Nature computational science最新文献

{"title":"Longitudinal alignments and syntheses of multimodal clinical data for personalized medicine with the PULSE framework","authors":"Wei Wu, Gen Li, Kai Wang, Hui Xu, Haodi Xiao, Changxi Hu, Sian Liu, Cheng Tang, Fei Liu, Zixing Zou, Bingzhou Li, Jinghang Li, Charlotte L. Zhang, Hang Wong, Ieng Chong, Wenyang Lu, Zhuo Sun, Yun Yin, Alexandre Loupy, Eric Oermann, Saleem A. Al Dajani, Hao Zhu, Jonathan Gootenberg, Omar O. Abudayyeh, Vadim N. Gladyshev, John E. J. Rasko, Kang Zhang, on behalf of the International Consortium of Digital Twins in Healthcare and Medicine","doi":"10.1038/s43588-026-01026-5","DOIUrl":"10.1038/s43588-026-01026-5","url":null,"abstract":"Multimodal models capable of imputing diverse data used in single-cell biology studies provide potential foundational opportunities in clinical practice. However, patient data uniquely comprise longitudinal mosaic measurements that reflect underlying physiological dynamics and exhibit temporal covariation, demanding a specialized approach. Here we present Patient Unified Longitudinal Signal Engine (PULSE), a longitudinal self-supervised framework that explicitly encodes personalized past states (historical paired modalities) to reconstruct full profiles from subsequent unpaired measurements, thus enhancing current visit multimodal alignment and generation. Applied to the UK Biobank, PULSE accurately generates metabolomic profiles and proteomic profiles from sparse routine blood tests. Compared with the ground truth metabolomic data (251 biomarkers), PULSE-generated profiles outperformed all benchmark methods. Furthermore, the framework accommodates incorporation of retinal images, electronic health records and blood markers with disease prediction: models trained on the generated proteomic profiles achieved areas under the curve of 0.72–0.83 for six common diseases, comparable to that using ground-truth proteomic data. The PULSE framework demonstrates that cross-modal alignment captures the continuous spectrum of disease physiology and extracts robust features that transcend the limitations of traditional binary case–controls. PULSE is an AI framework that uses patients’ longitudinal electronic health records to accurately generate within- and cross-modal data from routine clinical laboratory tests, enabling cost-effective precision medicine across diverse biomedical settings.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 9","pages":"954-970"},"PeriodicalIF":20.3,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s43588-026-01026-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148835366","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-rankings as a predictor of scientific impact beyond peer review","authors":"Buxin Su, Natalie Collina, Garrett Wen, Didong Li, Kyunghyun Cho, Jianqing Fan, Bingxin Zhao, Weijie Su","doi":"10.1038/s43588-026-01039-0","DOIUrl":"10.1038/s43588-026-01039-0","url":null,"abstract":"Peer review in academic research aims to ensure factual correctness and identify work of high scientific potential, but rapid submission growth has made this increasingly difficult. Here we investigate an additional measure for identifying high-impact research: authors’ rankings of their own submissions to the same artificial intelligence (AI) conference. Grounded in game-theoretic reasoning, we hypothesize that self-rankings are informative because authors understand their work’s conceptual depth and long-term promise. We tested this hypothesis in a large-scale experiment at a leading AI conference. Over more than a year, papers ranked highest by their authors received twice as many citations as their lowest-ranked counterparts, and self-rankings were especially effective at identifying highly cited papers. Self-rankings also outperformed peer-review scores in predicting future citation counts. These findings show that authors’ self-rankings can complement peer review when identifying high-impact AI research. The study finds that authors’ rankings of their own AI conference papers predict later citations better than peer-review scores, suggesting that self-rankings could provide a simple complement to peer review.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 9","pages":"939-944"},"PeriodicalIF":20.3,"publicationDate":"2026-08-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s43588-026-01039-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148815123","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":"Responsible and transparent use of AI in scientific publishing","authors":"","doi":"10.1038/s43588-026-01043-4","DOIUrl":"10.1038/s43588-026-01043-4","url":null,"abstract":"As AI becomes increasingly embedded in research and scientific publishing, transparency, accountability, and human oversight remain essential to safeguarding research integrity.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 8","pages":"803-803"},"PeriodicalIF":20.3,"publicationDate":"2026-08-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s43588-026-01043-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148785312","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":"Robust generative transition-state models for unseen chemistry.","authors":"Samir Darouich, Jacob W Toney, Weiliang Luo, Johannes Kästner, Mathias Niepert, Heather J Kulik","doi":"10.1038/s43588-026-01034-5","DOIUrl":"10.1038/s43588-026-01034-5","url":null,"abstract":"<p><p>Transition states (TSs) govern the rates and outcomes of chemical reactions, making their accurate prediction a central challenge in computational chemistry. Although recent machine learning models achieve near-chemical accuracy in the prediction of TS structures and the associated reaction barriers for small organic reactions, their ability to generalize beyond the training domain remains largely unexplored. Here we introduce targeted benchmarks to probe chemical and structural novelty in generative TS prediction. Building on Transition1x, a large-scale dataset of reactions involving small organic molecules, we curate extensions incorporating controlled elemental substitutions and diverse transition metal complexes (TMCs), which reveal fundamental limitations of generative models in the generalization to previously unseen elements. To address this challenge, we introduce a self-supervised pretraining strategy based on equilibrium conformers that exposes generative TS models to novel chemical environments before targeted fine-tuning. Across the proposed benchmarks, self-supervised pretraining substantially improves TS prediction for previously unseen systems, lowering the median root-mean-square deviation of TS geometries on Transition1x-TMC reactions and reducing fine-tuning data requirements, enabling reliable performance even in low-data regimes.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":20.3,"publicationDate":"2026-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148725557","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":"A universal metamaterial generative model","authors":"Chao Qian,&nbsp;Hongsheng Chen","doi":"10.1038/s43588-026-01032-7","DOIUrl":"10.1038/s43588-026-01032-7","url":null,"abstract":"A universal generative model — InfoMetaGen — provides an inverse design strategy for subwavelength meta-atoms and inhomogeneous metamaterial distributions.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 8","pages":"810-811"},"PeriodicalIF":20.3,"publicationDate":"2026-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148715037","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":"Robust out-of-distribution prediction of Buchwald–Hartwig reactions","authors":"Paulo Neves,&nbsp;Bo Hao,&nbsp;Santeri Aikonen,&nbsp;Justin B. Diccianni,&nbsp;Jörg K. Wegner,&nbsp;Philippe Schwaller,&nbsp;Iulia I. Strambeanu","doi":"10.1038/s43588-026-01017-6","DOIUrl":"10.1038/s43588-026-01017-6","url":null,"abstract":"The Buchwald–Hartwig cross-coupling is a cornerstone of modern pharmaceutical synthesis, yet predictive modeling of its outcomes remains constrained by data quality and chemical space coverage. Electronic laboratory notebooks contain heterogeneous, noisy records, while open-source high-throughput experimentation (HTE) datasets are fragmented and narrow in scope, leading to poor model performance on unseen substrates and conditions. Here we introduce a framework that systematically standardizes and integrates multiple reaction datasets into a high-quality, unique-structure-per-entity dataset, coupled with active learning to strategically expand chemical space. By merging published Buchwald–Hartwig HTE data with new experimental results, we achieve a model with predictive power across novel substrates and conditions, delivering improved out-of-distribution predictions compared with previous approaches. Crucially, model-guided reagent recommendations were validated experimentally, confirming the framework’s utility to uncover unexplored reactivity. This work establishes a blueprint for robust machine learning in synthetic chemistry and enables preemptive in silico reagent screening to accelerate pharmaceutical discovery. A predictive model capable of generalizing to previously unseen Buchwald–Hartwig chemical space is built to enable rapid, in silico optimization, reducing reaction scouting time from weeks to minutes.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 9","pages":"1015-1023"},"PeriodicalIF":20.3,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s43588-026-01017-6.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148708788","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":"Model-guided data production unlocks reliable reaction predictions","authors":"","doi":"10.1038/s43588-026-01018-5","DOIUrl":"10.1038/s43588-026-01018-5","url":null,"abstract":"A newly generated high-throughput experimentation (HTE) dataset is integrated with open-source data to produce a large and high-quality Buchwald–Hartwig reaction dataset for training machine learning models. The combination of HTE and active learning enabled the development of a robust machine-learning model with reliable out-of-distribution predictive power.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 9","pages":"921-922"},"PeriodicalIF":20.3,"publicationDate":"2026-08-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148708834","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":"Quantum scaling advantage using reduced search in an NP-complete problem","authors":"","doi":"10.1038/s43588-026-01033-6","DOIUrl":"10.1038/s43588-026-01033-6","url":null,"abstract":"An empirical scaling advantage for solving representative NP-complete problems is demonstrated by integrating a restricting space reduction algorithm with quantum solvers. Consequently, quantum resources are shown to grow more slowly than classical counterparts.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 8","pages":"814-815"},"PeriodicalIF":20.3,"publicationDate":"2026-08-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148671442","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":"Provenance grounds trust in autonomous science.","authors":"Robert MacKnight, Ivan M Novitskiy, Rushik Radadiya, Gabe Gomes","doi":"10.1038/s43588-026-01035-4","DOIUrl":"https://doi.org/10.1038/s43588-026-01035-4","url":null,"abstract":"","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 8","pages":"804-807"},"PeriodicalIF":20.3,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148802673","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":"Continual integration of single-cell multimodal data with MIRACLE","authors":"Jiahao Zhou,&nbsp;Jing Wang,&nbsp;Shuofeng Hu,&nbsp;Tongtong Kan,&nbsp;Chao Feng,&nbsp;Xiaohan Qiang,&nbsp;Guohua Dong,&nbsp;Jinhui Shi,&nbsp;Runyan Liu,&nbsp;Xiaochen Bo,&nbsp;Le Ou-Yang,&nbsp;Xiaomin Ying,&nbsp;Zhen He","doi":"10.1038/s43588-026-01030-9","DOIUrl":"10.1038/s43588-026-01030-9","url":null,"abstract":"Single-cell sequencing has transformed our understanding of cellular heterogeneity, enabling the construction of multi-omics atlases through data integration. However, conventional atlas updates require full reintegration of all datasets, creating scalability challenges that limit the timeliness and adaptability of biomedical research. Here we present multimodal integration with continual learning (MIRACLE), an online learning framework for scalable multimodal integration. Using dynamic architecture adaptation and data rehearsal, MIRACLE continually integrates diverse datasets while preserving biological fidelity. Across evaluations, MIRACLE achieves accurate online integration with substantially improved efficiency, refining and expanding atlases with new cross-modal, cross-tissue and cross-disease data. Applied to respiratory infections, it reveals both shared and pathogen-specific immune mechanisms in coronavirus disease 2019, influenza A and tuberculosis. Overall, MIRACLE provides an efficient and collaborative solution for the continual integration, sharing and exploration of biological knowledge. MIRACLE is an online continual learning framework that efficiently integrates single-cell multimodal data across batches, modalities, tissues, and diseases.","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":"6 9","pages":"988-1004"},"PeriodicalIF":20.3,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.comhttps://www.nature.com/articles/s43588-026-01030-9.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148649966","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}