Pub Date : 2024-12-06DOI: 10.1038/s42256-024-00938-z
Zeyu Li, Wang Han, Yue Zhang, Qingfei Fu, Jingxuan Li, Lizi Qin, Ruoyu Dong, Hao Sun, Yue Deng, Lijun Yang
Reconstructing spatiotemporal dynamics with sparse sensor measurement is a challenging task that is encountered in a wide spectrum of scientific and engineering applications. The problem is particularly challenging when the number or types of sensors (for example, randomly placed) are extremely sparse. Existing end-to-end learning models ordinarily do not generalize well to unseen full-field reconstruction of spatiotemporal dynamics, especially in sparse data regimes typically seen in real-world applications. To address this challenge, here we propose a sparse-sensor-assisted score-based generative model (S3GM) to reconstruct and predict full-field spatiotemporal dynamics on the basis of sparse measurements. Instead of learning directly the mapping between input and output pairs, an unconditioned generative model is first pretrained, capturing the joint distribution of a vast group of pretraining data in a self-supervised manner, followed by a sampling process conditioned on unseen sparse measurement. The efficacy of S3GM has been verified on multiple dynamical systems with various synthetic, real-world and laboratory-test datasets (ranging from turbulent flow modelling to weather/climate forecasting). The results demonstrate the sound performance of S3GM in zero-shot reconstruction and prediction of spatiotemporal dynamics even with high levels of data sparsity and noise. We find that S3GM exhibits high accuracy, generalizability and robustness when handling different reconstruction tasks. Reconstructing and predicting spatiotemporal dynamics from sparse sensor data is challenging, especially with limited sensors. Li et al. address this by using self-supervised pretraining of a generative model, improving accuracy and generalization.
{"title":"Learning spatiotemporal dynamics with a pretrained generative model","authors":"Zeyu Li, Wang Han, Yue Zhang, Qingfei Fu, Jingxuan Li, Lizi Qin, Ruoyu Dong, Hao Sun, Yue Deng, Lijun Yang","doi":"10.1038/s42256-024-00938-z","DOIUrl":"10.1038/s42256-024-00938-z","url":null,"abstract":"Reconstructing spatiotemporal dynamics with sparse sensor measurement is a challenging task that is encountered in a wide spectrum of scientific and engineering applications. The problem is particularly challenging when the number or types of sensors (for example, randomly placed) are extremely sparse. Existing end-to-end learning models ordinarily do not generalize well to unseen full-field reconstruction of spatiotemporal dynamics, especially in sparse data regimes typically seen in real-world applications. To address this challenge, here we propose a sparse-sensor-assisted score-based generative model (S3GM) to reconstruct and predict full-field spatiotemporal dynamics on the basis of sparse measurements. Instead of learning directly the mapping between input and output pairs, an unconditioned generative model is first pretrained, capturing the joint distribution of a vast group of pretraining data in a self-supervised manner, followed by a sampling process conditioned on unseen sparse measurement. The efficacy of S3GM has been verified on multiple dynamical systems with various synthetic, real-world and laboratory-test datasets (ranging from turbulent flow modelling to weather/climate forecasting). The results demonstrate the sound performance of S3GM in zero-shot reconstruction and prediction of spatiotemporal dynamics even with high levels of data sparsity and noise. We find that S3GM exhibits high accuracy, generalizability and robustness when handling different reconstruction tasks. Reconstructing and predicting spatiotemporal dynamics from sparse sensor data is challenging, especially with limited sensors. Li et al. address this by using self-supervised pretraining of a generative model, improving accuracy and generalization.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1566-1579"},"PeriodicalIF":18.8,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142783265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-05DOI: 10.1038/s42256-024-00944-1
Jianing Qiu, Kyle Lam, Guohao Li, Amish Acharya, Tien Yin Wong, Ara Darzi, Wu Yuan, Eric J. Topol
Large language model-based agentic systems can process input information, plan and decide, recall and reflect, interact and collaborate, leverage various tools and act. This opens up a wealth of opportunities within medicine and healthcare, ranging from clinical workflow automation to multi-agent-aided diagnosis.
{"title":"LLM-based agentic systems in medicine and healthcare","authors":"Jianing Qiu, Kyle Lam, Guohao Li, Amish Acharya, Tien Yin Wong, Ara Darzi, Wu Yuan, Eric J. Topol","doi":"10.1038/s42256-024-00944-1","DOIUrl":"10.1038/s42256-024-00944-1","url":null,"abstract":"Large language model-based agentic systems can process input information, plan and decide, recall and reflect, interact and collaborate, leverage various tools and act. This opens up a wealth of opportunities within medicine and healthcare, ranging from clinical workflow automation to multi-agent-aided diagnosis.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1418-1420"},"PeriodicalIF":18.8,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-05DOI: 10.1038/s42256-024-00940-5
Juntao Deng, Miao Gu, Pengyan Zhang, Mingyu Dong, Tao Liu, Yabin Zhang, Min Liu
Nanobodies can provide specific binding to divergent antigens, leading to many promising therapeutic and detection applications in recent years. Traditional technologies of nanobody discovery based on alpaca immunization and phage display are very time-consuming and labour-intensive. Despite recent progress in the study of nanobodies, developing fast and accurate computational tools for nanobody–antigen interaction (NAI) prediction is urgently desirable. Here we propose an ensemble deep learning-based framework named DeepNano-seq to predict general protein–protein interaction (PPI) containing NAI from pure sequence information. Quantitative comparison results show that DeepNano-seq possesses the best cross-species generalization ability among existing PPI algorithms. Nevertheless, several of the most effective PPI methods, including DeepNano-seq, demonstrate suboptimal performance for NAI prediction due to the distinction between NAI and PPI at both the pattern and data levels. Therefore, we organize NAI data from the public database for dedicated NAI modelling. Furthermore, we enhance the prediction pipeline of DeepNano-seq by directing the model’s attention to the antigen-binding sites through a prompt-based approach to present the final DeepNano. The comprehensive evaluation demonstrates that DeepNano performs superiorly in NAI prediction and virtual screening of nanobodies. Overall, DeepNano-seq and DeepNano can offer powerful tools for nanobody discovery. Predicting nanobody–antigen interactions is crucial for advancing nanobody development in drug discovery, but it remains a challenging task. Deng et al. propose DeepNano to enhance the prediction of nanobody–antigen interactions, facilitating virtual screening of target nanobodies.
{"title":"Nanobody–antigen interaction prediction with ensemble deep learning and prompt-based protein language models","authors":"Juntao Deng, Miao Gu, Pengyan Zhang, Mingyu Dong, Tao Liu, Yabin Zhang, Min Liu","doi":"10.1038/s42256-024-00940-5","DOIUrl":"10.1038/s42256-024-00940-5","url":null,"abstract":"Nanobodies can provide specific binding to divergent antigens, leading to many promising therapeutic and detection applications in recent years. Traditional technologies of nanobody discovery based on alpaca immunization and phage display are very time-consuming and labour-intensive. Despite recent progress in the study of nanobodies, developing fast and accurate computational tools for nanobody–antigen interaction (NAI) prediction is urgently desirable. Here we propose an ensemble deep learning-based framework named DeepNano-seq to predict general protein–protein interaction (PPI) containing NAI from pure sequence information. Quantitative comparison results show that DeepNano-seq possesses the best cross-species generalization ability among existing PPI algorithms. Nevertheless, several of the most effective PPI methods, including DeepNano-seq, demonstrate suboptimal performance for NAI prediction due to the distinction between NAI and PPI at both the pattern and data levels. Therefore, we organize NAI data from the public database for dedicated NAI modelling. Furthermore, we enhance the prediction pipeline of DeepNano-seq by directing the model’s attention to the antigen-binding sites through a prompt-based approach to present the final DeepNano. The comprehensive evaluation demonstrates that DeepNano performs superiorly in NAI prediction and virtual screening of nanobodies. Overall, DeepNano-seq and DeepNano can offer powerful tools for nanobody discovery. Predicting nanobody–antigen interactions is crucial for advancing nanobody development in drug discovery, but it remains a challenging task. Deng et al. propose DeepNano to enhance the prediction of nanobody–antigen interactions, facilitating virtual screening of target nanobodies.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1594-1604"},"PeriodicalIF":18.8,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777173","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Robots, integrated into biological systems as sociable partners, offer promising advancement in the mechanistic understanding of social behaviours. These biohybrid systems bring controllability to help elucidate the underlying biological intelligence previously inaccessible through traditional techniques. However, state-of-the-art interactive robots still struggle to convey multilevel, heterogeneous information within biological systems, making it challenging to mediate the complex interaction process effectively. Here we propose an autonomous, interactive rat-like robot that can engage with freely behaving rats by learning from the anatomical structure, dynamic motions and social interaction of rats. Imitation learning based on animal demonstration enables the robot with subtle templates of social behaviour, allowing it to capture the attention of rats and significantly arouse their interest. It also integrates visual perception, target tracking and behavioural decisions to substantially augment the interaction efficiency. We demonstrate that the robot can interact with rats for a continuous half-hour. Moreover, the robot can modulate the emotional states of rats through different interaction patterns during robot–rat social interaction. These results attest that the proposed interactive robot, with its long-term and repetitive interaction capabilities, overcomes the limitations of natural social interaction within biological systems. Such biohybrid systems capable of modulating the internal states of organisms may open the door to comprehending the ‘social’ interactions between humans and artificial intelligence. Interactive robots can be used to study animal social behaviour. Imitation learning can be used to enable a rat-like robot to learn subtle templates of social behaviour, demonstrating that it can modulate the emotional states of rats through varied interaction patterns.
{"title":"Modulating emotional states of rats through a rat-like robot with learned interaction patterns","authors":"Guanglu Jia, Zhe Chen, Yulai Zhang, Zhenshan Bing, Zhenzhen Quan, Xuechao Chen, Alois Knoll, Qiang Huang, Qing Shi","doi":"10.1038/s42256-024-00939-y","DOIUrl":"10.1038/s42256-024-00939-y","url":null,"abstract":"Robots, integrated into biological systems as sociable partners, offer promising advancement in the mechanistic understanding of social behaviours. These biohybrid systems bring controllability to help elucidate the underlying biological intelligence previously inaccessible through traditional techniques. However, state-of-the-art interactive robots still struggle to convey multilevel, heterogeneous information within biological systems, making it challenging to mediate the complex interaction process effectively. Here we propose an autonomous, interactive rat-like robot that can engage with freely behaving rats by learning from the anatomical structure, dynamic motions and social interaction of rats. Imitation learning based on animal demonstration enables the robot with subtle templates of social behaviour, allowing it to capture the attention of rats and significantly arouse their interest. It also integrates visual perception, target tracking and behavioural decisions to substantially augment the interaction efficiency. We demonstrate that the robot can interact with rats for a continuous half-hour. Moreover, the robot can modulate the emotional states of rats through different interaction patterns during robot–rat social interaction. These results attest that the proposed interactive robot, with its long-term and repetitive interaction capabilities, overcomes the limitations of natural social interaction within biological systems. Such biohybrid systems capable of modulating the internal states of organisms may open the door to comprehending the ‘social’ interactions between humans and artificial intelligence. Interactive robots can be used to study animal social behaviour. Imitation learning can be used to enable a rat-like robot to learn subtle templates of social behaviour, demonstrating that it can modulate the emotional states of rats through varied interaction patterns.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1580-1593"},"PeriodicalIF":18.8,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-05DOI: 10.1038/s42256-024-00953-0
Pascal Wallisch, Ibrahim Sheikh
{"title":"Towards a personalized AI assistant to learn machine learning","authors":"Pascal Wallisch, Ibrahim Sheikh","doi":"10.1038/s42256-024-00953-0","DOIUrl":"10.1038/s42256-024-00953-0","url":null,"abstract":"","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1413-1414"},"PeriodicalIF":18.8,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-05DOI: 10.1038/s42256-024-00959-8
Thomas Schmickl
Social learning is a powerful strategy of adaptation in nature. An interactive rat-like robot that engages in imitation learning with a freely behaving rat opens a way to study social behaviours.
{"title":"Memetic robots","authors":"Thomas Schmickl","doi":"10.1038/s42256-024-00959-8","DOIUrl":"10.1038/s42256-024-00959-8","url":null,"abstract":"Social learning is a powerful strategy of adaptation in nature. An interactive rat-like robot that engages in imitation learning with a freely behaving rat opens a way to study social behaviours.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1427-1428"},"PeriodicalIF":18.8,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142777168","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-04DOI: 10.1038/s42256-024-00957-w
Smita Deb, Partha Sharathi Dutta
A deep learning-based method shows promise in issuing early warnings of rate-induced tipping, of particular interest in anticipating effects due to anthropogenic climate change.
{"title":"Deep learning at the forefront of detecting tipping points","authors":"Smita Deb, Partha Sharathi Dutta","doi":"10.1038/s42256-024-00957-w","DOIUrl":"10.1038/s42256-024-00957-w","url":null,"abstract":"A deep learning-based method shows promise in issuing early warnings of rate-induced tipping, of particular interest in anticipating effects due to anthropogenic climate change.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1433-1434"},"PeriodicalIF":18.8,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142763063","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-02DOI: 10.1038/s42256-024-00936-1
Tianang Leng, Cesar de la Fuente-Nunez
Recurrent neural networks are efficient and capable agents for discovering new peptides with strong self-organizing capabilities.
递归神经网络具有较强的自组织能力，是发现新多肽的有效工具。
{"title":"AI in biomaterials discovery: generating self-assembling peptides with resource-efficient deep learning","authors":"Tianang Leng, Cesar de la Fuente-Nunez","doi":"10.1038/s42256-024-00936-1","DOIUrl":"10.1038/s42256-024-00936-1","url":null,"abstract":"Recurrent neural networks are efficient and capable agents for discovering new peptides with strong self-organizing capabilities.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1429-1430"},"PeriodicalIF":18.8,"publicationDate":"2024-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142758167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-29DOI: 10.1038/s42256-024-00947-y
Mohammad Hosseini, Christopher R. Donohue
{"title":"A plea for caution and guidance about using AI in genomics","authors":"Mohammad Hosseini, Christopher R. Donohue","doi":"10.1038/s42256-024-00947-y","DOIUrl":"10.1038/s42256-024-00947-y","url":null,"abstract":"","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1409-1410"},"PeriodicalIF":18.8,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142753769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-11-28DOI: 10.1038/s42256-024-00937-0
Yu Huang, Sebastian Bathiany, Peter Ashwin, Niklas Boers
Nonlinear dynamical systems exposed to changing forcing values can exhibit catastrophic transitions between distinct states. The phenomenon of critical slowing down can help anticipate such transitions if caused by a bifurcation and if the change in forcing is slow compared with the system’s internal timescale. However, in many real-world situations, these assumptions are not met and transitions can be triggered because the forcing exceeds a critical rate. For instance, the rapid pace of anthropogenic climate change compared with the internal timescales of key Earth system components, like polar ice sheets or the Atlantic Meridional Overturning Circulation, poses significant risk of rate-induced tipping. Moreover, random perturbations may cause some trajectories to cross an unstable boundary whereas others do not—even under the same forcing. Critical-slowing-down-based indicators generally cannot distinguish these cases of noise-induced tipping from no tipping. This severely limits our ability to assess the tipping risks and to predict individual trajectories. To address this, we make the first attempt to develop a deep learning framework predicting the transition probabilities of dynamical systems ahead of rate-induced transitions. Our method issues early warnings, as demonstrated on three prototypical systems for rate-induced tipping subjected to time-varying equilibrium drift and noise perturbations. Exploiting explainable artificial intelligence methods, our framework captures the fingerprints for the early detection of rate-induced tipping, even with long lead times. Our findings demonstrate the predictability of rate-induced and noise-induced tipping, advancing our ability to determine safe operating spaces for a broader class of dynamical systems than possible so far. Rate- and noise-induced transitions pose key tipping risks for ecosystems and climate subsystems, yet no predictive theory existed before. This study introduces deep learning as an effective prediction tool for these tipping events.
{"title":"Deep learning for predicting rate-induced tipping","authors":"Yu Huang, Sebastian Bathiany, Peter Ashwin, Niklas Boers","doi":"10.1038/s42256-024-00937-0","DOIUrl":"10.1038/s42256-024-00937-0","url":null,"abstract":"Nonlinear dynamical systems exposed to changing forcing values can exhibit catastrophic transitions between distinct states. The phenomenon of critical slowing down can help anticipate such transitions if caused by a bifurcation and if the change in forcing is slow compared with the system’s internal timescale. However, in many real-world situations, these assumptions are not met and transitions can be triggered because the forcing exceeds a critical rate. For instance, the rapid pace of anthropogenic climate change compared with the internal timescales of key Earth system components, like polar ice sheets or the Atlantic Meridional Overturning Circulation, poses significant risk of rate-induced tipping. Moreover, random perturbations may cause some trajectories to cross an unstable boundary whereas others do not—even under the same forcing. Critical-slowing-down-based indicators generally cannot distinguish these cases of noise-induced tipping from no tipping. This severely limits our ability to assess the tipping risks and to predict individual trajectories. To address this, we make the first attempt to develop a deep learning framework predicting the transition probabilities of dynamical systems ahead of rate-induced transitions. Our method issues early warnings, as demonstrated on three prototypical systems for rate-induced tipping subjected to time-varying equilibrium drift and noise perturbations. Exploiting explainable artificial intelligence methods, our framework captures the fingerprints for the early detection of rate-induced tipping, even with long lead times. Our findings demonstrate the predictability of rate-induced and noise-induced tipping, advancing our ability to determine safe operating spaces for a broader class of dynamical systems than possible so far. Rate- and noise-induced transitions pose key tipping risks for ecosystems and climate subsystems, yet no predictive theory existed before. This study introduces deep learning as an effective prediction tool for these tipping events.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1556-1565"},"PeriodicalIF":18.8,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-024-00937-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142753770","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：