{"title":"A meaningful map of the underexplored electrolyte universe","authors":"Stephen Lam, Romakanta Bhattarai","doi":"10.1038/s43588-026-00962-6","DOIUrl":"10.1038/s43588-026-00962-6","url":null,"abstract":"A machine learning framework reveals how dynamic routing and interpretability can accelerate the discovery of better electrolytes for next-generation batteries.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 3","pages":"229-230"},"PeriodicalIF":18.3,"publicationDate":"2026-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147370180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Guiding molecular design with flow models","authors":"Andreas Luttens","doi":"10.1038/s43588-026-00961-7","DOIUrl":"10.1038/s43588-026-00961-7","url":null,"abstract":"The PropMolFlow model uses flow matching to efficiently generate chemically valid molecules in three dimensions with targeted properties, enabling accelerated discovery of molecules useful in materials and pharmaceutical science.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 3","pages":"225-226"},"PeriodicalIF":18.3,"publicationDate":"2026-03-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147370642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"TANGO: direct optimization of constrained synthesizability for generative molecular design","authors":"Jeff Guo, Philippe Schwaller","doi":"10.1038/s43588-026-00959-1","DOIUrl":"10.1038/s43588-026-00959-1","url":null,"abstract":"Constrained synthesizability is an unaddressed challenge in generative molecular design: in particular, designing molecules satisfying multi-parameter optimization objectives, while simultaneously being synthesizable and enforcing the presence of specific building blocks in the synthesis. This is practically important for molecule re-purposing, sustainability and efficiency. Here we propose the Tanimoto Group Overlap (TANGO) reward function, which uses chemistry principles to transform a binary reward function into a continuous reward function. TANGO can augment molecular generative models to directly optimize for constrained synthesizability using reinforcement learning (RL). Our framework is general and addresses starting-material, intermediate and divergent-synthesis constraints. Contrary to many existing works in the field, we show that incentivizing a general-purpose model with RL is a productive approach to navigating challenging synthesizability optimization scenarios. The authors propose the TANGO reward function, which enables the generation of property-optimized small molecules with predicted synthesis routes, incorporating a small set of shared precursors.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 3","pages":"260-270"},"PeriodicalIF":18.3,"publicationDate":"2026-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147349919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Understanding large-scale cooperation in a nonlinear, interconnected world","authors":"Benjamin Allen","doi":"10.1038/s43588-026-00951-9","DOIUrl":"10.1038/s43588-026-00951-9","url":null,"abstract":"Large-scale cooperation is characterized by complex interaction patterns with nonlinear outcomes. Deepening our understanding may be critical to addressing real-world collective challenges.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 2","pages":"112-114"},"PeriodicalIF":18.3,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147288485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Cover runners-up of 2025","authors":"","doi":"10.1038/s43588-026-00967-1","DOIUrl":"10.1038/s43588-026-00967-1","url":null,"abstract":"We highlight some of our favorite cover suggestions from 2025.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 2","pages":"111-111"},"PeriodicalIF":18.3,"publicationDate":"2026-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s43588-026-00967-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147288484","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Partially shared multi-modal embedding learns holistic representation of cell state","authors":"Xinyi Zhang, G. V. Shivashankar, Caroline Uhler","doi":"10.1038/s43588-025-00948-w","DOIUrl":"10.1038/s43588-025-00948-w","url":null,"abstract":"Current technologies enable the simultaneous measurement of diverse data types at the single-cell level. However, data are often processed separately, or integrated via representation learning methods that obscure the contributions of each data modality. Here we present a computational framework that automatically learns partial information sharing between multiple modalities by using an Autoencoder with a Partially Overlapping Latent space learned through Latent Optimization (APOLLO). We tested APOLLO on simulated data, and on four applications involving paired single-cell data: SHARE-seq (scRNA-seq and scATAC-seq), CITE-seq (scRNA-seq and protein abundance), and two multiplexed imaging datasets. APOLLO enables the prediction of missing modalities, such as unmeasured protein stains, and allows disentangling which modality or cellular compartment is linked with a specific phenotype, such as the variability in protein localization observed across single cells. Overall, APOLLO efficiently integrates diverse data modalities and, by retaining and distinguishing between shared and modality-specific information, provides a more interpretable and holistic view of cell state. APOLLO is an autoencoder-based framework to integrate diverse data modalities while preserving both shared and modality-specific information. It enables predicting missing data modalities and identifying the influence of each modality on a phenotype.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 3","pages":"285-300"},"PeriodicalIF":18.3,"publicationDate":"2026-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s43588-025-00948-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147313265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Self-optimized spectral distance for low-light high-throughput Raman hyperspectral imaging.","authors":"Yurong Chen, Shen Wang, Yaonan Wang, Jianxu Mao, Lizhu Liu, Xiaoxu Cao, Zhuo Chen, Hui Zhang","doi":"10.1038/s43588-026-00957-3","DOIUrl":"https://doi.org/10.1038/s43588-026-00957-3","url":null,"abstract":"<p><p>Raman hyperspectral imaging is a powerful technique for probing the intrinsic properties of samples by combining vibrational spectroscopy with spatial imaging. Despite its potential, the inherently weak Raman scattering signal typically necessitates prolonged acquisition times or high-power lasers, thereby limiting its efficiency and broader applicability. Here we present a computational method for facilitating Raman imaging under challenging conditions. We propose that even low-quality measurements-acquired with short integration times or low-power lasers-still contain sufficient information of Raman spectra. To this end, an unsupervised learning-based method, self-optimized spectral distance (SSD), is developed to reconstruct Raman images directly from 'noisy' measurements. By eliminating the dependence on large-scale training datasets, long imaging times and high-energy lasers, SSD helps to advance high-throughput Raman imaging. In diverse applications, including cellular structure analysis, microparticle detection and pharmaceutical ingredient identification, SSD achieves high imaging quality while reducing acquisition time and excitation power at least one order of magnitude.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":18.3,"publicationDate":"2026-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147277923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rachel Adams, Fola Adeleke, Leah Junck, Ayantola Alayande, Aarushi Gupta, Urvashi Aneja, Samuel Segun, Rosalind Parkes-Ratanshi, Selam Abdella, Mark Gaffley, Scott Mahoney, Rirhandzu Makamu, Nana Eghele Adade, Liping Bian, Timothy Kintu, Atwine Mugume, Aline Germani, Michelle El Kawak, Bheeshma Patel, Olanrewaju Lawa, Sara Khalid, Olubayo Adekanmbi, Rasheedat Sikiru, Toyib Ogunremi, Farhan Yusuf, Hanna Minaye, Imo Etuk, Jimmy Nsenga, Uma Urs, Marzia Zaman, Khondaker A Mamun, Vivian Resende, Pedro Henrique Faria Silva Trocoli-Couto, Rositsa Zaimova, Mamadou Alpha Diallo, Nana Kofi Quakyi, Xiao Fan Liu, Daudi Jjingo, Imad Elhajj, Joyce Nakatumba-Nabende, Tamlyn Eslie Roman, Maryam Mustafa, Brenda Hendry, Yogesh Hooda, Chinazo Anebelundu, Bishesh Khanal, Faisal Sultan, Nirmal Ravi, Darlington Akogo, Zameer Brey, Dave Cohen, Joshua Proctor, Essa Mohamedali, Nneka Mobisson, Amelia Taylor, Joao Archegas, Amrita Mahale, Neal Lesh, Enrica Duncan, Theofrida J Maginga, Hugo Manuel Paz Morales, Henrique Dias Pereira Dos Santos, Tue Vo, Trang Th Nguyen, Robert Korom, Michael Leventhal, Shashi Jain, Livia Maria de Oliveira Ciabati, Praveen Devarsetty, Jane Hirst, Ankita Sharma, Moinul Chowdhury, Henrique Araujo Lima, Caroline Govathson, Sarah Morris
{"title":"Mapping the potential and limitations of using generative AI technologies to address socio-economic challenges in LMICs.","authors":"Rachel Adams, Fola Adeleke, Leah Junck, Ayantola Alayande, Aarushi Gupta, Urvashi Aneja, Samuel Segun, Rosalind Parkes-Ratanshi, Selam Abdella, Mark Gaffley, Scott Mahoney, Rirhandzu Makamu, Nana Eghele Adade, Liping Bian, Timothy Kintu, Atwine Mugume, Aline Germani, Michelle El Kawak, Bheeshma Patel, Olanrewaju Lawa, Sara Khalid, Olubayo Adekanmbi, Rasheedat Sikiru, Toyib Ogunremi, Farhan Yusuf, Hanna Minaye, Imo Etuk, Jimmy Nsenga, Uma Urs, Marzia Zaman, Khondaker A Mamun, Vivian Resende, Pedro Henrique Faria Silva Trocoli-Couto, Rositsa Zaimova, Mamadou Alpha Diallo, Nana Kofi Quakyi, Xiao Fan Liu, Daudi Jjingo, Imad Elhajj, Joyce Nakatumba-Nabende, Tamlyn Eslie Roman, Maryam Mustafa, Brenda Hendry, Yogesh Hooda, Chinazo Anebelundu, Bishesh Khanal, Faisal Sultan, Nirmal Ravi, Darlington Akogo, Zameer Brey, Dave Cohen, Joshua Proctor, Essa Mohamedali, Nneka Mobisson, Amelia Taylor, Joao Archegas, Amrita Mahale, Neal Lesh, Enrica Duncan, Theofrida J Maginga, Hugo Manuel Paz Morales, Henrique Dias Pereira Dos Santos, Tue Vo, Trang Th Nguyen, Robert Korom, Michael Leventhal, Shashi Jain, Livia Maria de Oliveira Ciabati, Praveen Devarsetty, Jane Hirst, Ankita Sharma, Moinul Chowdhury, Henrique Araujo Lima, Caroline Govathson, Sarah Morris","doi":"10.1038/s43588-026-00960-8","DOIUrl":"https://doi.org/10.1038/s43588-026-00960-8","url":null,"abstract":"<p><p>Drawing on the experiences and lessons learned from researchers based in low- and middle-income countries (LMICs) that leverage generative artificial intelligence (GenAI) technologies to address socio-economic challenges, we showcase the considerable potential to use GenAI to accelerate the progress towards achieving some of the Sustainable Development Goals, as well as considerable obstacles for creating locally adapted AI tools for fair development in LMICs. An expanded evidence base on GenAI in resource-limited settings is crucial for policymakers to understand opportunities and risks, while rights-based safeguards against AI harms can be strengthened by the lived experiences of local projects.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":18.3,"publicationDate":"2026-02-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147277908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Liangxuan Guo, Haoyang Chen, Yang Chen, Yanchao Bi, Shan Yu
{"title":"A neural network for modeling human concept formation, understanding and communication.","authors":"Liangxuan Guo, Haoyang Chen, Yang Chen, Yanchao Bi, Shan Yu","doi":"10.1038/s43588-026-00956-4","DOIUrl":"10.1038/s43588-026-00956-4","url":null,"abstract":"<p><p>A remarkable capability of the human brain is to form more abstract conceptual representations from sensorimotor experiences and flexibly apply them independent of direct sensory inputs. However, the computational mechanism underlying this ability remains poorly understood. Here we present a dual-module neural network framework, CATS Net, to bridge this gap. Our model consists of a concept-abstraction module that extracts low-dimensional conceptual representations, and a task-solving module that performs visual judgment tasks under the hierarchical gating control of the formed concepts. The system develops transferable semantic structure based on concept representations that enable cross-network knowledge transfer through conceptual communication. Model-brain fitting analyses reveal that these emergent concept spaces align with both neurocognitive semantic model and brain response structures in the human ventral occipitotemporal cortex, while the gating mechanisms mirror that in the semantic-control brain network. This work establishes a unified computational framework that can offer mechanistic insights for understanding human conceptual cognition and engineering artificial systems with human-like conceptual intelligence.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":18.3,"publicationDate":"2026-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146229696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
