Nature Machine Intelligence最新文献_第3页

A text-guided protein design framework 一个文本引导的蛋白质设计框架

IF 23.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-27 DOI: 10.1038/s42256-025-01011-z

Shengchao Liu, Yanjing Li, Zhuoxinran Li, Anthony Gitter, Yutao Zhu, Jiarui Lu, Zhao Xu, Weili Nie, Arvind Ramanathan, Chaowei Xiao, Jian Tang, Hongyu Guo, Anima Anandkumar

{"title":"A text-guided protein design framework","authors":"Shengchao Liu, Yanjing Li, Zhuoxinran Li, Anthony Gitter, Yutao Zhu, Jiarui Lu, Zhao Xu, Weili Nie, Arvind Ramanathan, Chaowei Xiao, Jian Tang, Hongyu Guo, Anima Anandkumar","doi":"10.1038/s42256-025-01011-z","DOIUrl":"https://doi.org/10.1038/s42256-025-01011-z","url":null,"abstract":"Current AI-assisted protein design utilizes mainly protein sequential and structural information. Meanwhile, there exists tremendous knowledge curated by humans in text format describing proteins’ high-level functionalities, yet whether the incorporation of such text data can help in protein design tasks has not been explored. To bridge this gap, we propose ProteinDT, a multimodal framework that leverages textual descriptions for protein design. ProteinDT consists of three consecutive steps: ProteinCLAP, which aligns the representation of two modalities, a facilitator that generates the protein representation from the text modality and a decoder that creates the protein sequences from the representation. To train ProteinDT, we construct a large dataset, SwissProtCLAP, with 441,000 text and protein pairs. We quantitatively verify the effectiveness of ProteinDT on three challenging tasks: (1) over 90% accuracy for text-guided protein generation; (2) best hit ratio on 12 zero-shot text-guided protein editing tasks; (3) superior performance on four out of six protein property prediction benchmarks.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"35 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143712763","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

A disease-specific language model for variant pathogenicity in cardiac and regulatory genomics 心脏和调控基因组学中变异致病性的疾病特异性语言模型

IF 23.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-24 DOI: 10.1038/s42256-025-01016-8

Huixin Zhan, Jason H. Moore, Zijun Zhang

{"title":"A disease-specific language model for variant pathogenicity in cardiac and regulatory genomics","authors":"Huixin Zhan, Jason H. Moore, Zijun Zhang","doi":"10.1038/s42256-025-01016-8","DOIUrl":"https://doi.org/10.1038/s42256-025-01016-8","url":null,"abstract":"Clinical variant classification of pathogenic versus benign genetic variants remains a challenge in genetics. Current genomic foundation models have enhanced variant effect prediction (VEP) accuracy through weakly supervised or unsupervised training, yet these models lack disease specificity. Here, to address this, we propose DYNA (disease-specificity fine-tuning via a Siamese neural network), broadly applicable to all genomic foundation models for more effective VEPs in disease contexts. We applied DYNA to the coding VEP in cardiovascular diseases and the non-coding VEP of RNA splicing regulation. These two tasks cover a wide range of specific disease–gene relationships and disease-causing regulatory mechanisms; therefore, their performance will inform the general utility of DYNA. In both cases, DYNA fine-tunes various pretrained genomic foundation models on small rare-variant sets. The DYNA fine-tuned models show superior performance in held-out rare-variant test sets and are further replicated in large, clinically relevant variant annotations in ClinVar. Importantly, we observed that different genomic foundation models excel at different downstream VEP tasks, necessitating a universal tool such as DYNA to fully harness the power of genomic foundation models. Thus, DYNA offers a potent disease-specific VEP method for clinical variant interpretation.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"59 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143678046","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

Transparency (in training data) is what we want （训练数据的）透明度是我们想要的

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-24 DOI: 10.1038/s42256-025-01023-9

引用次数: 0

Materiality and risk in the age of pervasive AI sensors 无处不在的人工智能传感器时代的物质性和风险

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-20 DOI: 10.1038/s42256-025-01017-7

Mona Sloane, Emanuel Moss, Susan Kennedy, Matthew Stewart, Pete Warden, Brian Plancher, Vijay Janapa Reddi

{"title":"Materiality and risk in the age of pervasive AI sensors","authors":"Mona Sloane, Emanuel Moss, Susan Kennedy, Matthew Stewart, Pete Warden, Brian Plancher, Vijay Janapa Reddi","doi":"10.1038/s42256-025-01017-7","DOIUrl":"10.1038/s42256-025-01017-7","url":null,"abstract":"Artificial intelligence (AI) systems connected to sensor-laden devices are becoming pervasive, which has notable implications for a range of AI risks, including to privacy, the environment, autonomy and more. There is therefore a growing need for increased accountability around the responsible development and deployment of these technologies. Here we highlight the dimensions of risk associated with AI systems that arise from the material affordances of sensors and their underlying calculative models. We propose a sensor-sensitive framework for diagnosing these risks, complementing existing approaches such as the US National Institute of Standards and Technology AI Risk Management Framework and the European Union AI Act, and discuss its implementation. We conclude by advocating for increased attention to the materiality of algorithmic systems, and of on-device AI sensors in particular, and highlight the need for development of a sensor design paradigm that empowers users and communities and leads to a future of increased fairness, accountability and transparency. Sloane and colleagues review emerging new dimensions of risks associated with materiality and AI algorithms run on pervasive sensors.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 3","pages":"334-345"},"PeriodicalIF":18.8,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143661528","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

Quantum circuit optimization with AlphaTensor 基于alphatsensor的量子电路优化

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-20 DOI: 10.1038/s42256-025-01001-1

Francisco J. R. Ruiz, Tuomas Laakkonen, Johannes Bausch, Matej Balog, Mohammadamin Barekatain, Francisco J. H. Heras, Alexander Novikov, Nathan Fitzpatrick, Bernardino Romera-Paredes, John van de Wetering, Alhussein Fawzi, Konstantinos Meichanetzidis, Pushmeet Kohli

{"title":"Quantum circuit optimization with AlphaTensor","authors":"Francisco J. R. Ruiz, Tuomas Laakkonen, Johannes Bausch, Matej Balog, Mohammadamin Barekatain, Francisco J. H. Heras, Alexander Novikov, Nathan Fitzpatrick, Bernardino Romera-Paredes, John van de Wetering, Alhussein Fawzi, Konstantinos Meichanetzidis, Pushmeet Kohli","doi":"10.1038/s42256-025-01001-1","DOIUrl":"10.1038/s42256-025-01001-1","url":null,"abstract":"A key challenge in realizing fault-tolerant quantum computers is circuit optimization. Focusing on the most expensive gates in fault-tolerant quantum computation (namely, the T gates), we address the problem of T-count optimization, that is, minimizing the number of T gates needed to implement a given circuit. To achieve this, we develop AlphaTensor-Quantum, a method based on deep reinforcement learning that exploits the relationship between optimizing the T-count and tensor decomposition. Unlike existing methods for T-count optimization, AlphaTensor-Quantum can incorporate domain-specific knowledge about quantum computation and leverage gadgets, which substantially reduces the T-count of the optimized circuits. AlphaTensor-Quantum outperforms the existing methods for T-count optimization on a set of arithmetic benchmarks (even when compared without using gadgets). Remarkably, it discovers an efficient algorithm akin to Karatsuba’s method for multiplication in finite fields. AlphaTensor-Quantum also finds the best human-designed solutions for relevant arithmetic computations used in Shor’s algorithm and for quantum chemistry simulation, thus demonstrating that it can save hundreds of hours of research by optimizing relevant quantum circuits in a fully automated way. Ruiz and colleagues introduce AlphaTensor-Quantum, a deep reinforcement learning method for optimizing quantum circuits. It outperforms existing methods and is capable of finding the best human-designed solutions for relevant quantum computations in a fully automated way.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 3","pages":"374-385"},"PeriodicalIF":18.8,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-025-01001-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143661217","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

Active exploration and reconstruction of vascular networks using microrobot swarms 利用微机器人群对血管网络进行主动探索和重建

IF 23.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-19 DOI: 10.1038/s42256-025-01012-y

Xingzhou Du, Yibin Wang, Junhui Law, Kaiwen Fang, Hui Chen, Yuezhen Liu, Jiangfan Yu

{"title":"Active exploration and reconstruction of vascular networks using microrobot swarms","authors":"Xingzhou Du, Yibin Wang, Junhui Law, Kaiwen Fang, Hui Chen, Yuezhen Liu, Jiangfan Yu","doi":"10.1038/s42256-025-01012-y","DOIUrl":"https://doi.org/10.1038/s42256-025-01012-y","url":null,"abstract":"Angiography is essential in interventional operations to image the vascular network. Passive contrast agents applied in angiography highly rely on the flow direction, making the imaging of upstream regions and embolic branches challenging. Active imaging is demanded for the accurate localization of blockages and lesions in vascular networks. Here an active exploration and reconstruction strategy is proposed, enabling full imaging of three-dimensional (3D) vascular networks with flow and blockage. The strategy implements magnetic particle swarms as active agents, which can be guided on demand towards the desired directions. An image processing unit is developed to capture the 3D position of the swarm inside the vessel. A simultaneous mapping and exploration sequence is proposed to realize the exploration, and the entire structure of the 3D vascular network is reconstructed after obtaining the position data. The proposed strategy is validated in vascular networks with different structures and conditions, and it enables the thorough exploration and reconstruction of regions that cannot be accessed by passive contrast agents. This strategy is promising in locating stenoses, thrombi and fistulae in vascular systems.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143653956","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

Embodied large language models enable robots to complete complex tasks in unpredictable environments 嵌入的大型语言模型使机器人能够在不可预测的环境中完成复杂的任务

IF 23.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-19 DOI: 10.1038/s42256-025-01005-x

Ruaridh Mon-Williams, Gen Li, Ran Long, Wenqian Du, Christopher G. Lucas

{"title":"Embodied large language models enable robots to complete complex tasks in unpredictable environments","authors":"Ruaridh Mon-Williams, Gen Li, Ran Long, Wenqian Du, Christopher G. Lucas","doi":"10.1038/s42256-025-01005-x","DOIUrl":"https://doi.org/10.1038/s42256-025-01005-x","url":null,"abstract":"Completing complex tasks in unpredictable settings challenges robotic systems, requiring a step change in machine intelligence. Sensorimotor abilities are considered integral to human intelligence. Thus, biologically inspired machine intelligence might usefully combine artificial intelligence with robotic sensorimotor capabilities. Here we report an embodied large-language-model-enabled robot (ELLMER) framework, utilizing GPT-4 and a retrieval-augmented generation infrastructure, to enable robots to complete long-horizon tasks in unpredictable settings. The method extracts contextually relevant examples from a knowledge base, producing action plans that incorporate force and visual feedback and enabling adaptation to changing conditions. We tested ELLMER on a robot tasked with coffee making and plate decoration; these tasks consist of a sequence of sub-tasks from drawer opening to pouring, each benefiting from distinct feedback types and methods. We show that the ELLMER framework allows the robot to complete the tasks. This demonstration marks progress towards scalable, efficient and ‘intelligent robots’ able to complete complex tasks in uncertain environments.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"28 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143653955","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

Explainable AI reveals Clever Hans effects in unsupervised learning models 可解释的人工智能揭示了无监督学习模型中的聪明汉斯效应

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-17 DOI: 10.1038/s42256-025-01000-2

Jacob Kauffmann, Jonas Dippel, Lukas Ruff, Wojciech Samek, Klaus-Robert Müller, Grégoire Montavon

{"title":"Explainable AI reveals Clever Hans effects in unsupervised learning models","authors":"Jacob Kauffmann, Jonas Dippel, Lukas Ruff, Wojciech Samek, Klaus-Robert Müller, Grégoire Montavon","doi":"10.1038/s42256-025-01000-2","DOIUrl":"10.1038/s42256-025-01000-2","url":null,"abstract":"Unsupervised learning has become an essential building block of artifical intelligence systems. The representations it produces, for example, in foundation models, are critical to a wide variety of downstream applications. It is therefore important to carefully examine unsupervised models to ensure not only that they produce accurate predictions on the available data but also that these accurate predictions do not arise from a Clever Hans (CH) effect. Here, using specially developed explainable artifical intelligence techniques and applying them to popular representation learning and anomaly detection models for image data, we show that CH effects are widespread in unsupervised learning. In particular, through use cases on medical and industrial inspection data, we demonstrate that CH effects systematically lead to significant performance loss of downstream models under plausible dataset shifts or reweighting of different data subgroups. Our empirical findings are enriched by theoretical insights, which point to inductive biases in the unsupervised learning machine as a primary source of CH effects. Overall, our work sheds light on unexplored risks associated with practical applications of unsupervised learning and suggests ways to systematically mitigate CH effects, thereby making unsupervised learning more robust. Building on recent explainable AI techniques, this Article highlights the pervasiveness of Clever Hans effects in unsupervised learning and the substantial risks associated with these effects in terms of the prediction accuracy on new data.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 3","pages":"412-422"},"PeriodicalIF":18.8,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-025-01000-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143635720","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

Towards unveiling sensitive and decisive patterns in explainable AI with a case study in geometric deep learning 以几何深度学习为例，揭示可解释人工智能中敏感和决定性的模式

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-17 DOI: 10.1038/s42256-025-00998-9

Jiajun Zhu, Siqi Miao, Rex Ying, Pan Li

{"title":"Towards unveiling sensitive and decisive patterns in explainable AI with a case study in geometric deep learning","authors":"Jiajun Zhu, Siqi Miao, Rex Ying, Pan Li","doi":"10.1038/s42256-025-00998-9","DOIUrl":"10.1038/s42256-025-00998-9","url":null,"abstract":"The interpretability of machine learning models has gained increasing attention, particularly in scientific domains where high precision and accountability are crucial. This research focuses on distinguishing between two critical data patterns—sensitive patterns (model related) and decisive patterns (task related)—which are commonly used as model interpretations but often lead to confusion. Specifically, this study compares the effectiveness of two main streams of interpretation methods: post-hoc methods and self-interpretable methods, in detecting these patterns. Recently, geometric deep learning (GDL) has shown superior predictive performance in various scientific applications, creating an urgent need for principled interpretation methods. Here, therefore, we conduct our study using several representative GDL applications as case studies. We evaluate 13 interpretation methods applied to 3 major GDL backbone models, using 4 scientific datasets to assess how well these methods identify sensitive and decisive patterns. Our findings indicate that post-hoc methods tend to provide interpretations better aligned with sensitive patterns, whereas certain self-interpretable methods exhibit strong and stable performance in detecting decisive patterns. Moreover, our study offers valuable insights into improving the reliability of these interpretation methods. For example, ensembling post-hoc interpretations from multiple models trained on the same task can effectively uncover the task’s decisive patterns. Interpreting decisions made by machine learning systems remains difficult. Here Zhu et al. test interpretability methods on their ability to identify model-related and task-related patterns.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 3","pages":"471-483"},"PeriodicalIF":18.8,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143635717","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

Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity 基于协同的机器人四足动物利用被动的自然智能和行为多样性

IF 18.8 1区计算机科学

Nature Machine Intelligence Pub Date : 2025-03-17 DOI: 10.1038/s42256-025-00988-x

Francesco Stella, Mickaël M. Achkar, Cosimo Della Santina, Josie Hughes

{"title":"Synergy-based robotic quadruped leveraging passivity for natural intelligence and behavioural diversity","authors":"Francesco Stella, Mickaël M. Achkar, Cosimo Della Santina, Josie Hughes","doi":"10.1038/s42256-025-00988-x","DOIUrl":"10.1038/s42256-025-00988-x","url":null,"abstract":"Quadrupedal animals show remarkable capabilities in traversing diverse terrains and display a range of behaviours and gait patterns. Achieving similar performance by exploiting the natural dynamics of the system is a key goal for robotics researchers. Here we show a bioinspired approach to the design of quadrupeds that seeks to exploit the body and the passive properties of the robot while maintaining active controllability on the system through minimal actuation. Utilizing an end-to-end computational design pipeline, neuromechanical couplings recorded in biological quadrupeds are translated into motor synergies, allowing minimal actuation to control the full structure via multijoint compliant mechanical couplings. Using this approach, we develop PAWS, a passive automata with synergies. By leveraging the principles of motor synergies, the design incorporates variable stiffness, anatomical insights and self-organization to simplify control while maximizing its capabilities. The resulting synergy-based quadruped requires only four actuators and exhibits emergent, animal-like dynamical responses, including passive robustness to environmental perturbations and a wide range of actuated behaviours. The finding contributes to the development of machine physical intelligence and provides robots with more efficient and natural-looking robotic locomotion by combining synergistic actuation, compliant body properties and embodied compensatory strategies. Stella, Achkar and colleagues present a bio-inspired quadruped robot that uses passive dynamics, motor synergies, variable stiffness and self-organization to achieve robust, adaptive, animal-like movement with just four actuators.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 3","pages":"386-399"},"PeriodicalIF":18.8,"publicationDate":"2025-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s42256-025-00988-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143635721","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