Frank Brückerhoff-Plückelmann, Anna P Ovvyan, Akhil Varri, Hendrik Borras, Bernhard Klein, Lennart Meyer, C David Wright, Harish Bhaskaran, Ghazi Sarwat Syed, Abu Sebastian, Holger Fröning, Wolfram Pernice
{"title":"Probabilistic photonic computing for AI.","authors":"Frank Brückerhoff-Plückelmann, Anna P Ovvyan, Akhil Varri, Hendrik Borras, Bernhard Klein, Lennart Meyer, C David Wright, Harish Bhaskaran, Ghazi Sarwat Syed, Abu Sebastian, Holger Fröning, Wolfram Pernice","doi":"10.1038/s43588-025-00800-1","DOIUrl":"10.1038/s43588-025-00800-1","url":null,"abstract":"<p><p>Probabilistic computing excels in approximating combinatorial problems and modeling uncertainty. However, using conventional deterministic hardware for probabilistic models is challenging: (pseudo) random number generation introduces computational overhead and additional data shuffling. Therefore, there is a pressing need for different probabilistic computing architectures that achieve low latencies with reasonable energy consumption. Physical computing offers a promising solution, as these systems do not rely on an abstract deterministic representation of data but directly encode the information in physical quantities, enabling inherent probabilistic architectures utilizing entropy sources. Photonic computing is a prominent variant of physical computing due to the large available bandwidth, several orthogonal degrees of freedom for data encoding and optimal properties for in-memory computing and parallel data transfer. Here, we highlight key developments in physical photonic computing and photonic random number generation. We further provide insights into the realization of probabilistic photonic processors and their impact on artificial intelligence systems and future challenges.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":"377-387"},"PeriodicalIF":12.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144133377","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":"Making the most of presubmission enquiries.","authors":"","doi":"10.1038/s43588-025-00817-6","DOIUrl":"10.1038/s43588-025-00817-6","url":null,"abstract":"","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":"355"},"PeriodicalIF":12.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144129670","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":"DNA data storage for biomedical images using HELIX.","authors":"Guanjin Qu, Zihui Yan, Xin Chen, Huaming Wu","doi":"10.1038/s43588-025-00793-x","DOIUrl":"10.1038/s43588-025-00793-x","url":null,"abstract":"<p><p>Deoxyribonucleic acid (DNA) data storage is expected to become a key medium for large-scale data. Biomedical data images typically require substantial storage space over extended periods, making them ideal candidates for DNA data storage. However, existing DNA data storage models are primarily designed for generic files and lack a comprehensive retrieval system for biomedical images. Here, to address this, we propose HELIX, a DNA-based storage system for biomedical images. HELIX introduces an image-compression algorithm tailored to the characteristics of biomedical images, achieving high compression rates and robust error tolerance. In addition, HELIX incorporates an error-correcting encoding algorithm that eliminates the need for indexing, enhancing storage density and decoding speed. We utilize a deep learning-based image repair algorithm for the predictive restoration of partially missing image blocks. In our in vitro experiments, we successfully stored two spatiotemporal genomics images. This sequencing process achieved 97.20% image quality at a depth of 7× coverage.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":"397-404"},"PeriodicalIF":12.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144043618","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}
Qi Yu, Ruitao Ma, Chen Qu, Riccardo Conte, Apurba Nandi, Priyanka Pandey, Paul L Houston, Dong H Zhang, Joel M Bowman
{"title":"Extending atomic decomposition and many-body representation with a chemistry-motivated approach to machine learning potentials.","authors":"Qi Yu, Ruitao Ma, Chen Qu, Riccardo Conte, Apurba Nandi, Priyanka Pandey, Paul L Houston, Dong H Zhang, Joel M Bowman","doi":"10.1038/s43588-025-00790-0","DOIUrl":"10.1038/s43588-025-00790-0","url":null,"abstract":"<p><p>Most widely used machine learning potentials for condensed-phase applications rely on many-body permutationally invariant polynomial or atom-centered neural networks. However, these approaches face challenges in achieving chemical interpretability in atomistic energy decomposition and fully matching the computational efficiency of traditional force fields. Here we present a method that combines aspects of both approaches and balances accuracy and force-field-level speed. This method utilizes a monomer-centered representation, where the potential energy is decomposed into the sum of chemically meaningful monomeric energies. The structural descriptors of monomers are described by one-body and two-body effective interactions, enforced by appropriate sets of permutationally invariant polynomials as inputs to the feed-forward neural networks. Systematic assessments of models for gas-phase water trimer, liquid water, methane-water cluster and liquid carbon dioxide are performed. The improved accuracy, efficiency and flexibility of this method have promise for constructing accurate machine learning potentials and enabling large-scale quantum and classical simulations for complex molecular systems.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":"418-426"},"PeriodicalIF":12.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144065335","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":"Evaluating and mitigating bias in AI-based medical text generation.","authors":"Xiuying Chen, Tairan Wang, Juexiao Zhou, Zirui Song, Xin Gao, Xiangliang Zhang","doi":"10.1038/s43588-025-00789-7","DOIUrl":"10.1038/s43588-025-00789-7","url":null,"abstract":"<p><p>Artificial intelligence (AI) systems, particularly those based on deep learning models, have increasingly achieved expert-level performance in medical applications. However, there is growing concern that such AI systems may reflect and amplify human bias, reducing the quality of their performance in historically underserved populations. The fairness issue has attracted considerable research interest in the medical imaging classification field, yet it remains understudied in the text-generation domain. In this study, we investigate the fairness problem in text generation within the medical field and observe substantial performance discrepancies across different races, sexes and age groups, including intersectional groups, various model scales and different evaluation metrics. To mitigate this fairness issue, we propose an algorithm that selectively optimizes those underserved groups to reduce bias. Our evaluations across multiple backbones, datasets and modalities demonstrate that our proposed algorithm enhances fairness in text generation without compromising overall performance.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":"388-396"},"PeriodicalIF":12.0,"publicationDate":"2025-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144058305","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}
Weihua Li, Hongwei Zheng, Jennie E Brand, Aaron Clauset
{"title":"Gender and racial diversity socialization in science.","authors":"Weihua Li, Hongwei Zheng, Jennie E Brand, Aaron Clauset","doi":"10.1038/s43588-025-00795-9","DOIUrl":"https://doi.org/10.1038/s43588-025-00795-9","url":null,"abstract":"<p><p>Scientific collaboration networks are a form of unequally distributed social capital that shapes both researcher job placement and long-term research productivity and prominence. However, the role of collaboration networks in shaping the gender and racial diversity of the scientific workforce remains unclear. Here we propose a computational null model to investigate the degree to which early-career scientific collaborators with representationally diverse cohorts of scholars are associated with forming or participating in more diverse research groups as established researchers. When testing this hypothesis using two large-scale, longitudinal datasets on scientific collaborations, we find that the gender and racial diversity in a researcher's early-career collaboration environment is strongly associated with the diversity of their collaborators in their established period. This diversity-association effect is particularly prominent for men. Coupled with gender and racial homophily between advisors and advisees, collaborator diversity represents a generational effect that partly explains why changes in representation within the scientific workforce tend to happen very slowly.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":""},"PeriodicalIF":12.0,"publicationDate":"2025-04-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144060512","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":"Multimodal learning for mapping genotype-phenotype dynamics.","authors":"Farhan Khodaee, Rohola Zandie, Elazer R Edelman","doi":"10.1038/s43588-024-00765-7","DOIUrl":"10.1038/s43588-024-00765-7","url":null,"abstract":"<p><p>How complex phenotypes emerge from intricate gene expression patterns is a fundamental question in biology. Integrating high-content genotyping approaches such as single-cell RNA sequencing and advanced learning methods such as language models offers an opportunity for dissecting this complex relationship. Here we present a computational integrated genetics framework designed to analyze and interpret the high-dimensional landscape of genotypes and their associated phenotypes simultaneously. We applied this approach to develop a multimodal foundation model to explore the genotype-phenotype relationship manifold for human transcriptomics at the cellular level. Analyzing this joint manifold showed a refined resolution of cellular heterogeneity, uncovered potential cross-tissue biomarkers and provided contextualized embeddings to investigate the polyfunctionality of genes shown for the von Willebrand factor (VWF) gene in endothelial cells. Overall, this study advances our understanding of the dynamic interplay between gene expression and phenotypic manifestation and demonstrates the potential of integrated genetics in uncovering new dimensions of cellular function and complexity.</p>","PeriodicalId":74246,"journal":{"name":"Nature computational science","volume":" ","pages":"333-344"},"PeriodicalIF":12.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143061684","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}