RNA molecules are essential regulators of biological processes and promising therapeutic targets for various diseases. Discovering small molecules that selectively bind to specific RNA conformations remains challenging due to RNA’s structural complexity and the limited availability of high-resolution data. Here we introduce GerNA-Bind, a geometric deep learning framework to predict RNA–ligand binding specificity by integrating multistate RNA–ligand representations and interactions. GerNA-Bind achieves state-of-the-art performance on multiple benchmark datasets and excels in predicting interactions for low-homology RNA–ligand pairs. It achieves a 20.8% improvement in precision for binding-site prediction compared with AlphaFold3. Furthermore, it offers informative, well-calibrated predictions with built-in uncertainty quantification. In a large-scale virtual screening application, GerNA-Bind identified 18 structurally diverse compounds targeting the oncogenic MALAT1 RNA, with experimentally confirmed submicromolar affinities. Among them, one leading compound selectively binds the MALAT1 triple helix, reduces its transcript levels and inhibits cancer cell migration. These findings highlight GerNA-Bind’s potential as a powerful tool for RNA-focused drug discovery, offering both accuracy and biological insight. Xia et al. introduce GerNA-Bind, a geometric deep learning framework designed to predict RNA–ligand binding specificity by integrating multistate RNA–ligand interactions.
{"title":"Deciphering RNA–ligand binding specificity with GerNA-Bind","authors":"Yunpeng Xia, Jiayi Li, Yi-Ting Chu, Jiahua Rao, Jing Chen, Chenqing Hua, Dong-Jun Yu, Xiu-Cai Chen, Shuangjia Zheng","doi":"10.1038/s42256-025-01154-z","DOIUrl":"10.1038/s42256-025-01154-z","url":null,"abstract":"RNA molecules are essential regulators of biological processes and promising therapeutic targets for various diseases. Discovering small molecules that selectively bind to specific RNA conformations remains challenging due to RNA’s structural complexity and the limited availability of high-resolution data. Here we introduce GerNA-Bind, a geometric deep learning framework to predict RNA–ligand binding specificity by integrating multistate RNA–ligand representations and interactions. GerNA-Bind achieves state-of-the-art performance on multiple benchmark datasets and excels in predicting interactions for low-homology RNA–ligand pairs. It achieves a 20.8% improvement in precision for binding-site prediction compared with AlphaFold3. Furthermore, it offers informative, well-calibrated predictions with built-in uncertainty quantification. In a large-scale virtual screening application, GerNA-Bind identified 18 structurally diverse compounds targeting the oncogenic MALAT1 RNA, with experimentally confirmed submicromolar affinities. Among them, one leading compound selectively binds the MALAT1 triple helix, reduces its transcript levels and inhibits cancer cell migration. These findings highlight GerNA-Bind’s potential as a powerful tool for RNA-focused drug discovery, offering both accuracy and biological insight. Xia et al. introduce GerNA-Bind, a geometric deep learning framework designed to predict RNA–ligand binding specificity by integrating multistate RNA–ligand interactions.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 12","pages":"1996-2008"},"PeriodicalIF":23.9,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145746793","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 : 2025-12-12DOI: 10.1038/s42256-025-01159-8
Brian D. Earp, Haotian Yuan, Julian Koplin, Sebastian Porsdam Mann
{"title":"LLM use in scholarly writing poses a provenance problem","authors":"Brian D. Earp, Haotian Yuan, Julian Koplin, Sebastian Porsdam Mann","doi":"10.1038/s42256-025-01159-8","DOIUrl":"10.1038/s42256-025-01159-8","url":null,"abstract":"","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 12","pages":"1889-1890"},"PeriodicalIF":23.9,"publicationDate":"2025-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145800041","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 : 2025-12-10DOI: 10.1038/s42256-025-01148-x
Mehran Karimzadeh, Aiden M. Sababi, Amir Momen-Roknabadi, Nae-Chyun Chen, Taylor B. Cavazos, Sukh Sekhon, Jieyang Wang, Rose Hanna, Alice Huang, Dang Nguyen, Selina Chen, Ti Lam, Kimberly H. Chau, Anna Hartwig, Lisa Fish, Helen Li, Babak Behsaz, Fereydoun Hormozdiari, Babak Alipanahi, Hani Goodarzi
Cell-free RNA (cfRNA) profiling has emerged as a powerful tool for non-invasive disease detection, but its application is limited by data sparsity and complexity, especially in settings with constrained sample availability. We introduce Exai-1, a multimodal, transformer-based generative foundation model that integrates RNA sequence embeddings with cfRNA abundance data to capture biologically meaningful representations of circulating RNAs. By leveraging both sequence and expression modalities, Exai-1 captures a biologically meaningful latent structure of cfRNA profiles. Pretrained on over 306 billion tokens from 8,339 samples, Exai-1 enhances signal fidelity, reduces technical noise and improves disease detection by generating synthetic cfRNA profiles. We show that self-attention and variational inference are particularly important for the preservation of biological signals and contextual relationships. Additionally, Exai-1 facilitates cross-biofluid translation and assay compatibility through disentangling biological signals from confounders. By uniting sequence-informed embeddings with cfRNA expression patterns, Exai-1 establishes a transfer learning foundation for liquid biopsy, offering a scalable and adaptable framework for next-generation cfRNA-based diagnostics. Exai-1, a cell-free RNA foundation model that integrates sequence, structure and expression features, advances liquid biopsy diagnostics by denoising noisy data, augmenting limited datasets and improving the generalizability of cancer detection models.
{"title":"A multimodal cell-free RNA language model for liquid biopsy applications","authors":"Mehran Karimzadeh, Aiden M. Sababi, Amir Momen-Roknabadi, Nae-Chyun Chen, Taylor B. Cavazos, Sukh Sekhon, Jieyang Wang, Rose Hanna, Alice Huang, Dang Nguyen, Selina Chen, Ti Lam, Kimberly H. Chau, Anna Hartwig, Lisa Fish, Helen Li, Babak Behsaz, Fereydoun Hormozdiari, Babak Alipanahi, Hani Goodarzi","doi":"10.1038/s42256-025-01148-x","DOIUrl":"10.1038/s42256-025-01148-x","url":null,"abstract":"Cell-free RNA (cfRNA) profiling has emerged as a powerful tool for non-invasive disease detection, but its application is limited by data sparsity and complexity, especially in settings with constrained sample availability. We introduce Exai-1, a multimodal, transformer-based generative foundation model that integrates RNA sequence embeddings with cfRNA abundance data to capture biologically meaningful representations of circulating RNAs. By leveraging both sequence and expression modalities, Exai-1 captures a biologically meaningful latent structure of cfRNA profiles. Pretrained on over 306 billion tokens from 8,339 samples, Exai-1 enhances signal fidelity, reduces technical noise and improves disease detection by generating synthetic cfRNA profiles. We show that self-attention and variational inference are particularly important for the preservation of biological signals and contextual relationships. Additionally, Exai-1 facilitates cross-biofluid translation and assay compatibility through disentangling biological signals from confounders. By uniting sequence-informed embeddings with cfRNA expression patterns, Exai-1 establishes a transfer learning foundation for liquid biopsy, offering a scalable and adaptable framework for next-generation cfRNA-based diagnostics. Exai-1, a cell-free RNA foundation model that integrates sequence, structure and expression features, advances liquid biopsy diagnostics by denoising noisy data, augmenting limited datasets and improving the generalizability of cancer detection models.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 12","pages":"1927-1938"},"PeriodicalIF":23.9,"publicationDate":"2025-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01148-x.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145711554","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}
Pub Date : 2025-12-09DOI: 10.1038/s42256-025-01149-w
Kevin Portner, Till Zellweger, Flavio Martinelli, Laura Bégon-Lours, Valeria Bragaglia, Christoph Weilenmann, Daniel Jubin, Donato Francesco Falcone, Felix Hermann, Oscar Hrynkevych, Tommaso Stecconi, Antonio La Porta, Ute Drechsler, Antonis Olziersky, Bert Jan Offrein, Wulfram Gerstner, Mathieu Luisier, Alexandros Emboras
Advancements in memristive devices have given rise to a new generation of specialized hardware for bio-inspired computing. However, most of these implementations draw only partial inspiration from the architecture and functionalities of the mammalian brain. Moreover, the use of memristive hardware is typically restricted to specific elements within the learning algorithm, leaving computationally expensive operations to be executed in software. Here we demonstrate reinforcement learning through an actor–critic temporal difference algorithm implemented on analogue memristors, mirroring the principles of reward-based learning in a neural network architecture similar to the one found in biology. Memristors are used as multipurpose elements within the learning algorithm: they act as synaptic weights that are trained online, they calculate the weight updates associated with the temporal difference error directly in hardware and they determine the actions to navigate the environment. Owing to these features, weight training can take place entirely in memory, eliminating data movement. We test our framework on two navigation tasks—the T-maze and the Morris water maze—using analogue memristors based on the valence change memory effect. Our approach represents the first step towards fully in-memory and online neuromorphic computing engines based on bio-inspired learning schemes. A framework based on actor–critic temporal difference learning and employing a biologically plausible network architecture that mimics reward-based learning on memristors and enables full in-memory training for navigation tasks is discussed.
{"title":"Actor–critic networks with analogue memristors mimicking reward-based learning","authors":"Kevin Portner, Till Zellweger, Flavio Martinelli, Laura Bégon-Lours, Valeria Bragaglia, Christoph Weilenmann, Daniel Jubin, Donato Francesco Falcone, Felix Hermann, Oscar Hrynkevych, Tommaso Stecconi, Antonio La Porta, Ute Drechsler, Antonis Olziersky, Bert Jan Offrein, Wulfram Gerstner, Mathieu Luisier, Alexandros Emboras","doi":"10.1038/s42256-025-01149-w","DOIUrl":"10.1038/s42256-025-01149-w","url":null,"abstract":"Advancements in memristive devices have given rise to a new generation of specialized hardware for bio-inspired computing. However, most of these implementations draw only partial inspiration from the architecture and functionalities of the mammalian brain. Moreover, the use of memristive hardware is typically restricted to specific elements within the learning algorithm, leaving computationally expensive operations to be executed in software. Here we demonstrate reinforcement learning through an actor–critic temporal difference algorithm implemented on analogue memristors, mirroring the principles of reward-based learning in a neural network architecture similar to the one found in biology. Memristors are used as multipurpose elements within the learning algorithm: they act as synaptic weights that are trained online, they calculate the weight updates associated with the temporal difference error directly in hardware and they determine the actions to navigate the environment. Owing to these features, weight training can take place entirely in memory, eliminating data movement. We test our framework on two navigation tasks—the T-maze and the Morris water maze—using analogue memristors based on the valence change memory effect. Our approach represents the first step towards fully in-memory and online neuromorphic computing engines based on bio-inspired learning schemes. A framework based on actor–critic temporal difference learning and employing a biologically plausible network architecture that mimics reward-based learning on memristors and enables full in-memory training for navigation tasks is discussed.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 12","pages":"1939-1953"},"PeriodicalIF":23.9,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01149-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145705166","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}
Pub Date : 2025-12-09DOI: 10.1038/s42256-025-01157-w
Yue Zhang, Xiaojuan Qi, Zhongrui Wang
Reinforcement learning has a key role in artifical intelligence (AI), but its implementation on neuromorphic hardware typically involves operations executed on conventional digital computers. A study now addresses this issue by implementing an actor–critic network fully in hardware using analogue memristors.
{"title":"Fully analogue reinforcement learning with memristors","authors":"Yue Zhang, Xiaojuan Qi, Zhongrui Wang","doi":"10.1038/s42256-025-01157-w","DOIUrl":"10.1038/s42256-025-01157-w","url":null,"abstract":"Reinforcement learning has a key role in artifical intelligence (AI), but its implementation on neuromorphic hardware typically involves operations executed on conventional digital computers. A study now addresses this issue by implementing an actor–critic network fully in hardware using analogue memristors.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 12","pages":"1893-1894"},"PeriodicalIF":23.9,"publicationDate":"2025-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145799985","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 : 2025-12-04DOI: 10.1038/s42256-025-01155-y
Binxu Wang, Carlos R. Ponce
Even before training, convolutional neural networks may reflect the brain’s visual processing principles. A study now shows how structure alone can help to explain the alignment between brains and models.
{"title":"Structure as an inductive bias for brain–model alignment","authors":"Binxu Wang, Carlos R. Ponce","doi":"10.1038/s42256-025-01155-y","DOIUrl":"10.1038/s42256-025-01155-y","url":null,"abstract":"Even before training, convolutional neural networks may reflect the brain’s visual processing principles. A study now shows how structure alone can help to explain the alignment between brains and models.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 12","pages":"1895-1896"},"PeriodicalIF":23.9,"publicationDate":"2025-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680424","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 : 2025-12-01DOI: 10.1038/s42256-025-01135-2
Chi-Hieu Nguyen, Thai Hoang Dinh, Diep N. Nguyen, Kristin Lauter, Miran Kim
Deep reinforcement learning (DRL) demonstrates significant potential in solving complex control and decision-making problems, but it may inadvertently expose sensitive, environment-specific information, raising privacy and security concerns for computer systems, humans and organizations. This work introduces a privacy-preserving framework using homomorphic encryption and advanced learning algorithms to secure DRL processes. Our framework enables the encryption of sensitive information, including states, actions and rewards, before sharing it with an untrusted processing platform. This encryption ensures data privacy, prevents unauthorized access and maintains compliance with data protection laws throughout the learning process. In addition, we develop innovative algorithms to efficiently handle a wide range of encrypted control tasks. Our core innovation is the homomorphic encryption-compatible Adam optimizer, which reparameterizes momentum values to bypass the need for high-degree polynomial approximations of inverse square roots on encrypted data. This adaptation, previously unexplored in homomorphic encryption-based ML research, enables stable and efficient training with adaptive learning rates in encrypted domains, addressing a critical bottleneck for privacy-preserving DRL with sparse rewards. Evaluations on standard DRL benchmarks demonstrate that our encrypted DRL performs comparably with its unencrypted counterpart (with a gap of less than 10%) and maintaining data confidentiality with homomorphic encryption. This work facilitates the integration of privacy-preserving DRL into real-world applications, addressing critical privacy concerns, and promoting the ethical advancement of artificial intelligence. A secure artificial intelligence framework is introduced that leverages homomorphic encryption to safeguard sensitive information in deep reinforcement learning, achieving accurate decision-making and ensuring data privacy and confidentiality.
{"title":"Empowering artificial intelligence with homomorphic encryption for secure deep reinforcement learning","authors":"Chi-Hieu Nguyen, Thai Hoang Dinh, Diep N. Nguyen, Kristin Lauter, Miran Kim","doi":"10.1038/s42256-025-01135-2","DOIUrl":"10.1038/s42256-025-01135-2","url":null,"abstract":"Deep reinforcement learning (DRL) demonstrates significant potential in solving complex control and decision-making problems, but it may inadvertently expose sensitive, environment-specific information, raising privacy and security concerns for computer systems, humans and organizations. This work introduces a privacy-preserving framework using homomorphic encryption and advanced learning algorithms to secure DRL processes. Our framework enables the encryption of sensitive information, including states, actions and rewards, before sharing it with an untrusted processing platform. This encryption ensures data privacy, prevents unauthorized access and maintains compliance with data protection laws throughout the learning process. In addition, we develop innovative algorithms to efficiently handle a wide range of encrypted control tasks. Our core innovation is the homomorphic encryption-compatible Adam optimizer, which reparameterizes momentum values to bypass the need for high-degree polynomial approximations of inverse square roots on encrypted data. This adaptation, previously unexplored in homomorphic encryption-based ML research, enables stable and efficient training with adaptive learning rates in encrypted domains, addressing a critical bottleneck for privacy-preserving DRL with sparse rewards. Evaluations on standard DRL benchmarks demonstrate that our encrypted DRL performs comparably with its unencrypted counterpart (with a gap of less than 10%) and maintaining data confidentiality with homomorphic encryption. This work facilitates the integration of privacy-preserving DRL into real-world applications, addressing critical privacy concerns, and promoting the ethical advancement of artificial intelligence. A secure artificial intelligence framework is introduced that leverages homomorphic encryption to safeguard sensitive information in deep reinforcement learning, achieving accurate decision-making and ensuring data privacy and confidentiality.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 12","pages":"1913-1926"},"PeriodicalIF":23.9,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145645246","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 : 2025-11-28DOI: 10.1038/s42256-025-01146-z
Daniel Durstewitz, Bruno Averbeck, Georgia Koppe
Modern artificial intelligence (AI) models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task and then deployed with fixed parameters. Their training is costly, slow and gradual, requiring billions of repetitions. In stark contrast, animals continuously adapt to the ever-changing contingencies in their environments. This is particularly important for social species, where behavioural policies and reward outcomes may frequently change in interaction with peers. The underlying computational processes are often marked by rapid shifts in an animal’s behaviour and rather sudden transitions in neuronal population activity. Such computational capacities are of growing importance for AI systems operating in the real world, like those guiding robots or autonomous vehicles, or for agentic AI interacting with humans online. Can AI learn from neuroscience? This Perspective explores this question, integrating the literature on continual and in-context learning in AI with the neuroscience of learning on behavioural tasks with shifting rules, reward probabilities or outcomes. We outline an agenda for how the links between neuroscience and AI could be tightened, thus supporting the transfer of ideas and findings between both areas and contributing to the evolving field of NeuroAI. Durstewitz et al. explore what artificial intelligence can learn from the brain’s ability to adjust quickly to changing environments. By linking neuroscience studies of flexible behaviour with advances in continual and in-context learning, this Perspective outlines ways to strengthen the exchange of ideas between the two fields and advance NeuroAI.
{"title":"What neuroscience can tell AI about learning in continuously changing environments","authors":"Daniel Durstewitz, Bruno Averbeck, Georgia Koppe","doi":"10.1038/s42256-025-01146-z","DOIUrl":"10.1038/s42256-025-01146-z","url":null,"abstract":"Modern artificial intelligence (AI) models, such as large language models, are usually trained once on a huge corpus of data, potentially fine-tuned for a specific task and then deployed with fixed parameters. Their training is costly, slow and gradual, requiring billions of repetitions. In stark contrast, animals continuously adapt to the ever-changing contingencies in their environments. This is particularly important for social species, where behavioural policies and reward outcomes may frequently change in interaction with peers. The underlying computational processes are often marked by rapid shifts in an animal’s behaviour and rather sudden transitions in neuronal population activity. Such computational capacities are of growing importance for AI systems operating in the real world, like those guiding robots or autonomous vehicles, or for agentic AI interacting with humans online. Can AI learn from neuroscience? This Perspective explores this question, integrating the literature on continual and in-context learning in AI with the neuroscience of learning on behavioural tasks with shifting rules, reward probabilities or outcomes. We outline an agenda for how the links between neuroscience and AI could be tightened, thus supporting the transfer of ideas and findings between both areas and contributing to the evolving field of NeuroAI. Durstewitz et al. explore what artificial intelligence can learn from the brain’s ability to adjust quickly to changing environments. By linking neuroscience studies of flexible behaviour with advances in continual and in-context learning, this Perspective outlines ways to strengthen the exchange of ideas between the two fields and advance NeuroAI.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 12","pages":"1897-1912"},"PeriodicalIF":23.9,"publicationDate":"2025-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145611610","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 : 2025-11-19DOI: 10.1038/s42256-025-01122-7
Simon Deltadahl, Julian Gilbey, Christine Van Laer, Nancy Boeckx, Mathie P. G. Leers, Tanya Freeman, Laura Aiken, Timothy Farren, Matthew Smith, Mohamad Zeina, Stephen MacDonald, Daniel Gleghorn, BloodCounts! consortium, James HF Rudd, Concetta Piazzese, Joseph Taylor, Nicholas Gleadall, Carola-Bibiane Schönlieb, Suthesh Sivapalaratnam, Michael Roberts, Parashkev Nachev
Blood cell morphology assessment via light microscopy constitutes a cornerstone of haematological diagnostics, providing crucial insights into diverse pathological conditions. This complex task demands expert interpretation owing to subtle morphological variations, biological heterogeneity and technical imaging factors that obstruct automated approaches. Conventional machine learning methods using discriminative models struggle with domain shifts, intraclass variability and rare morphological variants, constraining their clinical utility. We introduce CytoDiffusion, a diffusion-based generative classifier that faithfully models the distribution of blood cell morphology, combining accurate classification with robust anomaly detection, resistance to distributional shifts, interpretability, data efficiency and uncertainty quantification that surpasses clinical experts. Our approach outperforms state-of-the-art discriminative models in anomaly detection (area under the curve, 0.990 versus 0.916), resistance to domain shifts (0.854 versus 0.738 accuracy) and performance in low-data regimes (0.962 versus 0.924 balanced accuracy). In particular, CytoDiffusion generates synthetic blood cell images that expert haematologists cannot distinguish from real ones (accuracy, 0.523; 95% confidence interval: [0.505, 0.542]), demonstrating good command of the underlying distribution. Furthermore, we enhance model explainability through directly interpretable counterfactual heat maps. Our comprehensive evaluation framework establishes a multidimensional benchmark for medical image analysis in haematology, ultimately enabling improved diagnostic accuracy in clinical settings. Diffusion models are reframed by developing a generative blood cell classifier that performs reliably in low-data regimes, adapts to domain shifts, detects anomalies with robustness and provides uncertainty estimates that surpass clinical expert benchmarks.
通过光学显微镜进行血细胞形态评估是血液学诊断的基石，为不同的病理状况提供了重要的见解。由于细微的形态变化、生物异质性和技术成像因素阻碍了自动化方法，这项复杂的任务需要专家解释。使用判别模型的传统机器学习方法与领域转移、类内变异性和罕见的形态变异作斗争，限制了它们的临床应用。我们介绍了CytoDiffusion，这是一种基于扩散的生成分类器，它忠实地模拟了血细胞形态的分布，将准确的分类与鲁棒的异常检测、对分布变化的抵抗、可解释性、数据效率和不确定性量化相结合，超越了临床专家。我们的方法在异常检测（曲线下面积，0.990 vs 0.916）、抗域移（0.854 vs 0.738精度）和低数据状态下的性能（0.962 vs 0.924平衡精度）方面优于最先进的判别模型。特别是，CytoDiffusion生成的合成血细胞图像，血液专家无法将其与真实的血细胞图像区分开来（准确率为0.523；95%置信区间：[0.505,0.542]），显示出对潜在分布的良好掌握。此外，我们通过直接可解释的反事实热图增强了模型的可解释性。我们的综合评估框架建立了血液学医学图像分析的多维基准，最终提高了临床诊断的准确性。扩散模型通过开发再生血细胞分类器进行重构，该分类器在低数据状态下可靠地执行，适应域转移，鲁棒性检测异常，并提供超过临床专家基准的不确定性估计。
{"title":"Deep generative classification of blood cell morphology","authors":"Simon Deltadahl, Julian Gilbey, Christine Van Laer, Nancy Boeckx, Mathie P. G. Leers, Tanya Freeman, Laura Aiken, Timothy Farren, Matthew Smith, Mohamad Zeina, Stephen MacDonald, Daniel Gleghorn, BloodCounts! consortium, James HF Rudd, Concetta Piazzese, Joseph Taylor, Nicholas Gleadall, Carola-Bibiane Schönlieb, Suthesh Sivapalaratnam, Michael Roberts, Parashkev Nachev","doi":"10.1038/s42256-025-01122-7","DOIUrl":"10.1038/s42256-025-01122-7","url":null,"abstract":"Blood cell morphology assessment via light microscopy constitutes a cornerstone of haematological diagnostics, providing crucial insights into diverse pathological conditions. This complex task demands expert interpretation owing to subtle morphological variations, biological heterogeneity and technical imaging factors that obstruct automated approaches. Conventional machine learning methods using discriminative models struggle with domain shifts, intraclass variability and rare morphological variants, constraining their clinical utility. We introduce CytoDiffusion, a diffusion-based generative classifier that faithfully models the distribution of blood cell morphology, combining accurate classification with robust anomaly detection, resistance to distributional shifts, interpretability, data efficiency and uncertainty quantification that surpasses clinical experts. Our approach outperforms state-of-the-art discriminative models in anomaly detection (area under the curve, 0.990 versus 0.916), resistance to domain shifts (0.854 versus 0.738 accuracy) and performance in low-data regimes (0.962 versus 0.924 balanced accuracy). In particular, CytoDiffusion generates synthetic blood cell images that expert haematologists cannot distinguish from real ones (accuracy, 0.523; 95% confidence interval: [0.505, 0.542]), demonstrating good command of the underlying distribution. Furthermore, we enhance model explainability through directly interpretable counterfactual heat maps. Our comprehensive evaluation framework establishes a multidimensional benchmark for medical image analysis in haematology, ultimately enabling improved diagnostic accuracy in clinical settings. Diffusion models are reframed by developing a generative blood cell classifier that performs reliably in low-data regimes, adapts to domain shifts, detects anomalies with robustness and provides uncertainty estimates that surpass clinical expert benchmarks.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 11","pages":"1791-1803"},"PeriodicalIF":23.9,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s42256-025-01122-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145547308","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}
The scalable solution to constrained combinatorial problems in high dimensions can address many challenges encountered in scientific and engineering disciplines. Inspired by the use of graph neural networks for quadratic-cost combinatorial optimization problems, Heydaribeni and colleagues proposed HypOp, which aims to efficiently solve general problems with higher-order constraints by leveraging hypergraph neural networks to extend previous algorithms to arbitrary cost functions. It incorporates a distributed training architecture to handle larger-scale tasks efficiently. Here we reproduce the primary experiments of HypOp and examine its robustness with respect to the number of graphics processing units, distributed partitioning strategies and fine-tuning methods. We also assess its transferability by applying it to the maximum clique problem and the quadratic assignment problem. The results validate the reusability of HypOp across diverse application scenarios. Furthermore, we provide guidelines offering practical insights for effectively applying it to multiple combinatorial optimization problems. HypOp is a scalable method for solving complex combinatorial problems. This study reproduces its results, tests its robustness, extends it to new tasks and provides practical guidelines for broader scientific applications.
{"title":"Reusability report: A distributed strategy for solving combinatorial optimization problems with hypergraph neural networks","authors":"Xiaodi Li, Jianfeng Gui, Wei Xue, Baochuan Wang, Kai Chen, Pijing Wei, Junfeng Xia, Zhenyu Yue","doi":"10.1038/s42256-025-01141-4","DOIUrl":"10.1038/s42256-025-01141-4","url":null,"abstract":"The scalable solution to constrained combinatorial problems in high dimensions can address many challenges encountered in scientific and engineering disciplines. Inspired by the use of graph neural networks for quadratic-cost combinatorial optimization problems, Heydaribeni and colleagues proposed HypOp, which aims to efficiently solve general problems with higher-order constraints by leveraging hypergraph neural networks to extend previous algorithms to arbitrary cost functions. It incorporates a distributed training architecture to handle larger-scale tasks efficiently. Here we reproduce the primary experiments of HypOp and examine its robustness with respect to the number of graphics processing units, distributed partitioning strategies and fine-tuning methods. We also assess its transferability by applying it to the maximum clique problem and the quadratic assignment problem. The results validate the reusability of HypOp across diverse application scenarios. Furthermore, we provide guidelines offering practical insights for effectively applying it to multiple combinatorial optimization problems. HypOp is a scalable method for solving complex combinatorial problems. This study reproduces its results, tests its robustness, extends it to new tasks and provides practical guidelines for broader scientific applications.","PeriodicalId":48533,"journal":{"name":"Nature Machine Intelligence","volume":"7 11","pages":"1870-1878"},"PeriodicalIF":23.9,"publicationDate":"2025-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145547309","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}
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：