Nature Computational Science
banner
natcomputsci.nature.com
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
🚨Out now!⚛️🛠️We celebrate the 100th anniversary of the advent quantum mechanics with a Focus issue that covers recent breakthroughs, unmet challenges, and pathways for moving forward to address such challenges. www.nature.com/collections/...

🧵(1/13)
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
🚨Out now!⚛️🛠️We celebrate the 100th anniversary of the advent quantum mechanics with a Focus issue that covers recent breakthroughs, unmet challenges, and pathways for moving forward to address such challenges. www.nature.com/collections/...

🧵(1/13)
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
📢What happens to all the electronic waste coming from computing? @sophurky.bsky.social investigates this issue is a recent News Feature. www.nature.com/articles/s43... #ArtificialIntelligence

🔓 rdcu.be/eVi1O
The afterlife of 20 million AI chips - Nature Computational Science
Data-center operators try to recycle retired hardware, but a broken global recycling infrastructure stands in the way.
www.nature.com
December 18, 2025 at 1:54 PM
🚨We are hiring! We are seeking an editor with experience in computational biology (genome informatics and/or computational structural biology preferred) to join the team. Interested? Apply now! springernature.wd3.myworkdayjobs.com/SpringerNatu... 🖥️ 🧬 #ResearchPublishing
December 9, 2025 at 4:21 PM
📢Jan Ewald and colleagues from @scadsai.bsky.social introduce an open-source tool called AUTOENCODIX, developed to enable reproducible comparison of vanilla, variational, stacked, ontology-based, and cross-modal autoencoders for biological molecular profiling data. www.nature.com/articles/s43...
AUTOENCODIX: a generalized and versatile framework to train and evaluate autoencoders for biological representation learning and beyond - Nature Computational Science
An open-source framework called AUTOENCODIX is developed to enable reproducible comparison of vanilla, variational, stacked, ontology-based and cross-modal autoencoders.
www.nature.com
December 9, 2025 at 4:10 PM
📢Out now! @dashunwang.bsky.social and colleagues introduce SciSciGPT, a prototype AI collaborator for the domain of science of science that streamlines a wide range of empirical and analytical research tasks. www.nature.com/articles/s43... #cssky
SciSciGPT: advancing human–AI collaboration in the science of science - Nature Computational Science
SciSciGPT is an open-source prototype AI collaborator that explores the use of LLM research tools to automate workflows, support diverse analytical approaches and enhance reproducibility in the domain...
www.nature.com
December 9, 2025 at 4:00 PM
📢 @emorychannano.bsky.social, @samblau.bsky.social and colleagues develop a DL approach for optimizing the nonlinear optical properties of core-shell upconverting nanoparticles, uncovering photophysical design rules and a roadmap for DL in nanoscience. www.nature.com/articles/s43...

🔓 rdcu.be/eTH72
Gradient-based optimization of complex nanoparticle heterostructures enabled by deep learning on heterogeneous graphs - Nature Computational Science
Graph neural networks built on physically motivated representations enable gradient-based optimization of complex upconverting nanoparticle heterostructures, revealing photophysical design rules and a...
www.nature.com
December 8, 2025 at 5:21 PM
📢Bo Zhang and colleagues present ChemAHNet, a tool for predicting stereoselectivity and absolute configuration in asymmetric hydrogenation of olefins. www.nature.com/articles/s43... #chemsky

🔓 rdcu.be/eTl2Q
Chemistry-informed deep learning model for predicting stereoselectivity and absolute configuration in asymmetric hydrogenation - Nature Computational Science
This study introduces ChemAHNet, a deep learning model that predicts stereoselectivity and absolute configurations in the asymmetric hydrogenation of olefins with two prochiral centers, providing a br...
www.nature.com
December 5, 2025 at 7:14 PM
📢Out now! Ouyang Zhu and Jun Li from @notredame.bsky.social present Scouter, a lightweight AI method that can predict genome-wide transcriptional responses to single- and two-gene perturbations using LLM embeddings. www.nature.com/articles/s43... 🖥️ 🧬
Scouter predicts transcriptional responses to genetic perturbations with large language model embeddings - Nature Computational Science
A lightweight AI method called Scouter that predicts genome-wide transcriptional responses to single- and two-gene perturbations using large language model embeddings is presented and achieves substan...
www.nature.com
December 5, 2025 at 7:10 PM
📢Lei Xing and colleagues present an unsupervised DL method that uncovers clear trajectories of brain activity, effectively distinguishing cognitive events, learning stages, and active vs passive movement. www.nature.com/articles/s43... #compneurosky

🔓 rdcu.be/eS85Y
Revealing neurocognitive and behavioral patterns through unsupervised manifold learning of dynamic brain data - Nature Computational Science
BCNE, an unsupervised deep-learning method, reveals clear trajectories of brain activity and effectively distinguishes cognitive events, learning stages and active versus passive movement, outperformi...
www.nature.com
December 4, 2025 at 1:35 PM
📢Bahar Behsaz, Hosein Mohimani and colleagues introduce a scalable mass spectral search tool that identifies both known molecules and structural variants by estimating match significance. www.nature.com/articles/s43... 🖥️ 🧬 #chemsky

🔓 rdcu.be/eSAr3
Identifying variants of molecules through database search of mass spectra - Nature Computational Science
The authors present a scalable mass spectral search tool that identifies both known molecules and structural variants by estimating match significance. The method revealed biosynthetic pathways in Str...
www.nature.com
December 1, 2025 at 4:55 PM
🚨Our November issue is now live, and it includes a study on how LLMs align with the reading brain, a generative model for structure-based molecular design, and much more! Check it out! www.nature.com/natcomputsci...
November 21, 2025 at 3:27 PM
📢How should authors go about putting the point-by-point response to reviewers' document together, in order to make the process smoother and more efficient for authors, editors, and reviewers? Check out our latest Editorial! www.nature.com/articles/s43... #SciencePublishing #ResearchPublishing
How to respond to reviewers - Nature Computational Science
We provide recommendations on how to write an effective point-by-point response document.
www.nature.com
November 21, 2025 at 3:14 PM
📢Hao Sun and colleagues introduce Parallel Symbolic Enumeration (PSE) for discovering physical laws from limited data, outperforming state-of-the-art methods by evaluating millions of expressions in parallel and reusing computations. www.nature.com/articles/s43... ⚛️
Discovering physical laws with parallel symbolic enumeration - Nature Computational Science
In this work, the authors introduce parallel symbolic enumeration (PSE), a model that discovers physical laws from data with improved accuracy and speed. By evaluating millions of expressions in paral...
www.nature.com
November 21, 2025 at 2:57 PM
📢Research Highlights out today! We highlight work by @walter4c.bsky.social, @matteocinelli.bsky.social, and colleagues on how LLMs generate judgments about reliability and political bias, and how their procedures compare to human evaluation. www.nature.com/articles/s43... #cssky
How LLMs generate judgments - Nature Computational Science
Nature Computational Science - How LLMs generate judgments
www.nature.com
November 20, 2025 at 6:30 PM
📢Out now: Peng Zhang, Jian Ji and colleagues present PerioGT, a framework for polymer property prediction that enhances generalization under data scarcity. www.nature.com/articles/s43... #chemsky

🔓 rdcu.be/eQYFI
Periodicity-aware deep learning for polymers - Nature Computational Science
PerioGT is a self-supervised learning framework for polymer property prediction, integrating periodicity priors and additional conditions to enhance generalization under data scarcity and enable broad...
www.nature.com
November 20, 2025 at 3:58 PM
📢 @samnastase.bsky.social and colleagues show that aligning ECoG data into a shared space improves how well LLMs predict brain activity during language comprehension. www.nature.com/articles/s43... #compneuro #Neuroscience #ArtificialIntelligence

🔓 rdcu.be/eQzYm
Aligning brains into a shared space improves their alignment with large language models - Nature Computational Science
Aligning electrocorticography data into a shared space improves how large language models predict brain activity during language comprehension, enhancing encoding accuracy, cross-participant generaliz...
www.nature.com
November 18, 2025 at 3:29 PM
📢 @fionakolbinger.bsky.social and @jnkt.bsky.social characterize the discordance between metrics used to evaluate AI tools and their clinical impact, proposing a framework to reduce this disconnect. www.nature.com/articles/s43... @tudresden.bsky.social @ekfzdigital.bsky.social

🔓 rdcu.be/eQmQp
Adaptive validation strategies for real-world clinical artificial intelligence - Nature Computational Science
Technical metrics used to evaluate medical artificial intelligence tools often fail to predict their clinical impact. We characterize this discordance and propose a framework of study designs to guide...
www.nature.com
November 17, 2025 at 3:23 PM
📢Yi Yang and colleagues report two efficient methods to compute topological surface states in photonic and acoustic systems, cutting memory and time use by up to 100-fold. www.nature.com/articles/s43... ⚛️

🔓 rdcu.be/ePXEz
Efficient algorithms for the surface density of states in topological photonic and acoustic systems - Nature Computational Science
This study reports two efficient methods—cyclic reduction and transfer matrix—to compute topological surface states in photonic and acoustic systems, cutting memory and time use by up to 100-fold and ...
www.nature.com
November 14, 2025 at 4:54 PM
📢Chang-Yu Hsieh and colleagues introduce SynGFN, a molecular design tool that enables the assembly of molecules from synthesizable building blocks. www.nature.com/articles/s43... #chemsky

🔓 rdcu.be/ePMAP
SynGFN: learning across chemical space with generative flow-based molecular discovery - Nature Computational Science
A persistent gap from theoretical molecules to experimentally viable compounds has hindered the practical adoption of generative algorithms. This study proposes SynGFN as a bridge linking molecular de...
www.nature.com
November 13, 2025 at 4:20 PM
📢Yiqing Zhou, Eun-Ah Kim and colleagues report an ML decoder that efficiently corrects errors in quantum logical circuits with entangling gates, with the decoder achieving competitive accuracy while running much faster than conventional methods. www.nature.com/articles/s43... ⚛️
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
November 5, 2025 at 4:43 PM
Sandro Lera and colleagues introduce a data-driven method for ranking law firms based on litigation outcomes, revealing that traditional reputation-based rankings do not reflect legal performance accurately. www.nature.com/articles/s43... #cssky #MLSky
Data-driven law firm rankings to reduce information asymmetry in legal disputes - Nature Computational Science
This study introduces a data-driven method for ranking law firms based on litigation outcomes, revealing that traditional reputation-based rankings do not reflect legal performance accurately.
www.nature.com
October 31, 2025 at 6:35 PM
Guang Chen and colleagues present a deep learning model that integrates unpaired spatial multi-omics data and enables unsupervised cross-modal prediction, aiding spatial domain identification and downstream biological analysis. www.nature.com/articles/s43... 🖥️ 🧬

🔓 rdcu.be/eNjse
Integrative deep learning of spatial multi-omics with SWITCH - Nature Computational Science
In this study the authors present SWITCH, a deep learning model that integrates unpaired spatial multi-omics data and enables unsupervised cross-modal prediction, aiding spatial domain identification ...
www.nature.com
October 29, 2025 at 3:36 PM
📢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... ⚛️
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
October 24, 2025 at 4:06 PM
📢 Yong Li and colleagues report a neural symbolic regression method that uncovers network dynamics from data, refining biological and ecological models and revealing new insights into disease transmission. www.nature.com/articles/s43... #complexity #NetSci

🔓 rdcu.be/eMoSt
Discover network dynamics with neural symbolic regression - Nature Computational Science
This study presents a neural symbolic regression approach that autonomously uncovers network dynamics from data. It was demonstrated to refine existing models of gene regulation and ecology, and ident...
www.nature.com
October 23, 2025 at 2:32 PM
📢 Philipp Grohs and colleagues present an approach that reduces the computational cost to model and compute crystalline materials, such as graphene or lithium hydride, by a factor of 50 compared with previous work. www.nature.com/articles/s43... ⚛️
Transferable neural wavefunctions for solids - Nature Computational Science
Investigating crystalline materials often requires calculations for many variations of a system, substantially increasing the computational burden. By training a transferable neural wavefunction acros...
www.nature.com
October 22, 2025 at 2:24 PM