Nature Machine Intelligence最新文献

{"title":"Improving diffusion-based protein backbone generation with global-geometry-aware latent encoding","authors":"Yuyang Zhang, Yuhang Liu, Zinnia Ma, Min Li, Chunfu Xu, Haipeng Gong","doi":"10.1038/s42256-025-01059-x","DOIUrl":"https://doi.org/10.1038/s42256-025-01059-x","url":null,"abstract":"<p>The global structural properties of a protein, such as shape, fold and topology, strongly affect its function. Although recent breakthroughs in diffusion-based generative models have greatly advanced de novo protein design, particularly in generating diverse and realistic structures, it remains challenging to design proteins of specific geometries without residue-level control over the topological details. A more practical, top-down approach is needed for prescribing the overall geometric arrangements of secondary structure elements in the generated protein structures. In response, we propose TopoDiff, an unsupervised framework that learns and exploits a global-geometry-aware latent representation, enabling both unconditional and controllable diffusion-based protein generation. Trained on the Protein Data Bank and CATH datasets, the structure encoder embeds protein global geometries into a 32-dimensional latent space, from which latent codes sampled by the latent sampler serve as informative conditions for the diffusion-based backbone decoder. In benchmarks against existing baselines, TopoDiff demonstrates comparable performance on established metrics including designability, diversity and novelty, as well as markedly improves coverage over the fold types of natural proteins in the CATH dataset. Moreover, latent conditioning enables versatile manipulations at the global-geometry level to control the generated protein structures, through which we derived a number of novel folds of mainly beta proteins with comprehensive experimental validation.</p>","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"232 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144311696","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}

{"title":"Generalized biological foundation model with unified nucleic acid and protein language","authors":"Yong He, Pan Fang, Yongtao Shan, Yuanfei Pan, Yanhong Wei, Yichang Chen, Yihao Chen, Yi Liu, Zhenyu Zeng, Zhan Zhou, Feng Zhu, Edward C. Holmes, Jieping Ye, Jun Li, Yuelong Shu, Mang Shi, Zhaorong Li","doi":"10.1038/s42256-025-01044-4","DOIUrl":"https://doi.org/10.1038/s42256-025-01044-4","url":null,"abstract":"<p>The language of biology, encoded in DNA, RNA and proteins, forms the foundation of life but remains challenging to decode owing to its complexity. Traditional computational methods often struggle to integrate information across these molecules, limiting a comprehensive understanding of biological systems. Advances in natural language processing with pre-trained models offer possibilities for interpreting biological language. Here we introduce LucaOne, a pre-trained foundation model trained on nucleic acid and protein sequences from 169,861 species. Through large-scale data integration and semi-supervised learning, LucaOne shows an understanding of key biological principles, such as DNA–protein translation. Using few-shot learning, it effectively comprehends the central dogma of molecular biology and performs competitively on tasks involving DNA, RNA or protein inputs. Our results highlight the potential of unified foundation models to address complex biological questions, providing an adaptable framework for bioinformatics research and enhancing the interpretation of life’s complexity.</p>","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"48 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144311695","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}

{"title":"Next-generation phenotyping of inherited retinal diseases from multimodal imaging with Eye2Gene","authors":"Nikolas Pontikos, William A. Woof, Siying Lin, Biraja Ghoshal, Bernardo S. Mendes, Advaith Veturi, Quang Nguyen, Behnam Javanmardi, Michalis Georgiou, Alexander Hustinx, Miguel A. Ibarra-Arellano, Ismail Moghul, Yichen Liu, Kristina Pfau, Maximilian Pfau, Mital Shah, Jing Yu, Saoud Al-Khuzaei, Siegfried K. Wagner, Malena Daich Varela, Thales Antonio Cabral de Guimarães, Sagnik Sen, Gunjan Naik, Dayyanah Sumodhee, Dun Jack Fu, Nathaniel Kabiri, Jennifer Furman, Bart Liefers, Aaron Y. Lee, Samantha R. De Silva, Caio Marques, Fabiana Motta, Yu Fujinami-Yokokawa, Alison J. Hardcastle, Gavin Arno, Birgit Lorenz, Philipp Herrmann, Kaoru Fujinami, Juliana Sallum, Savita Madhusudhan, Susan M. Downes, Frank G. Holz, Konstantinos Balaskas, Andrew R. Webster, Omar A. Mahroo, Peter M. Krawitz, Michel Michaelides","doi":"10.1038/s42256-025-01040-8","DOIUrl":"https://doi.org/10.1038/s42256-025-01040-8","url":null,"abstract":"<p>Rare eye diseases such as inherited retinal diseases (IRDs) are challenging to diagnose genetically. IRDs are typically monogenic disorders and represent a leading cause of blindness in children and working-age adults worldwide. A growing number are now being targeted in clinical trials, with approved treatments increasingly available. However, access requires a genetic diagnosis to be established sufficiently early. Critically, the timely identification of a genetic cause remains challenging. We demonstrate that a deep learning algorithm, Eye2Gene, trained on a large multimodal imaging dataset of individuals with IRDs (<i>n</i> = 2,451) and externally validated on data provided by five different clinical centres, provides better-than-expert-level top-five accuracy of 83.9% for supporting genetic diagnosis for the 63 most common genetic causes. We demonstrate that Eye2Gene’s next-generation phenotyping can increase diagnostic yield by improving screening for IRDs, phenotype-driven variant prioritization and automatic similarity matching in phenotypic space to identify new genes. Eye2Gene is accessible online (app.eye2gene.com) for research purposes.</p>","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"6 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144311697","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}

{"title":"Mask-prior-guided denoising diffusion improves inverse protein folding","authors":"Peizhen Bai, Filip Miljković, Xianyuan Liu, Leonardo De Maria, Rebecca Croasdale-Wood, Owen Rackham, Haiping Lu","doi":"10.1038/s42256-025-01042-6","DOIUrl":"https://doi.org/10.1038/s42256-025-01042-6","url":null,"abstract":"<p>Inverse protein folding generates valid amino acid sequences that can fold into a desired protein structure, with recent deep learning advances showing strong potential and competitive performance. However, challenges remain, such as predicting elements with high structural uncertainty, including disordered regions. To tackle such low-confidence residue prediction, we propose a mask-prior-guided denoising diffusion (MapDiff) framework that accurately captures both structural information and residue interactions for inverse protein folding. MapDiff is a discrete diffusion probabilistic model that iteratively generates amino acid sequences with reduced noise, conditioned on a given protein backbone. To incorporate structural information and residue interactions, we have developed a graph-based denoising network with a mask-prior pretraining strategy. Moreover, in the generative process, we combine the denoising diffusion implicit model with Monte-Carlo dropout to reduce uncertainty. Evaluation on four challenging sequence design benchmarks shows that MapDiff substantially outperforms state-of-the-art methods. Furthermore, the in silico sequences generated by MapDiff closely resemble the physico-chemical and structural characteristics of native proteins across different protein families and architectures.</p>","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"33 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296155","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}

{"title":"Learning vision-based agile flight via differentiable physics","authors":"Yuang Zhang, Yu Hu, Yunlong Song, Danping Zou, Weiyao Lin","doi":"10.1038/s42256-025-01048-0","DOIUrl":"https://doi.org/10.1038/s42256-025-01048-0","url":null,"abstract":"<p>Autonomous aerial robot swarms promise transformative applications, from planetary exploration to search and rescue in complex environments. However, navigating these swarms efficiently in unknown and cluttered spaces without bulky sensors, heavy computation or constant communication between robots remains a major research problem. This paper introduces an end-to-end approach that combines deep learning with first-principles physics through differentiable simulation to enable autonomous navigation by several aerial robots through complex environments at high speed. Our approach directly optimizes a neural network control policy by backpropagating loss gradients through the robot simulation using a simple point-mass physics model. Despite this simplicity, our method excels in both multi-agent and single-agent applications. In multi-agent scenarios, our system demonstrates self-organized behaviour, which enables autonomous coordination without communication or centralized planning. In single-agent scenarios, our system achieved a 90% success rate in navigating through complex unknown environments and demonstrated enhanced robustness compared to previous state-of-the-art approaches. Our system can operate without state estimation and adapt to dynamic obstacles. In real-world forest environments, it navigates at speeds of up to 20 m s⁻¹, doubling the speed of previous imitation-learning-based solutions. Notably, all these capabilities are deployed on a budget-friendly US$21 computer, which costs less than 5% of the GPU-equipped board used in existing systems.</p>","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"26 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296156","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}

{"title":"A new perspective on the simulation of stochastic problems in fluid mechanics with diffusion models","authors":"Luca Guastoni, Ricardo Vinuesa","doi":"10.1038/s42256-025-01060-4","DOIUrl":"https://doi.org/10.1038/s42256-025-01060-4","url":null,"abstract":"Generative deep learning models offer a fundamentally new approach for simulating stochastic processes in turbulent flows.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"43 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144296157","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}

{"title":"Embedding high-resolution touch across robotic hands enables adaptive human-like grasping","authors":"Zihang Zhao, Wanlin Li, Yuyang Li, Tengyu Liu, Boren Li, Meng Wang, Kai Du, Hangxin Liu, Yixin Zhu, Qining Wang, Kaspar Althoefer, Song-Chun Zhu","doi":"10.1038/s42256-025-01053-3","DOIUrl":"https://doi.org/10.1038/s42256-025-01053-3","url":null,"abstract":"<p>Developing robotic hands that adapt to real-world dynamics remains a fundamental challenge in robotics and machine intelligence. Despite notable advances in replicating human-hand kinematics and control algorithms, robotic systems still struggle to match human capabilities in dynamic environments, primarily due to inadequate tactile feedback. To bridge this gap, we present F-TAC Hand, a biomimetic hand featuring high-resolution tactile sensing (0.1-mm spatial resolution) across 70% of its surface area. Through optimized hand design, we overcome traditional challenges in integrating high-resolution tactile sensors while preserving the full range of motion. The hand, powered by our generative algorithm that synthesizes human-like hand configurations, demonstrates robust grasping capabilities in dynamic real-world conditions. Extensive evaluation across 600 real-world trials demonstrates that this tactile-embodied system significantly outperforms non-tactile-informed alternatives in complex manipulation tasks (<i>P</i> &lt; 0.0001). These results provide empirical evidence for the critical role of rich tactile embodiment in developing advanced robotic intelligence, offering promising perspectives on the relationship between physical sensing capabilities and intelligent behaviour.</p>","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"25 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144238245","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}

{"title":"Human-like object concept representations emerge naturally in multimodal large language models","authors":"Changde Du, Kaicheng Fu, Bincheng Wen, Yi Sun, Jie Peng, Wei Wei, Ying Gao, Shengpei Wang, Chuncheng Zhang, Jinpeng Li, Shuang Qiu, Le Chang, Huiguang He","doi":"10.1038/s42256-025-01049-z","DOIUrl":"https://doi.org/10.1038/s42256-025-01049-z","url":null,"abstract":"<p>Understanding how humans conceptualize and categorize natural objects offers critical insights into perception and cognition. With the advent of large language models (LLMs), a key question arises: can these models develop human-like object representations from linguistic and multimodal data? Here we combined behavioural and neuroimaging analyses to explore the relationship between object concept representations in LLMs and human cognition. We collected 4.7 million triplet judgements from LLMs and multimodal LLMs to derive low-dimensional embeddings that capture the similarity structure of 1,854 natural objects. The resulting 66-dimensional embeddings were stable, predictive and exhibited semantic clustering similar to human mental representations. Remarkably, the dimensions underlying these embeddings were interpretable, suggesting that LLMs and multimodal LLMs develop human-like conceptual representations of objects. Further analysis showed strong alignment between model embeddings and neural activity patterns in brain regions such as the extrastriate body area, parahippocampal place area, retrosplenial cortex and fusiform face area. This provides compelling evidence that the object representations in LLMs, although not identical to human ones, share fundamental similarities that reflect key aspects of human conceptual knowledge. Our findings advance the understanding of machine intelligence and inform the development of more human-like artificial cognitive systems.</p>","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"40 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144238243","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}

{"title":"Unregulated emotional risks of AI wellness apps","authors":"Julian De Freitas, I. Glenn Cohen","doi":"10.1038/s42256-025-01051-5","DOIUrl":"https://doi.org/10.1038/s42256-025-01051-5","url":null,"abstract":"We propose that AI-driven wellness apps powered by large language models can foster extreme emotional attachments and dependencies akin to human relationships — posing risks such as ambiguous loss and dysfunctional dependence — that challenge current regulatory frameworks and necessitate safeguards and informed interventions within these platforms.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"59 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144229006","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}

{"title":"A multimodal conversational agent for DNA, RNA and protein tasks","authors":"Bernardo P. de Almeida, Guillaume Richard, Hugo Dalla-Torre, Christopher Blum, Lorenz Hexemer, Priyanka Pandey, Stefan Laurent, Chandana Rajesh, Marie Lopez, Alexandre Laterre, Maren Lang, Uğur Şahin, Karim Beguir, Thomas Pierrot","doi":"10.1038/s42256-025-01047-1","DOIUrl":"https://doi.org/10.1038/s42256-025-01047-1","url":null,"abstract":"<p>Language models are thriving, powering conversational agents that assist and empower humans to solve a number of tasks. Recently, these models were extended to support additional modalities including vision, audio and video, demonstrating impressive capabilities across multiple domains, including healthcare. Still, conversational agents remain limited in biology as they cannot yet fully comprehend biological sequences. Meanwhile, high-performance foundation models for biological sequences have been built through self-supervision over sequencing data, but these need to be fine-tuned for each specific application, preventing generalization between tasks. In addition, these models are not conversational, which limits their utility to users with coding capabilities. Here we propose to bridge the gap between biology foundation models and conversational agents by introducing ChatNT, a multimodal conversational agent with an advanced understanding of biological sequences. ChatNT achieves new state-of-the-art results on the Nucleotide Transformer benchmark while being able to solve all tasks at once, in English, and to generalize to unseen questions. In addition, we have curated a set of more biologically relevant instruction tasks from DNA, RNA and proteins, spanning multiple species, tissues and biological processes. ChatNT reaches performance on par with state-of-the-art specialized methods on those tasks. We also present a perplexity-based technique to help calibrate the confidence of our model predictions. By applying attribution methods through the English decoder and DNA encoder, we demonstrate that ChatNT’s answers are based on biologically coherent features such as detecting the promoter TATA motif or splice site dinucleotides. Our framework for genomics instruction tuning can be extended to more tasks and data modalities (for example, structure and imaging), making it a widely applicable tool for biology. ChatNT provides a potential direction for building generally capable agents that understand biology from first principles while being accessible to users with no coding background.</p>","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"39 1","pages":""},"PeriodicalIF":23.8,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144229007","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}