmegin, Adam Ia, Adam2, Adam3, Ace and Pgapl）, all of which result in male sterility. The sperm from these animals are known to have defective zona-binding ability and at the same time lose oviduct-migrating ability. Concerning spermzona binding, the widely accepted involvement of sugar moiety on zona pellucida 3 （ZP3） is indicated to be dispensable by gene disruption experiments. Thus, the landscape of the mechanism of fertilization is revolving considerably. In the sperm-egg fusion process, CD9 on egg and IZUMO1 on sperm have emerged as essential factors. This review focuses on the mechanism of fertilization elucidated by gene-manipulated animals.展开更多
Nucleus-nucleus potentials are determined in the framework of double folding model for M3Y-Reid and M3Y- Paris effective nucleon-nucleon （NN） interactions. Both zero-range and finite-range exchange parts of NN inter...Nucleus-nucleus potentials are determined in the framework of double folding model for M3Y-Reid and M3Y- Paris effective nucleon-nucleon （NN） interactions. Both zero-range and finite-range exchange parts of NN interactions are considered in the folding procedure. In this paper the spherical projectile-spherical target system 16O＋^2008Pb is selected for calculating the barrier energies, fusion cross sections and barrier distributions with the density-independent and density-dependent NN interactions on the basis of M3Y-Reid and M3Y Paris NN interactions. The barrier energies become lower for Paris NN interactions in comparison with Reid NN interactions, and also for finite-range exchange part in comparison with zero-range exchange part. The density-dependent NN interactions give similar fusion cross sections and barrier distributions, and the density-independent NN interaction causes the barrier distribution moving to a higher position. However, the density-independent Reid NN interaction with zero-range exchange part gives the lowest fusion cross sections. We find that the calculated fusion cross sections and the barrier distributions are in agreement with the experimental data after renormalization of the nuclear potential due to coupled-channel effect.展开更多
Within the realm of multimodal neural machine translation(MNMT),addressing the challenge of seamlessly integrating textual data with corresponding image data to enhance translation accuracy has become a pressing issue...Within the realm of multimodal neural machine translation(MNMT),addressing the challenge of seamlessly integrating textual data with corresponding image data to enhance translation accuracy has become a pressing issue.We saw that discrepancies between textual content and associated images can lead to visual noise,potentially diverting the model’s focus away from the textual data and so affecting the translation’s comprehensive effectiveness.To solve this visual noise problem,we propose an innovative KDNR-MNMT model.Themodel combines the knowledge distillation technique with an anti-noise interaction mechanism,which makes full use of the synthesized graphic knowledge and local image interaction masks,aiming to extract more effective visual features.Meanwhile,the KDNR-MNMT model adopts a multimodal adaptive gating fusion strategy to enhance the constructive interaction of different modal information.By integrating a perceptual attention mechanism,which uses cross-modal interaction cues within the Transformer framework,our approach notably enhances the quality of machine translation outputs.To confirmthemodel’s performance,we carried out extensive testing and assessment on the extensively utilized Multi30K dataset.The outcomes of our experiments prove substantial enhancements in our model’s BLEU and METEOR scores,with respective increases of 0.78 and 0.99 points over prevailing methods.This accomplishment affirms the potency of our strategy for mitigating visual interference and heralds groundbreaking advancements within themultimodal NMT domain,further propelling the evolution of this scholarly pursuit.展开更多
Identifying drug-drug interactions(DDIs)is essential to prevent adverse effects from polypharmacy.Although deep learning has advanced DDI identification,the gap between powerful models and their lack of clinical appli...Identifying drug-drug interactions(DDIs)is essential to prevent adverse effects from polypharmacy.Although deep learning has advanced DDI identification,the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits.Here,we developed a Multi-Dimensional Feature Fusion model named MDFF,which integrates one-dimensional simplified molec-ular input line entry system sequence features,two-dimensional molecular graph features,and three-dimensional geometric features to enhance drug representations for predicting DDIs.MDFF was trained and validated on two DDI datasets,evaluated across three distinct scenarios,and compared with advanced DDI prediction models using accuracy,precision,recall,area under the curve,and F1 score metrics.MDFF achieved state-of-the-art performance across all metrics.Ablation experiments showed that integrating multi-dimensional drug features yielded the best results.More importantly,we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs.Among 12 real-world adverse drug reaction reports,the predictions of 9 reports were supported by relevant evidence.Additionally,MDFF demon-strated the ability to explain adverse DDI mechanisms,providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.展开更多
With the growing application of intelligent robots in service,manufacturing,and medical fields,efficient and natural interaction between humans and robots has become key to improving collaboration efficiency and user ...With the growing application of intelligent robots in service,manufacturing,and medical fields,efficient and natural interaction between humans and robots has become key to improving collaboration efficiency and user experience.Gesture recognition,as an intuitive and contactless interaction method,can overcome the limitations of traditional interfaces and enable real-time control and feedback of robot movements and behaviors.This study first reviews mainstream gesture recognition algorithms and their application on different sensing platforms(RGB cameras,depth cameras,and inertial measurement units).It then proposes a gesture recognition method based on multimodal feature fusion and a lightweight deep neural network that balances recognition accuracy with computational efficiency.At system level,a modular human-robot interaction architecture is constructed,comprising perception,decision,and execution layers,and gesture commands are transmitted and mapped to robot actions in real time via the ROS communication protocol.Through multiple comparative experiments on public gesture datasets and a self-collected dataset,the proposed method’s superiority is validated in terms of accuracy,response latency,and system robustness,while user-experience tests assess the interface’s usability.The results provide a reliable technical foundation for robot collaboration and service in complex scenarios,offering broad prospects for practical application and deployment.展开更多
With the increasing importance of multimodal data in emotional expression on social media,mainstream methods for sentiment analysis have shifted from unimodal to multimodal approaches.However,the challenges of extract...With the increasing importance of multimodal data in emotional expression on social media,mainstream methods for sentiment analysis have shifted from unimodal to multimodal approaches.However,the challenges of extracting high-quality emotional features and achieving effective interaction between different modalities remain two major obstacles in multimodal sentiment analysis.To address these challenges,this paper proposes a Text-Gated Interaction Network with Inter-Sample Commonality Perception(TGICP).Specifically,we utilize a Inter-sample Commonality Perception(ICP)module to extract common features from similar samples within the same modality,and use these common features to enhance the original features of each modality,thereby obtaining a richer and more complete multimodal sentiment representation.Subsequently,in the cross-modal interaction stage,we design a Text-Gated Interaction(TGI)module,which is text-driven.By calculating the mutual information difference between the text modality and nonverbal modalities,the TGI module dynamically adjusts the influence of emotional information from the text modality on nonverbal modalities.This helps to reduce modality information asymmetry while enabling full cross-modal interaction.Experimental results show that the proposed model achieves outstanding performance on both the CMU-MOSI and CMU-MOSEI baseline multimodal sentiment analysis datasets,validating its effectiveness in emotion recognition tasks.展开更多
By means of the multilinear variable separation(MLVS) approach, new interaction solutions with low-dimensional arbitrary functions of the(2+1)-dimensional Nizhnik–Novikov–Veselovtype system are constructed. Four-dro...By means of the multilinear variable separation(MLVS) approach, new interaction solutions with low-dimensional arbitrary functions of the(2+1)-dimensional Nizhnik–Novikov–Veselovtype system are constructed. Four-dromion structure, ring-parabolic soliton structure and corresponding fusion phenomena for the physical quantity U =λ(lnf)_(xy) are revealed for the first time. This MLVS approach can also be used to deal with the(2+1)-dimensional Sasa–Satsuma system.展开更多
In this paper, the nonlinear interaction of ultra-high power laser beam with fusion plasma at relativistic regime in the presence of obliquely external magnetic field has been studied. Imposing an external magnetic fi...In this paper, the nonlinear interaction of ultra-high power laser beam with fusion plasma at relativistic regime in the presence of obliquely external magnetic field has been studied. Imposing an external magnetic field on plasma can modify the density profile of the plasma so that the thermal conductivity of electrons reduces which is considered to be the decrease of the threshold energy for ignition. To achieve the fusion of Hydrogen–Boron(HB) fuel,the block acceleration model of plasma is employed. Energy production by HB isotopes can be of interest, since its reaction does not generate radioactive tritium. By using the inhibit factor in the block model acceleration of plasma and Maxwell's as well as the momentum transfer equations, the electron density distribution and dielectric permittivity of the plasma medium are obtained. Numerical results indicate that with increasing the intensity of the external magnetic field, the oscillation of the laser magnetic field decreases, while the dielectric permittivity increases. Moreover, the amplitude of the electron density becomes highly peaked and the plasma electrons are strongly bunched with increasing the intensity of external magnetic field. Therefore, the magnetized plasma can act as a positive focusing lens to enhance the fusion process. Besides, we find that with increasing θ-angle(from oblique external magnetic field) between 0 and 90°, the dielectric permittivity increases, while for θ between 90° and 180°, the dielectric permittivity decreases with increasing θ.展开更多
This paper presents a data fusion algorithm for dynamic system with multi-sensor and uncertain system models. The algorithm is mainly based on Kalman filter and interacting multiple model(IMM). It processes crosscorre...This paper presents a data fusion algorithm for dynamic system with multi-sensor and uncertain system models. The algorithm is mainly based on Kalman filter and interacting multiple model(IMM). It processes crosscorrelated sensor noises by using augmented fusion before model interacting. And eigenvalue decomposition is utilized to reduce calculation complexity and implement parallel computing. In simulation part, the feasibility of the algorithm was tested and verified, and the relationship between sensor number and the estimation precision was studied. Results show that simply increasing the number of sensor cannot always improve the performance of the estimation. Type and number of sensors should be optimized in practical applications.展开更多
Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges...Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges mentioned above with a single model.To tackle this dilemma,this paper proposes spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting(STSIGMA),an efficient end-to-end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework.ST-SIGMA adopts a trident encoder-decoder architecture to learn scene semantics and agent interaction information on bird’s-eye view(BEV)maps simultaneously.Specifically,an iterative aggregation network is first employed as the scene semantic encoder(SSE)to learn diverse scene information.To preserve dynamic interactions of traffic agents,ST-SIGMA further exploits a spatio-temporal graph network as the graph interaction encoder.Meanwhile,a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed.Extensive experiments on the nuScenes data set have demonstrated that the proposed ST-SIGMA achieves significant improvements compared to the state-of-theart(SOTA)methods in terms of scene perception and trajectory forecasting,respectively.Therefore,the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in realworld AD scenarios.展开更多
ELI-Beamlines(ELI-BL),one of the three pillars of the Extreme Light Infrastructure endeavour,will be in a unique position to perform research in high-energy-density-physics(HEDP),plasma physics and ultra-high intensit...ELI-Beamlines(ELI-BL),one of the three pillars of the Extreme Light Infrastructure endeavour,will be in a unique position to perform research in high-energy-density-physics(HEDP),plasma physics and ultra-high intensity(UHI)ð>10^(22) W=cm^(2)) lasereplasma interaction.Recently the need for HED laboratory physics was identified and the P3(plasma physics platform)installation under construction in ELI-BL will be an answer.The ELI-BL 10 PW laser makes possible fundamental research topics from high-field physics to new extreme states of matter such as radiation-dominated ones,high-pressure quantum ones,warm dense matter(WDM)and ultra-relativistic plasmas.HEDP is of fundamental importance for research in the field of laboratory astrophysics and inertial confinement fusion(ICF).Reaching such extreme states of matter now and in the future will depend on the use of plasma optics for amplifying and focusing laser pulses.This article will present the relevant technological infrastructure being built in ELI-BL for HEDP and UHI,and gives a brief overview of some research under way in the field of UHI,laboratory astrophysics,ICF,WDM,and plasma optics.展开更多
Biography videos based on life performances of prominent figures in history aim to describe great mens' life.In this paper,a novel interactive video summarization for biography video based on multimodal fusion is ...Biography videos based on life performances of prominent figures in history aim to describe great mens' life.In this paper,a novel interactive video summarization for biography video based on multimodal fusion is proposed,which is a novel approach of visualizing the specific features for biography video and interacting with video content by taking advantage of the ability of multimodality.In general,a story of movie progresses by dialogues of characters and the subtitles are produced with the basis on the dialogues which contains all the information related to the movie.In this paper,JGibbsLDA is applied to extract key words from subtitles because the biography video consists of different aspects to depict the characters' whole life.In terms of fusing keywords and key-frames,affinity propagation is adopted to calculate the similarity between each key-frame cluster and keywords.Through the method mentioned above,a video summarization is presented based on multimodal fusion which describes video content more completely.In order to reduce the time spent on searching the interest video content and get the relationship between main characters,a kind of map is adopted to visualize video content and interact with video summarization.An experiment is conducted to evaluate video summarization and the results demonstrate that this system can formally facilitate the exploration of video content while improving interaction and finding events of interest efficiently.展开更多
The interactions between the W nano-dust and deuterium plasma at different lo- cations of the EAST tokamak are simulated using a molecular dynamics code. It is shown that nano-dust particles, with the radius, Rd, ~5 n...The interactions between the W nano-dust and deuterium plasma at different lo- cations of the EAST tokamak are simulated using a molecular dynamics code. It is shown that nano-dust particles, with the radius, Rd, ~5 nm, can exist for at least several nano-seconds under the interactions from the ions without being ablated in some specific places of the tokamak edge plasma, while those with Rd ≥~25 nm may be ablated if the plasma temperature T~ 50 eV and density n^10^19 m-3. In addition, the collisions of tungsten nano-dust grains with a tungsten wall at 100 m/s or I000 m/s impinging speeds are simulated. It is demonstrated that the dust will stick to the wall, and the collision will not cause substantial damage to the wall, but it may be able to cause partial destruction of the dust grains themselves depending on their incident speeds.展开更多
Reliable simulations of laseretarget interaction on the macroscopic scale are burdened by the fact that the energy transport is very often non-local.This means that the mean-free-path of the transported species is lar...Reliable simulations of laseretarget interaction on the macroscopic scale are burdened by the fact that the energy transport is very often non-local.This means that the mean-free-path of the transported species is larger than the local gradient scale lengths and transport can be no longer considered diffusive.Kinetic simulations are not a feasible option due to tremendous computational demands,limited validity of the collisional operators and inaccurate treatment of thermal radiation.This is the point where hydrodynamic codes with non-local radiation and electron heat transport based on first principles emerge.The simulation code PETE(Plasma Euler and Transport Equations)combines both of them with a laser absorption method based on the Helmholtz equation and a radiation diffusion scheme presented in this article.In the case of modelling ablation processes it can be observed that both,thermal and radiative,transport processes are strongly non-local for laser intensities of 10^(13) W=cm^(2) and above.In this paper simulations for various laser intensities and different ablator materials are presented,where the non-local and diffusive treatments of radiation transport are compared.Significant discrepancies are observed,supporting importance of non-local transport for inertial confinement fusion related studies as well as for pre-pulse generated plasma in ultra-high intensity laseretarget interaction.展开更多
The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are ...The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are complex,the edges are blurred,and the sample numbers are unbalanced.To solve these problems,this paper proposes a Multi-branch Cross-scale Interactive Feature fusion Transformer model(MCIF-Transformer Mask RCNN)for PET/CT lung tumor instance segmentation,The main innovative works of this paper are as follows:Firstly,the ResNet-Transformer backbone network is used to extract global feature and local feature in lung images.The pixel dependence relationship is established in local and non-local fields to improve the model perception ability.Secondly,the Cross-scale Interactive Feature Enhancement auxiliary network is designed to provide the shallow features to the deep features,and the cross-scale interactive feature enhancement module(CIFEM)is used to enhance the attention ability of the fine-grained features.Thirdly,the Cross-scale Interactive Feature fusion FPN network(CIF-FPN)is constructed to realize bidirectional interactive fusion between deep features and shallow features,and the low-level features are enhanced in deep semantic features.Finally,4 ablation experiments,3 comparison experiments of detection,3 comparison experiments of segmentation and 6 comparison experiments with two-stage and single-stage instance segmentation networks are done on PET/CT lung medical image datasets.The results showed that APdet,APseg,ARdet and ARseg indexes are improved by 5.5%,5.15%,3.11%and 6.79%compared with Mask RCNN(resnet50).Based on the above research,the precise detection and segmentation of the lesion region are realized in this paper.This method has positive significance for the detection of lung tumors.展开更多
The importance of developing new technologies to obtain energy by means of nuclear fusion procedures is beyond question. There are several different and technically possible models for doing this, though to date none ...The importance of developing new technologies to obtain energy by means of nuclear fusion procedures is beyond question. There are several different and technically possible models for doing this, though to date none of these has been able to attain an industrial reactor with an end performance greater than unity. We still find ourselves at the initial phase, after many years, as a result of having failed as yet to come up with a commercially productive machine. Nuclear fusion research has defined a prototype reactor based on a fluid conductor, isolated materially in a physical container and confined by means of magnetic fields. In this fluid-plasma which interacts with magnetic fields, fusion reactions are caused that release energy, while at the same time a quantity of movement and angular momentum is moved or “rotated” and transported. However, turbulence is caused in these magnetic confinement fusion processes that reduces system efficiency and prevents the obtaining of sufficient net energy from the nuclear reactions. This paper aims to propose new dynamic hypotheses to enhance our understanding of the behaviour of the plasma in the reactor. In doing so, we put forward a profound revision of classical dynamics. After over thirty years studying rotational dynamics, we propose a new theory of dynamic interactions to better interpret nature in rotation. This new theory has been tested experimentally returning positive results, even by third parties. We suggest that these new dynamic hypotheses, which we hold applicable to particle systems accelerated by rotation, be used in the interpretation and design of fusion reactors. We believe that this proposal could, in addition to magnetic confinement, achieve confinement by simultaneous and compatible dynamic interaction. Accordingly, we are of the opinion that it would be possible to get better performance and results in the design of fusion reactors by way of simultaneous magnetic and dynamic interaction confinement.展开更多
Cell fusion is a basic biological process that plays critical roles in both physiological and pathological processes.However,how mechanical factors influence the fusion process is not fully understood.In this study,we...Cell fusion is a basic biological process that plays critical roles in both physiological and pathological processes.However,how mechanical factors influence the fusion process is not fully understood.In this study,we reported filopodia-mediated fusion among MCF-7 cells.We showed that the filopodia protrusion force induced significant bending of the cell membrane,which was essential for membrane fusion between neighboring cells,and then eventually induced the formation of multinucleated syncytia.The inhibition of actin polymerization significantly reduced the fusion ratio,whereas increased actin polymerization promoted fusion.We found that several factors influence the fusion process,e.g.,the cell density,substrate pattern,and stiffness.For example,cell density has a significant effect on cell fusion.There was an optimal cell density for cell fusion.The fusion probability increased with increasing cell density within a moderate cell density range but decreased within a high cell density range.Substrate properties also influence the fusion behavior.For example,the fusion ratio was reduced on nanogrooved surfaces and soft substrates because the surface pattern restricted cell alignment and motility,and soft substrates reduced the activity of the actin dynamics of filopodia for cell fusion.This study not only contributes to our under-standing of the basic biology of cell fusion but also has important implications for understanding the mechanisms of cancer progression and potential therapeutic intervention methods.展开更多
Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing...Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing computational methods for preclinical and clinical cancer drug response(CDR)prediction,challenges remain regarding the generalization of new drugs that are unseen in the training set.Herein,we propose a multimodal fusion deep learning(DL)model called drug-target and single-cell language based CDR(DTLCDR)to predict preclinical and clinical CDRs.The model integrates chemical descriptors,molecular graph representations,predicted protein target profiles of drugs,and cell line expression profiles with general knowledge from single cells.Among these features,a well-trained drug-target interaction(DTI)prediction model is used to generate target profiles of drugs,and a pretrained single-cell language model is integrated to provide general genomic knowledge.Comparison experiments on the cell line drug sensitivity dataset demonstrated that DTLCDR exhibited improved generalizability and robustness in predicting unseen drugs compared with previous state-of-the-art baseline methods.Further ablation studies verified the effectiveness of each component of our model,highlighting the significant contribution of target information to generalizability.Subsequently,the ability of DTLCDR to predict novel molecules was validated through in vitro cell experiments,demonstrating its potential for real-world applications.Moreover,DTLCDR was transferred to the clinical datasets,demonstrating satisfactory performance in the clinical data,regardless of whether the drugs were included in the cell line dataset.Overall,our results suggest that the DTLCDR is a promising tool for personalized drug discovery.展开更多
基金supported by the Natural Science Foundation of Wenzhou University of Technology,China(Grant No.:ky202211).
文摘Research indicates that microbe activity within the human body significantly influences health by being closely linked to various diseases.Accurately predicting microbe-disease interactions(MDIs)offers critical insights for disease intervention and pharmaceutical research.Current advanced AI-based technologies automatically generate robust representations of microbes and diseases,enabling effective MDI predictions.However,these models continue to face significant challenges.A major issue is their reliance on complex feature extractors and classifiers,which substantially diminishes the models’generalizability.To address this,we introduce a novel graph autoencoder framework that utilizes decoupled representation learning and multi-scale information fusion strategies to efficiently infer potential MDIs.Initially,we randomly mask portions of the input microbe-disease graph based on Bernoulli distribution to boost self-supervised training and minimize noise-related performance degradation.Secondly,we employ decoupled representation learning technology,compelling the graph neural network(GNN)to independently learn the weights for each feature subspace,thus enhancing its expressive power.Finally,we implement multi-scale information fusion technology to amalgamate the multi-layer outputs of GNN,reducing information loss due to occlusion.Extensive experiments on public datasets demonstrate that our model significantly surpasses existing top MDI prediction models.This indicates that our model can accurately predict unknown MDIs and is likely to aid in disease discovery and precision pharmaceutical research.Code and data are accessible at:https://github.com/shmildsj/MDI-IFDRL.
文摘An average human ejaculate contains over 100 million sperm, but only a few succeed in accomplishing the journey to an egg by migration through the female reproductive tract. Among these few sperm, only one participates in fertilization. There might be an ingenious molecular mechanism to ensure that the very best sperm fertilize an egg. However, recent gene disruption experiments in mice have revealed that many factors previously described as important for fertilization are largely dispensable. One could argue that the fertilization mechanism is made robust against gene disruptions. However, this is not likely, as there are already six different gene-disrupted mouse lines （Calmegin, Adam Ia, Adam2, Adam3, Ace and Pgapl）, all of which result in male sterility. The sperm from these animals are known to have defective zona-binding ability and at the same time lose oviduct-migrating ability. Concerning spermzona binding, the widely accepted involvement of sugar moiety on zona pellucida 3 （ZP3） is indicated to be dispensable by gene disruption experiments. Thus, the landscape of the mechanism of fertilization is revolving considerably. In the sperm-egg fusion process, CD9 on egg and IZUMO1 on sperm have emerged as essential factors. This review focuses on the mechanism of fertilization elucidated by gene-manipulated animals.
基金Project supported by the National Natural Science Foundation of China (Grant No 60572177)
文摘Nucleus-nucleus potentials are determined in the framework of double folding model for M3Y-Reid and M3Y- Paris effective nucleon-nucleon （NN） interactions. Both zero-range and finite-range exchange parts of NN interactions are considered in the folding procedure. In this paper the spherical projectile-spherical target system 16O＋^2008Pb is selected for calculating the barrier energies, fusion cross sections and barrier distributions with the density-independent and density-dependent NN interactions on the basis of M3Y-Reid and M3Y Paris NN interactions. The barrier energies become lower for Paris NN interactions in comparison with Reid NN interactions, and also for finite-range exchange part in comparison with zero-range exchange part. The density-dependent NN interactions give similar fusion cross sections and barrier distributions, and the density-independent NN interaction causes the barrier distribution moving to a higher position. However, the density-independent Reid NN interaction with zero-range exchange part gives the lowest fusion cross sections. We find that the calculated fusion cross sections and the barrier distributions are in agreement with the experimental data after renormalization of the nuclear potential due to coupled-channel effect.
基金supported by the Henan Provincial Science and Technology Research Project:232102211017,232102211006,232102210044,242102211020 and 242102211007the ZhengzhouUniversity of Light Industry Science and Technology Innovation Team Program Project:23XNKJTD0205.
文摘Within the realm of multimodal neural machine translation(MNMT),addressing the challenge of seamlessly integrating textual data with corresponding image data to enhance translation accuracy has become a pressing issue.We saw that discrepancies between textual content and associated images can lead to visual noise,potentially diverting the model’s focus away from the textual data and so affecting the translation’s comprehensive effectiveness.To solve this visual noise problem,we propose an innovative KDNR-MNMT model.Themodel combines the knowledge distillation technique with an anti-noise interaction mechanism,which makes full use of the synthesized graphic knowledge and local image interaction masks,aiming to extract more effective visual features.Meanwhile,the KDNR-MNMT model adopts a multimodal adaptive gating fusion strategy to enhance the constructive interaction of different modal information.By integrating a perceptual attention mechanism,which uses cross-modal interaction cues within the Transformer framework,our approach notably enhances the quality of machine translation outputs.To confirmthemodel’s performance,we carried out extensive testing and assessment on the extensively utilized Multi30K dataset.The outcomes of our experiments prove substantial enhancements in our model’s BLEU and METEOR scores,with respective increases of 0.78 and 0.99 points over prevailing methods.This accomplishment affirms the potency of our strategy for mitigating visual interference and heralds groundbreaking advancements within themultimodal NMT domain,further propelling the evolution of this scholarly pursuit.
基金supported by the National Key R&D Program of China(Grant No.:2023YFC2604400)the National Natural Science Foundation of China(Grant No.:62103436).
文摘Identifying drug-drug interactions(DDIs)is essential to prevent adverse effects from polypharmacy.Although deep learning has advanced DDI identification,the gap between powerful models and their lack of clinical application and evaluation has hindered clinical benefits.Here,we developed a Multi-Dimensional Feature Fusion model named MDFF,which integrates one-dimensional simplified molec-ular input line entry system sequence features,two-dimensional molecular graph features,and three-dimensional geometric features to enhance drug representations for predicting DDIs.MDFF was trained and validated on two DDI datasets,evaluated across three distinct scenarios,and compared with advanced DDI prediction models using accuracy,precision,recall,area under the curve,and F1 score metrics.MDFF achieved state-of-the-art performance across all metrics.Ablation experiments showed that integrating multi-dimensional drug features yielded the best results.More importantly,we obtained adverse drug reaction reports uploaded by Xiangya Hospital of Central South University from 2021 to 2023 and used MDFF to identify potential adverse DDIs.Among 12 real-world adverse drug reaction reports,the predictions of 9 reports were supported by relevant evidence.Additionally,MDFF demon-strated the ability to explain adverse DDI mechanisms,providing insights into the mechanisms behind one specific report and highlighting its potential to assist practitioners in improving medical practice.
文摘With the growing application of intelligent robots in service,manufacturing,and medical fields,efficient and natural interaction between humans and robots has become key to improving collaboration efficiency and user experience.Gesture recognition,as an intuitive and contactless interaction method,can overcome the limitations of traditional interfaces and enable real-time control and feedback of robot movements and behaviors.This study first reviews mainstream gesture recognition algorithms and their application on different sensing platforms(RGB cameras,depth cameras,and inertial measurement units).It then proposes a gesture recognition method based on multimodal feature fusion and a lightweight deep neural network that balances recognition accuracy with computational efficiency.At system level,a modular human-robot interaction architecture is constructed,comprising perception,decision,and execution layers,and gesture commands are transmitted and mapped to robot actions in real time via the ROS communication protocol.Through multiple comparative experiments on public gesture datasets and a self-collected dataset,the proposed method’s superiority is validated in terms of accuracy,response latency,and system robustness,while user-experience tests assess the interface’s usability.The results provide a reliable technical foundation for robot collaboration and service in complex scenarios,offering broad prospects for practical application and deployment.
基金supported by the Natural Science Foundation of Henan under Grant 242300421220the Henan Provincial Science and Technology Research Project under Grants 252102211047 and 252102211062+3 种基金the Jiangsu Provincial Scheme Double Initiative Plan JSS-CBS20230474the XJTLU RDF-21-02-008the Science and Technology Innovation Project of Zhengzhou University of Light Industry under Grant 23XNKJTD0205the Higher Education Teaching Reform Research and Practice Project of Henan Province under Grant 2024SJGLX0126.
文摘With the increasing importance of multimodal data in emotional expression on social media,mainstream methods for sentiment analysis have shifted from unimodal to multimodal approaches.However,the challenges of extracting high-quality emotional features and achieving effective interaction between different modalities remain two major obstacles in multimodal sentiment analysis.To address these challenges,this paper proposes a Text-Gated Interaction Network with Inter-Sample Commonality Perception(TGICP).Specifically,we utilize a Inter-sample Commonality Perception(ICP)module to extract common features from similar samples within the same modality,and use these common features to enhance the original features of each modality,thereby obtaining a richer and more complete multimodal sentiment representation.Subsequently,in the cross-modal interaction stage,we design a Text-Gated Interaction(TGI)module,which is text-driven.By calculating the mutual information difference between the text modality and nonverbal modalities,the TGI module dynamically adjusts the influence of emotional information from the text modality on nonverbal modalities.This helps to reduce modality information asymmetry while enabling full cross-modal interaction.Experimental results show that the proposed model achieves outstanding performance on both the CMU-MOSI and CMU-MOSEI baseline multimodal sentiment analysis datasets,validating its effectiveness in emotion recognition tasks.
基金supported by the National Natural Science Foundation of China (11771395)。
文摘By means of the multilinear variable separation(MLVS) approach, new interaction solutions with low-dimensional arbitrary functions of the(2+1)-dimensional Nizhnik–Novikov–Veselovtype system are constructed. Four-dromion structure, ring-parabolic soliton structure and corresponding fusion phenomena for the physical quantity U =λ(lnf)_(xy) are revealed for the first time. This MLVS approach can also be used to deal with the(2+1)-dimensional Sasa–Satsuma system.
文摘In this paper, the nonlinear interaction of ultra-high power laser beam with fusion plasma at relativistic regime in the presence of obliquely external magnetic field has been studied. Imposing an external magnetic field on plasma can modify the density profile of the plasma so that the thermal conductivity of electrons reduces which is considered to be the decrease of the threshold energy for ignition. To achieve the fusion of Hydrogen–Boron(HB) fuel,the block acceleration model of plasma is employed. Energy production by HB isotopes can be of interest, since its reaction does not generate radioactive tritium. By using the inhibit factor in the block model acceleration of plasma and Maxwell's as well as the momentum transfer equations, the electron density distribution and dielectric permittivity of the plasma medium are obtained. Numerical results indicate that with increasing the intensity of the external magnetic field, the oscillation of the laser magnetic field decreases, while the dielectric permittivity increases. Moreover, the amplitude of the electron density becomes highly peaked and the plasma electrons are strongly bunched with increasing the intensity of external magnetic field. Therefore, the magnetized plasma can act as a positive focusing lens to enhance the fusion process. Besides, we find that with increasing θ-angle(from oblique external magnetic field) between 0 and 90°, the dielectric permittivity increases, while for θ between 90° and 180°, the dielectric permittivity decreases with increasing θ.
基金the National Natural Science Foundation of China(No.61374160)the Shanghai Aerospace Science and Technology Innovation Fund(No.SAST201237)
文摘This paper presents a data fusion algorithm for dynamic system with multi-sensor and uncertain system models. The algorithm is mainly based on Kalman filter and interacting multiple model(IMM). It processes crosscorrelated sensor noises by using augmented fusion before model interacting. And eigenvalue decomposition is utilized to reduce calculation complexity and implement parallel computing. In simulation part, the feasibility of the algorithm was tested and verified, and the relationship between sensor number and the estimation precision was studied. Results show that simply increasing the number of sensor cannot always improve the performance of the estimation. Type and number of sensors should be optimized in practical applications.
基金Basic and Advanced Research Projects of CSTC,Grant/Award Number:cstc2019jcyj-zdxmX0008Science and Technology Research Program of Chongqing Municipal Education Commission,Grant/Award Numbers:KJQN202100634,KJZDK201900605National Natural Science Foundation of China,Grant/Award Number:62006065。
文摘Scene perception and trajectory forecasting are two fundamental challenges that are crucial to a safe and reliable autonomous driving(AD)system.However,most proposed methods aim at addressing one of the two challenges mentioned above with a single model.To tackle this dilemma,this paper proposes spatio-temporal semantics and interaction graph aggregation for multi-agent perception and trajectory forecasting(STSIGMA),an efficient end-to-end method to jointly and accurately perceive the AD environment and forecast the trajectories of the surrounding traffic agents within a unified framework.ST-SIGMA adopts a trident encoder-decoder architecture to learn scene semantics and agent interaction information on bird’s-eye view(BEV)maps simultaneously.Specifically,an iterative aggregation network is first employed as the scene semantic encoder(SSE)to learn diverse scene information.To preserve dynamic interactions of traffic agents,ST-SIGMA further exploits a spatio-temporal graph network as the graph interaction encoder.Meanwhile,a simple yet efficient feature fusion method to fuse semantic and interaction features into a unified feature space as the input to a novel hierarchical aggregation decoder for downstream prediction tasks is designed.Extensive experiments on the nuScenes data set have demonstrated that the proposed ST-SIGMA achieves significant improvements compared to the state-of-theart(SOTA)methods in terms of scene perception and trajectory forecasting,respectively.Therefore,the proposed approach outperforms SOTA in terms of model generalisation and robustness and is therefore more feasible for deployment in realworld AD scenarios.
基金The authors acknowledge support from the project ELI:Extreme Light Infrastructure from European Regional Devel-opment(CZ.02.1.01/0.0/0.0/15-008/0000162)Also supported by the project High Field Initiative(CZ.02.1.01/0.0/0.0/15-003/0000449)from European Regional Development Fund.
文摘ELI-Beamlines(ELI-BL),one of the three pillars of the Extreme Light Infrastructure endeavour,will be in a unique position to perform research in high-energy-density-physics(HEDP),plasma physics and ultra-high intensity(UHI)ð>10^(22) W=cm^(2)) lasereplasma interaction.Recently the need for HED laboratory physics was identified and the P3(plasma physics platform)installation under construction in ELI-BL will be an answer.The ELI-BL 10 PW laser makes possible fundamental research topics from high-field physics to new extreme states of matter such as radiation-dominated ones,high-pressure quantum ones,warm dense matter(WDM)and ultra-relativistic plasmas.HEDP is of fundamental importance for research in the field of laboratory astrophysics and inertial confinement fusion(ICF).Reaching such extreme states of matter now and in the future will depend on the use of plasma optics for amplifying and focusing laser pulses.This article will present the relevant technological infrastructure being built in ELI-BL for HEDP and UHI,and gives a brief overview of some research under way in the field of UHI,laboratory astrophysics,ICF,WDM,and plasma optics.
基金Supported by the National Key Research and Development Plan(2016YFB1001200)the Natural Science Foundation of China(U1435220,61232013)Natural Science Research Projects of Universities in Jiangsu Province(16KJA520003)
文摘Biography videos based on life performances of prominent figures in history aim to describe great mens' life.In this paper,a novel interactive video summarization for biography video based on multimodal fusion is proposed,which is a novel approach of visualizing the specific features for biography video and interacting with video content by taking advantage of the ability of multimodality.In general,a story of movie progresses by dialogues of characters and the subtitles are produced with the basis on the dialogues which contains all the information related to the movie.In this paper,JGibbsLDA is applied to extract key words from subtitles because the biography video consists of different aspects to depict the characters' whole life.In terms of fusing keywords and key-frames,affinity propagation is adopted to calculate the similarity between each key-frame cluster and keywords.Through the method mentioned above,a video summarization is presented based on multimodal fusion which describes video content more completely.In order to reduce the time spent on searching the interest video content and get the relationship between main characters,a kind of map is adopted to visualize video content and interact with video summarization.An experiment is conducted to evaluate video summarization and the results demonstrate that this system can formally facilitate the exploration of video content while improving interaction and finding events of interest efficiently.
基金supported by National Natural Science Foundation of China (No. 11075186)
文摘The interactions between the W nano-dust and deuterium plasma at different lo- cations of the EAST tokamak are simulated using a molecular dynamics code. It is shown that nano-dust particles, with the radius, Rd, ~5 nm, can exist for at least several nano-seconds under the interactions from the ions without being ablated in some specific places of the tokamak edge plasma, while those with Rd ≥~25 nm may be ablated if the plasma temperature T~ 50 eV and density n^10^19 m-3. In addition, the collisions of tungsten nano-dust grains with a tungsten wall at 100 m/s or I000 m/s impinging speeds are simulated. It is demonstrated that the dust will stick to the wall, and the collision will not cause substantial damage to the wall, but it may be able to cause partial destruction of the dust grains themselves depending on their incident speeds.
文摘Reliable simulations of laseretarget interaction on the macroscopic scale are burdened by the fact that the energy transport is very often non-local.This means that the mean-free-path of the transported species is larger than the local gradient scale lengths and transport can be no longer considered diffusive.Kinetic simulations are not a feasible option due to tremendous computational demands,limited validity of the collisional operators and inaccurate treatment of thermal radiation.This is the point where hydrodynamic codes with non-local radiation and electron heat transport based on first principles emerge.The simulation code PETE(Plasma Euler and Transport Equations)combines both of them with a laser absorption method based on the Helmholtz equation and a radiation diffusion scheme presented in this article.In the case of modelling ablation processes it can be observed that both,thermal and radiative,transport processes are strongly non-local for laser intensities of 10^(13) W=cm^(2) and above.In this paper simulations for various laser intensities and different ablator materials are presented,where the non-local and diffusive treatments of radiation transport are compared.Significant discrepancies are observed,supporting importance of non-local transport for inertial confinement fusion related studies as well as for pre-pulse generated plasma in ultra-high intensity laseretarget interaction.
基金funded by National Natural Science Foundation of China No.62062003Ningxia Natural Science Foundation Project No.2023AAC03293.
文摘The precise detection and segmentation of tumor lesions are very important for lung cancer computer-aided diagnosis.However,in PET/CT(Positron Emission Tomography/Computed Tomography)lung images,the lesion shapes are complex,the edges are blurred,and the sample numbers are unbalanced.To solve these problems,this paper proposes a Multi-branch Cross-scale Interactive Feature fusion Transformer model(MCIF-Transformer Mask RCNN)for PET/CT lung tumor instance segmentation,The main innovative works of this paper are as follows:Firstly,the ResNet-Transformer backbone network is used to extract global feature and local feature in lung images.The pixel dependence relationship is established in local and non-local fields to improve the model perception ability.Secondly,the Cross-scale Interactive Feature Enhancement auxiliary network is designed to provide the shallow features to the deep features,and the cross-scale interactive feature enhancement module(CIFEM)is used to enhance the attention ability of the fine-grained features.Thirdly,the Cross-scale Interactive Feature fusion FPN network(CIF-FPN)is constructed to realize bidirectional interactive fusion between deep features and shallow features,and the low-level features are enhanced in deep semantic features.Finally,4 ablation experiments,3 comparison experiments of detection,3 comparison experiments of segmentation and 6 comparison experiments with two-stage and single-stage instance segmentation networks are done on PET/CT lung medical image datasets.The results showed that APdet,APseg,ARdet and ARseg indexes are improved by 5.5%,5.15%,3.11%and 6.79%compared with Mask RCNN(resnet50).Based on the above research,the precise detection and segmentation of the lesion region are realized in this paper.This method has positive significance for the detection of lung tumors.
文摘The importance of developing new technologies to obtain energy by means of nuclear fusion procedures is beyond question. There are several different and technically possible models for doing this, though to date none of these has been able to attain an industrial reactor with an end performance greater than unity. We still find ourselves at the initial phase, after many years, as a result of having failed as yet to come up with a commercially productive machine. Nuclear fusion research has defined a prototype reactor based on a fluid conductor, isolated materially in a physical container and confined by means of magnetic fields. In this fluid-plasma which interacts with magnetic fields, fusion reactions are caused that release energy, while at the same time a quantity of movement and angular momentum is moved or “rotated” and transported. However, turbulence is caused in these magnetic confinement fusion processes that reduces system efficiency and prevents the obtaining of sufficient net energy from the nuclear reactions. This paper aims to propose new dynamic hypotheses to enhance our understanding of the behaviour of the plasma in the reactor. In doing so, we put forward a profound revision of classical dynamics. After over thirty years studying rotational dynamics, we propose a new theory of dynamic interactions to better interpret nature in rotation. This new theory has been tested experimentally returning positive results, even by third parties. We suggest that these new dynamic hypotheses, which we hold applicable to particle systems accelerated by rotation, be used in the interpretation and design of fusion reactors. We believe that this proposal could, in addition to magnetic confinement, achieve confinement by simultaneous and compatible dynamic interaction. Accordingly, we are of the opinion that it would be possible to get better performance and results in the design of fusion reactors by way of simultaneous magnetic and dynamic interaction confinement.
基金supported by the National Natural Science Foundation of China(Grant Nos.11932017 and 12122212).
文摘Cell fusion is a basic biological process that plays critical roles in both physiological and pathological processes.However,how mechanical factors influence the fusion process is not fully understood.In this study,we reported filopodia-mediated fusion among MCF-7 cells.We showed that the filopodia protrusion force induced significant bending of the cell membrane,which was essential for membrane fusion between neighboring cells,and then eventually induced the formation of multinucleated syncytia.The inhibition of actin polymerization significantly reduced the fusion ratio,whereas increased actin polymerization promoted fusion.We found that several factors influence the fusion process,e.g.,the cell density,substrate pattern,and stiffness.For example,cell density has a significant effect on cell fusion.There was an optimal cell density for cell fusion.The fusion probability increased with increasing cell density within a moderate cell density range but decreased within a high cell density range.Substrate properties also influence the fusion behavior.For example,the fusion ratio was reduced on nanogrooved surfaces and soft substrates because the surface pattern restricted cell alignment and motility,and soft substrates reduced the activity of the actin dynamics of filopodia for cell fusion.This study not only contributes to our under-standing of the basic biology of cell fusion but also has important implications for understanding the mechanisms of cancer progression and potential therapeutic intervention methods.
基金supported by the National Key Research and Development Program of China(Grant No.:2023YFC2605002)the National Key R&D Program of China(Grant No.:2022YFF1203003)+2 种基金Beijing AI Health Cultivation Project,China(Grant No.:Z221100003522022)the National Natural Science Foundation of China(Grant No.:82273772)the Beijing Natural Science Foundation,China(Grant No.:7212152).
文摘Accurate prediction of drug responses in cancer cell lines(CCLs)and transferable prediction of clinical drug responses using CCLs are two major tasks in personalized medicine.Despite the rapid advancements in existing computational methods for preclinical and clinical cancer drug response(CDR)prediction,challenges remain regarding the generalization of new drugs that are unseen in the training set.Herein,we propose a multimodal fusion deep learning(DL)model called drug-target and single-cell language based CDR(DTLCDR)to predict preclinical and clinical CDRs.The model integrates chemical descriptors,molecular graph representations,predicted protein target profiles of drugs,and cell line expression profiles with general knowledge from single cells.Among these features,a well-trained drug-target interaction(DTI)prediction model is used to generate target profiles of drugs,and a pretrained single-cell language model is integrated to provide general genomic knowledge.Comparison experiments on the cell line drug sensitivity dataset demonstrated that DTLCDR exhibited improved generalizability and robustness in predicting unseen drugs compared with previous state-of-the-art baseline methods.Further ablation studies verified the effectiveness of each component of our model,highlighting the significant contribution of target information to generalizability.Subsequently,the ability of DTLCDR to predict novel molecules was validated through in vitro cell experiments,demonstrating its potential for real-world applications.Moreover,DTLCDR was transferred to the clinical datasets,demonstrating satisfactory performance in the clinical data,regardless of whether the drugs were included in the cell line dataset.Overall,our results suggest that the DTLCDR is a promising tool for personalized drug discovery.
