Nature Machine Intelligence最新文献_第2页

Deeper evaluation of a single-cell foundation model

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-12 DOI: 10.1038/s42256-024-00949-w

Rebecca Boiarsky, Nalini M. Singh, Alejandro Buendia, Ava P. Amini, Gad Getz, David Sontag

引用次数: 0

Successful implementation of the EU AI Act requires interdisciplinary efforts

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-10 DOI: 10.1038/s42256-024-00954-z

Christian Montag, Michèle Finck

引用次数: 0

An interpretable RNA foundation model for exploring functional RNA motifs in plants

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-09 DOI: 10.1038/s42256-024-00946-z

Haopeng Yu, Heng Yang, Wenqing Sun, Zongyun Yan, Xiaofei Yang, Huakun Zhang, Yiliang Ding, Ke Li

{"title":"An interpretable RNA foundation model for exploring functional RNA motifs in plants","authors":"Haopeng Yu, Heng Yang, Wenqing Sun, Zongyun Yan, Xiaofei Yang, Huakun Zhang, Yiliang Ding, Ke Li","doi":"10.1038/s42256-024-00946-z","DOIUrl":"10.1038/s42256-024-00946-z","url":null,"abstract":"The complex ‘language’ of plant RNA encodes a vast array of biological regulatory elements that orchestrate crucial aspects of plant growth, development and adaptation to environmental stresses. Recent advancements in foundation models (FMs) have demonstrated their unprecedented potential to decipher complex ‘language’ in biology. In this study, we introduced PlantRNA-FM, a high-performance and interpretable RNA FM specifically designed for plants. PlantRNA-FM was pretrained on an extensive dataset, integrating RNA sequences and RNA structure information from 1,124 distinct plant species. PlantRNA-FM exhibits superior performance in plant-specific downstream tasks. PlantRNA-FM achieves an F1 score of 0.974 for genic region annotation, whereas the current best-performing model achieves 0.639. Our PlantRNA-FM is empowered by our interpretable framework that facilitates the identification of biologically functional RNA sequence and structure motifs, including both RNA secondary and tertiary structure motifs across transcriptomes. Through experimental validations, we revealed translation-associated RNA motifs in plants. Our PlantRNA-FM also highlighted the importance of the position information of these functional RNA motifs in genic regions. Taken together, our PlantRNA-FM facilitates the exploration of functional RNA motifs across the complexity of transcriptomes, empowering plant scientists with capabilities for programming RNA codes in plants. Approaches are needed to explore regulatory RNA motifs in plants. An interpretable RNA foundation model is developed, trained on thousands of plant transcriptomes, which achieves superior performance in plant RNA biology tasks and enables the discovery of functional RNA sequence and structure motifs across transcriptomes.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1616-1625"},"PeriodicalIF":18.8,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-024-00946-z.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142793852","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}

引用次数: 0

Evaluating generalizability of artificial intelligence models for molecular datasets

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-06 DOI: 10.1038/s42256-024-00931-6

Yasha Ektefaie, Andrew Shen, Daria Bykova, Maximillian G. Marin, Marinka Zitnik, Maha Farhat

{"title":"Evaluating generalizability of artificial intelligence models for molecular datasets","authors":"Yasha Ektefaie, Andrew Shen, Daria Bykova, Maximillian G. Marin, Marinka Zitnik, Maha Farhat","doi":"10.1038/s42256-024-00931-6","DOIUrl":"10.1038/s42256-024-00931-6","url":null,"abstract":"Deep learning has made rapid advances in modelling molecular sequencing data. Despite achieving high performance on benchmarks, it remains unclear to what extent deep learning models learn general principles and generalize to previously unseen sequences. Benchmarks traditionally interrogate model generalizability by generating metadata- or sequence similarity-based train and test splits of input data before assessing model performance. Here we show that this approach mischaracterizes model generalizability by failing to consider the full spectrum of cross-split overlap, that is, similarity between train and test splits. We introduce SPECTRA, the spectral framework for model evaluation. Given a model and a dataset, SPECTRA plots model performance as a function of decreasing cross-split overlap and reports the area under this curve as a measure of generalizability. We use SPECTRA with 18 sequencing datasets and phenotypes ranging from antibiotic resistance in tuberculosis to protein–ligand binding and evaluate the generalizability of 19 state-of-the-art deep learning models, including large language models, graph neural networks, diffusion models and convolutional neural networks. We show that sequence similarity- and metadata-based splits provide an incomplete assessment of model generalizability. Using SPECTRA, we find that as cross-split overlap decreases, deep learning models consistently show reduced performance, varying by task and model. Although no model consistently achieved the highest performance across all tasks, deep learning models can, in some cases, generalize to previously unseen sequences on specific tasks. SPECTRA advances our understanding of how foundation models generalize in biological applications. Ektefaie and colleagues introduce the spectral framework for models evaluation (SPECTRA) to measure the generalizability of machine learning models for molecular sequences.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 12","pages":"1512-1524"},"PeriodicalIF":18.8,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142782801","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}

引用次数: 0

Learning spatiotemporal dynamics with a pretrained generative model

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-06 DOI: 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

{"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}

引用次数: 0

LLM-based agentic systems in medicine and healthcare

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-05 DOI: 10.1038/s42256-024-00944-1

Jianing Qiu, Kyle Lam, Guohao Li, Amish Acharya, Tien Yin Wong, Ara Darzi, Wu Yuan, Eric J. Topol

引用次数: 0

Nanobody–antigen interaction prediction with ensemble deep learning and prompt-based protein language models

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-05 DOI: 10.1038/s42256-024-00940-5

Juntao Deng, Miao Gu, Pengyan Zhang, Mingyu Dong, Tao Liu, Yabin Zhang, Min Liu

{"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}

引用次数: 0

Modulating emotional states of rats through a rat-like robot with learned interaction patterns

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-05 DOI: 10.1038/s42256-024-00939-y

Guanglu Jia, Zhe Chen, Yulai Zhang, Zhenshan Bing, Zhenzhen Quan, Xuechao Chen, Alois Knoll, Qiang Huang, Qing Shi

{"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}

引用次数: 0

Towards a personalized AI assistant to learn machine learning

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-05 DOI: 10.1038/s42256-024-00953-0

Pascal Wallisch, Ibrahim Sheikh

引用次数: 0

Memetic robots

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2024-12-05 DOI: 10.1038/s42256-024-00959-8

Thomas Schmickl

引用次数: 0