Nature Computational Science
@natcomputsci.nature.com
A @natureportfolio.nature.com journal on mathematical models and computational methods/tools that help advance science in multiple disciplines. https://www.nature.com/natcomputsci
Pinned
🚨Our January issue is now live, including an approach for discovering mathematical expressions from data, a framework for digital twins and workflows of chemistry laboratories, the introduction of our 5-year anniversary Series, and much more! www.nature.com/natcomputsci...
📢New Article alert! Elsa Olivetti and colleagues develop DiffSyn, a generative approach for predicting materials synthesis recipes. www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/e1ViT
🔓 rdcu.be/e1ViT
DiffSyn: a generative diffusion approach to materials synthesis planning - Nature Computational Science
A generative AI approach is developed for predicting materials synthesis recipes—a complex challenge in materials science. Using this approach, the authors experimentally synthesized a material using ...
www.nature.com
February 2, 2026 at 2:36 PM
📢New Article alert! Elsa Olivetti and colleagues develop DiffSyn, a generative approach for predicting materials synthesis recipes. www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/e1ViT
🔓 rdcu.be/e1ViT
📢Out now! Sebastiano Cultrera di Montesano, Peter S. Winter, @lcrawford.bsky.social, and colleagues present a hierarchical cross-entropy loss that improves performance of single-cell annotation models. www.nature.com/articles/s43... 🖥️ 🧬
Improving atlas-scale single-cell annotation models with hierarchical cross-entropy loss - Nature Computational Science
A hierarchical cross-entropy loss is presented, which incorporates ontology structure into training and improves the out-of-distribution performance of large-scale single-cell annotation models withou...
www.nature.com
January 30, 2026 at 3:19 PM
📢Out now! Sebastiano Cultrera di Montesano, Peter S. Winter, @lcrawford.bsky.social, and colleagues present a hierarchical cross-entropy loss that improves performance of single-cell annotation models. www.nature.com/articles/s43... 🖥️ 🧬
📢Out now! @codingfisch.bsky.social and colleagues present deepmriprep, a tool that leverages neural networks to enable 37x faster Voxel-based Morphometry preprocessing of MRI data than existing methods. www.nature.com/articles/s43... #compneurosky
deepmriprep: voxel-based morphometry preprocessing via deep neural networks - Nature Computational Science
deepmriprep leverages neural networks to enable voxel-based morphometry preprocessing of MRI data that is 37× faster than existing methods while achieving comparable accuracy in segmentation, registra...
www.nature.com
January 30, 2026 at 3:14 PM
📢Out now! @codingfisch.bsky.social and colleagues present deepmriprep, a tool that leverages neural networks to enable 37x faster Voxel-based Morphometry preprocessing of MRI data than existing methods. www.nature.com/articles/s43... #compneurosky
Many more commentary pieces are coming this year for our special Series! Stay tuned!
🧵(4/4)
🧵(4/4)
January 29, 2026 at 5:05 PM
Many more commentary pieces are coming this year for our special Series! Stay tuned!
🧵(4/4)
🧵(4/4)
In the first opinion piece of the Series, Omer San and colleagues discuss the timely topic of digital twins and their evolution from analytical instruments to autonomous systems. www.nature.com/articles/s43...
🧵(3/4)
🧵(3/4)
The evolution of digital twins from reactive to agentic systems - Nature Computational Science
Digital twins are evolving into self-learning, autonomous systems that link models, data and human interaction. Realizing their full potential depends on interoperability, standardization and the inte...
www.nature.com
January 29, 2026 at 5:05 PM
In the first opinion piece of the Series, Omer San and colleagues discuss the timely topic of digital twins and their evolution from analytical instruments to autonomous systems. www.nature.com/articles/s43...
🧵(3/4)
🧵(3/4)
In our Editorial, we reflect on the different topics we have published and highlighted, as well as how we have engaged with the research community. www.nature.com/articles/s43...
🧵(2/4)
🧵(2/4)
Turning five - Nature Computational Science
We celebrate the fifth anniversary of Nature Computational Science and reflect on how we have engaged with the research community.
www.nature.com
January 29, 2026 at 5:05 PM
In our Editorial, we reflect on the different topics we have published and highlighted, as well as how we have engaged with the research community. www.nature.com/articles/s43...
🧵(2/4)
🧵(2/4)
🚨Nature Computational Science is turning 5! To celebrate our fifth anniversary, we are launching a Series that includes a selection of articles published over the past five years and specially commissioned opinion pieces, one per issue of 2026. www.nature.com/collections/...
🧵(1/4)
🧵(1/4)
January 29, 2026 at 5:05 PM
🚨Nature Computational Science is turning 5! To celebrate our fifth anniversary, we are launching a Series that includes a selection of articles published over the past five years and specially commissioned opinion pieces, one per issue of 2026. www.nature.com/collections/...
🧵(1/4)
🧵(1/4)
🚨Our January issue is now live, including an approach for discovering mathematical expressions from data, a framework for digital twins and workflows of chemistry laboratories, the introduction of our 5-year anniversary Series, and much more! www.nature.com/natcomputsci...
January 29, 2026 at 5:01 PM
🚨Our January issue is now live, including an approach for discovering mathematical expressions from data, a framework for digital twins and workflows of chemistry laboratories, the introduction of our 5-year anniversary Series, and much more! www.nature.com/natcomputsci...
📢Out now! @stemartiniani.bsky.social and colleagues present PropMolFlow, a flow-matching method for property-guided molecule generation. #MoleculeDiscovery #FlowMatching www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/eZ5cG
🔓 rdcu.be/eZ5cG
PropMolFlow: property-guided molecule generation with geometry-complete flow matching - Nature Computational Science
PropMolFlow is a flow-matching method for property-guided molecule generation that matches diffusion model performance while generating stable, valid structures more quickly and enabling the discovery...
www.nature.com
January 21, 2026 at 1:48 PM
📢Out now! @stemartiniani.bsky.social and colleagues present PropMolFlow, a flow-matching method for property-guided molecule generation. #MoleculeDiscovery #FlowMatching www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/eZ5cG
🔓 rdcu.be/eZ5cG
📢Kun Qu and colleagues present SPEED, a deep matrix factorization framework that leverages atlas-level single-cell epigenomic data to denoise spatial epigenomics data. www.nature.com/articles/s43... #Epigenetics #Epigenomics
🔓 rdcu.be/eYTfT
🔓 rdcu.be/eYTfT
January 13, 2026 at 3:19 PM
📢Kun Qu and colleagues present SPEED, a deep matrix factorization framework that leverages atlas-level single-cell epigenomic data to denoise spatial epigenomics data. www.nature.com/articles/s43... #Epigenetics #Epigenomics
🔓 rdcu.be/eYTfT
🔓 rdcu.be/eYTfT
📢Out now! Li Jin and colleagues present MAPLE, a pairwise-learning framework for reliable and privacy-preserving prediction of epigenetic age and disease risk. www.nature.com/articles/s43... #Epigenetics #Epigenomics
January 13, 2026 at 3:13 PM
📢Out now! Li Jin and colleagues present MAPLE, a pairwise-learning framework for reliable and privacy-preserving prediction of epigenetic age and disease risk. www.nature.com/articles/s43... #Epigenetics #Epigenomics
📢Xiao-Fei Zhang and Luonan Chen present PanoSpace, a framework that enhances low-resolution spatial transcriptomics data to reconstruct single-cell–level, continuous tissue maps. www.nature.com/articles/s43... 🖥️ 🧬
🔓 rdcu.be/eXQdw
🔓 rdcu.be/eXQdw
Unlocking single-cell level and continuous whole-slide insights in spatial transcriptomics with PanoSpace - Nature Computational Science
PanoSpace enhances low-resolution spatial transcriptomics data to reconstruct continuous tissue maps at single-cell resolution. In cancer tissues and mouse brain, it refines cell localization, identit...
www.nature.com
January 6, 2026 at 4:04 PM
📢Xiao-Fei Zhang and Luonan Chen present PanoSpace, a framework that enhances low-resolution spatial transcriptomics data to reconstruct single-cell–level, continuous tissue maps. www.nature.com/articles/s43... 🖥️ 🧬
🔓 rdcu.be/eXQdw
🔓 rdcu.be/eXQdw
An accompanying News & Views by Tong Zhao and Yan Zeng is also available for this paper! www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/eXGQT
🔓 rdcu.be/eXGQT
Digital twins for self-driving chemistry laboratories - Nature Computational Science
Digital twins of self-driving chemistry laboratories may help reduce reliance on costly real-world experimentation and enable the testing of hypothetical automated workflows in silico.
www.nature.com
January 5, 2026 at 7:35 PM
An accompanying News & Views by Tong Zhao and Yan Zeng is also available for this paper! www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/eXGQT
🔓 rdcu.be/eXGQT
📢 @aicooper.bsky.social, @aspuru.bsky.social, @animesh-garg.bsky.social and colleagues introduce MATTERIX, a GPU-accelerated framework for high-fidelity digital twins and workflows of chemistry labs. www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/eXGQM
🔓 rdcu.be/eXGQM
MATTERIX: toward a digital twin for robotics-assisted chemistry laboratory automation - Nature Computational Science
MATTERIX, a multiscale graphics processing unit-accelerated framework for high-fidelity digital twins and workflows of chemistry laboratories, is presented, simulating robot and device operation, flui...
www.nature.com
January 5, 2026 at 7:35 PM
📢 @aicooper.bsky.social, @aspuru.bsky.social, @animesh-garg.bsky.social and colleagues introduce MATTERIX, a GPU-accelerated framework for high-fidelity digital twins and workflows of chemistry labs. www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/eXGQM
🔓 rdcu.be/eXGQM
📢Out now! Woo Youn Kim and colleagues develop a denoising model for capturing molecular energy changes, enabling more accurate and robust molecular structure optimization. www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/eXG5d
🔓 rdcu.be/eXG5d
Riemannian denoising model for molecular structure optimization with chemical accuracy - Nature Computational Science
A denoising model on a Riemannian manifold is developed to better capture molecular energy changes and enable more accurate and robust molecular structure optimization, outperforming conventional Eucl...
www.nature.com
January 5, 2026 at 7:23 PM
📢Out now! Woo Youn Kim and colleagues develop a denoising model for capturing molecular energy changes, enabling more accurate and robust molecular structure optimization. www.nature.com/articles/s43... #chemsky
🔓 rdcu.be/eXG5d
🔓 rdcu.be/eXG5d
📢Yiwen Wang and colleagues present a generative spike-based framework to re-establish functional connectivity across pathway-damaged brain regions, enabling biomimetic neural prostheses and closed-loop brain stimulation. www.nature.com/articles/s43... #compneurosky
🔓 rdcu.be/eXG3F
🔓 rdcu.be/eXG3F
A generative spike prediction model using behavioral reinforcement for re-establishing neural functional connectivity - Nature Computational Science
The study presents a generative spike-based framework to re-establish functional connectivity across pathway-damaged brain regions, enabling biomimetic neural prostheses and closed-loop brain stimulat...
www.nature.com
January 5, 2026 at 7:21 PM
📢Yiwen Wang and colleagues present a generative spike-based framework to re-establish functional connectivity across pathway-damaged brain regions, enabling biomimetic neural prostheses and closed-loop brain stimulation. www.nature.com/articles/s43... #compneurosky
🔓 rdcu.be/eXG3F
🔓 rdcu.be/eXG3F
An accompanying Research Briefing is also available for this paper! www.nature.com/articles/s43... 🖥️ 🧬
🔓 rdcu.be/eXGzQ
🔓 rdcu.be/eXGzQ
Mapping cell–cell communication networks onto cell-state transition trajectories via a dynamic model - Nature Computational Science
The physics-informed coevolution-learning algorithm-based framework CCCvelo infers the spatio-temporal dynamics of cell-state transitions driven by both intercellular communication and intracellular t...
www.nature.com
January 5, 2026 at 6:11 PM
An accompanying Research Briefing is also available for this paper! www.nature.com/articles/s43... 🖥️ 🧬
🔓 rdcu.be/eXGzQ
🔓 rdcu.be/eXGzQ
📢Out now! A new study introduces CCCvelo, a computational tool that uses spatial omics data to identify how cell-cell communication directs cell fate decisions. www.nature.com/articles/s43... 🖥️ 🧬
🔓 rdcu.be/eXGyJ
🔓 rdcu.be/eXGyJ
Decoding cell state transitions driven by dynamic cell–cell communication in spatial transcriptomics - Nature Computational Science
This Article introduces CCCvelo, a computational tool that uses spatial omics data to identify how cell–cell communication directs cell fate decisions, uncovering the spatiotemporal signaling dynamics...
www.nature.com
January 5, 2026 at 6:11 PM
📢Out now! A new study introduces CCCvelo, a computational tool that uses spatial omics data to identify how cell-cell communication directs cell fate decisions. www.nature.com/articles/s43... 🖥️ 🧬
🔓 rdcu.be/eXGyJ
🔓 rdcu.be/eXGyJ
Finally, the Focus also includes additional material published on the topic of quantum mechanics. We very much hope you enjoy it! ⚛️🛠️
www.nature.com/collections/...
🧵(13/13)
www.nature.com/collections/...
🧵(13/13)
Expanding the Frontiers of Computation with Quantum Mechanics
This year marks 100 years since the advent of quantum mechanics, which underpins much of modern quantum physics, chemistry, computing methods and technologies.
www.nature.com
December 23, 2025 at 12:25 AM
Finally, the Focus also includes additional material published on the topic of quantum mechanics. We very much hope you enjoy it! ⚛️🛠️
www.nature.com/collections/...
🧵(13/13)
www.nature.com/collections/...
🧵(13/13)
An accompanying News & Views by Vishwanathan Akshay and Mile Gu is also available for this paper! www.nature.com/articles/s43... ⚛️
🧵(12/13)
🧵(12/13)
Improving the balance of trade-offs in multi-objective optimization with quantum computing - Nature Computational Science
A recent study demonstrates the applicability of quantum computers for multi-objective optimization, bringing quantum computing a step closer towards practical applications.
www.nature.com
December 23, 2025 at 12:25 AM
An accompanying News & Views by Vishwanathan Akshay and Mile Gu is also available for this paper! www.nature.com/articles/s43... ⚛️
🧵(12/13)
🧵(12/13)
Stefan Woerner and colleagues investigate using quantum computing to tackle multi-objective optimization, showing promising results on IBM Quantum computer when compared to classical methods. www.nature.com/articles/s43... ⚛
🧵(11/13)
🧵(11/13)
Quantum approximate multi-objective optimization - Nature Computational Science
This study explores the use of quantum computing to address multi-objective optimization challenges. By using a low-depth quantum approximate optimization algorithm to approximate the optimal Pareto f...
www.nature.com
December 23, 2025 at 12:25 AM
Stefan Woerner and colleagues investigate using quantum computing to tackle multi-objective optimization, showing promising results on IBM Quantum computer when compared to classical methods. www.nature.com/articles/s43... ⚛
🧵(11/13)
🧵(11/13)
An accompanying News & Views by Xiu-Hao Deng and Yuan Xu is also available for this paper! www.nature.com/articles/s43... ⚛
🧵(10/13)
🧵(10/13)
Efficiently decoding quantum errors with machine learning - Nature Computational Science
Quantum computers are inching closer to practical deployment, but shielding fragile quantum information from errors is still very challenging. Now, a machine-learning-based decoder offers a strategy f...
www.nature.com
December 23, 2025 at 12:25 AM
An accompanying News & Views by Xiu-Hao Deng and Yuan Xu is also available for this paper! www.nature.com/articles/s43... ⚛
🧵(10/13)
🧵(10/13)
In another Article, Yiqing Zhou, Eun-Ah Kim, and colleagues report a machine learning decoder for correcting errors in quantum logical circuits with entangling gates. www.nature.com/articles/s43... ⚛️
🧵(9/13)
🧵(9/13)
Learning to decode logical circuits - Nature Computational Science
This study reports a machine learning decoder that efficiently corrects errors in quantum logical circuits with entangling gates. The Multi-Core Circuit Decoder achieves competitive accuracy while run...
www.nature.com
December 23, 2025 at 12:25 AM
In another Article, Yiqing Zhou, Eun-Ah Kim, and colleagues report a machine learning decoder for correcting errors in quantum logical circuits with entangling gates. www.nature.com/articles/s43... ⚛️
🧵(9/13)
🧵(9/13)
An accompanying News & Views by Yubing Qian and Ji Chen is also available for this paper! www.nature.com/articles/s43... ⚛
🧵(8/13)
🧵(8/13)
Down to one network for computing crystalline materials - Nature Computational Science
A recent study proposes using a single neural network to model and compute a wide range of solid-state materials, demonstrating exceptional transferability and substantially reduced computational cost...
www.nature.com
December 23, 2025 at 12:25 AM
An accompanying News & Views by Yubing Qian and Ji Chen is also available for this paper! www.nature.com/articles/s43... ⚛
🧵(8/13)
🧵(8/13)