Article
|
Open Access
Featured
-
-
Article
| Open AccessRobustly federated learning model for identifying high-risk patients with postoperative gastric cancer recurrence
Medical data faces isolation and cross-center performance issues. Here, the authors propose a robust federated learning model to identify high-risk postoperative gastric cancer recurrence, achieving promising results across data from four independent medical institutions.
- Bao Feng
- , Jiangfeng Shi
- & Wansheng Long
-
Article
| Open AccessA dynamic knowledge graph approach to distributed self-driving laboratories
Global challenges demand global solutions. Here, the authors show a distributed self-driving lab architecture in The World Avatar, linking robots in Cambridge and Singapore for asynchronous multi-objective reaction optimisation.
- Jiaru Bai
- , Sebastian Mosbach
- & Markus Kraft
-
Article
| Open AccessSegment anything in medical images
Segmentation is an important fundamental task in medical image analysis. Here the authors show a deep learning model for efficient and accurate segmentation across a wide range of medical image modalities and anatomies.
- Jun Ma
- , Yuting He
- & Bo Wang
-
Article
| Open AccessMesoscale simulation of biomembranes with FreeDTS
In this work, the authors report the FreeDTS software to simulate biomembranes at the mesoscale. The software provides various membrane simulations, focusing on protein organization and shape remodeling. A versatile tool propelling realistic membrane studies and diverse applications.
- Weria Pezeshkian
- & John H. Ipsen
-
Article
| Open AccessEncoding of multi-modal emotional information via personalized skin-integrated wireless facial interface
Technologies in human emotion recognition are challenged by their capability to accurately extract and exploit the emotional information. Lee et al. report a personalized skin-integrated facial interface to sense and combine facial and vocal expression data, enabling enhanced communication in virtual reality.
- Jin Pyo Lee
- , Hanhyeok Jang
- & Jiyun Kim
-
Article
| Open AccessPersonalising intravenous to oral antibiotic switch decision making through fair interpretable machine learning
The decision to switch patients from intravenous to oral antibiotic therapy is important for the individual and wider society. Here, authors show a machine learning model using routine clinical data can predict when a patient could switch.
- William J. Bolton
- , Richard Wilson
- & Timothy M. Rawson
-
Article
| Open AccessCryo-EM structure and B-factor refinement with ensemble representation
Cryo-EM is the go-to method for visualizing large, flexible biomolecules. Here, authors introduce a new Gaussian mixture modelling method for cryo-EM modelling tasks, including refinement, composite map generation and ensemble representation.
- Joseph G. Beton
- , Thomas Mulvaney
- & Maya Topf
-
Article
| Open AccessTowards provably efficient quantum algorithms for large-scale machine-learning models
It is still unclear whether and how quantum computing might prove useful in solving known large-scale classical machine learning problems. Here, the authors show that variants of known quantum algorithms for solving differential equations can provide an advantage in solving some instances of stochastic gradient descent dynamics.
- Junyu Liu
- , Minzhao Liu
- & Liang Jiang
-
Article
| Open AccessSelective knowledge sharing for privacy-preserving federated distillation without a good teacher
While federated learning is promising for efficient collaborative learning without revealing local data, it remains vulnerable to white-box privacy attacks, suffers from high communication overhead, and struggles to adapt to heterogeneous models. Here, the authors show a federated distillation method to tackle these challenges, which leverages the strengths of knowledge distillation in a federated learning setting.
- Jiawei Shao
- , Fangzhao Wu
- & Jun Zhang
-
Article
| Open AccessGene-SGAN: discovering disease subtypes with imaging and genetic signatures via multi-view weakly-supervised deep clustering
Many diseases can display distinct brain imaging phenotypes across individuals, potentially reflecting disease subtypes. However, biological interpretability is limited if the derived subtypes are not associated with genetic drivers or susceptibility factors. Here, the authors describe a deep-learning method that links imaging phenotypes with genetic factors, thereby conferring genetic correlations to the disease subtypes.
- Zhijian Yang
- , Junhao Wen
- & Christos Davatzikos
-
Article
| Open AccessImproving deep neural network generalization and robustness to background bias via layer-wise relevance propagation optimization
Image background features can undesirably affect deep networks’ decisions. Here, the authors show that the optimization of Layer-wise Relevance Propagation explanation heatmaps can hinder such influence, improving out-of-distribution generalization.
- Pedro R. A. S. Bassi
- , Sergio S. J. Dertkigil
- & Andrea Cavalli
-
Article
| Open AccessTemporal dendritic heterogeneity incorporated with spiking neural networks for learning multi-timescale dynamics
Brain-inspired spiking neural networks have shown their capability for effective learning, however current models may not consider realistic heterogeneities present in the brain. The authors propose a neuron model with temporal dendritic heterogeneity for improved neuromorphic computing applications.
- Hanle Zheng
- , Zhong Zheng
- & Lei Deng
-
Article
| Open AccessLearning low-rank latent mesoscale structures in networks
Network structures can be examined at different scales, and subnetworks in the form of motifs can provide insights into global network properties. The authors propose an approach to decompose a network into a set of latent motifs, which can be used for network comparison, network denoising, and edge inference.
- Hanbaek Lyu
- , Yacoub H. Kureh
- & Mason A. Porter
-
Article
| Open AccessWaveguide holography for 3D augmented reality glasses
Near-eye displays are pivotal for building augmented and virtual reality platforms, but hurdles remain in achieving comfort and realistic visual experiences. Here, authors demonstrate compact 3D holographic glasses with focus cues by combining merits of waveguide displays and holographic displays.
- Changwon Jang
- , Kiseung Bang
- & Douglas Lanman
-
Article
| Open AccessDesign automation of microfluidic single and double emulsion droplets with machine learning
Generating microfluidic droplets with application-specific desired characteristics is hard. Here the authors report fluid-agnostic machine learning models capable of accurately predicting device geometries and flow conditions required to generate stable single and double emulsions.
- Ali Lashkaripour
- , David P. McIntyre
- & Polly M. Fordyce
-
Article
| Open AccessTowards a transferable fermionic neural wavefunction for molecules
Neural wavefunctions have become a highly accurate approach to solve the Schrödinger equation. Here, the authors propose an approach to optimize for a generalized wavefunction across compounds, which can help developing a foundation wavefunction model.
- Michael Scherbela
- , Leon Gerard
- & Philipp Grohs
-
Article
| Open AccessMosaic: in-memory computing and routing for small-world spike-based neuromorphic systems
Designing efficient artificial neural network circuit architectures for optimal information routing remains a challenge. Here, the authors propose “Mosaic", the first demonstration of on-chip in-memory spike routing using memristors, optimized for small-world graphs prevalent in mammalian brains, offering orders of magnitude reduction in routing events compared to current approaches.
- Thomas Dalgaty
- , Filippo Moro
- & Melika Payvand
-
Article
| Open AccessRevealing hidden patterns in deep neural network feature space continuum via manifold learning
Existing feature visualisation methods are not well-suited for regression tasks. Here, authors introduce a method to learn the manifold topology related to deep neural network output and target labels and provide insightful visualisations of the high-dimensional features while preserving the local geometry.
- Md Tauhidul Islam
- , Zixia Zhou
- & Lei Xing
-
Article
| Open AccessUncertainties in critical slowing down indicators of observation-based fingerprints of the Atlantic Overturning Circulation
Ben-Yami et al. present methods to quantify uncertainties and address biases in indicators for detecting stability changes in key Earth system components. Data gap filling introduces biases, but the stability decline in the North Atlantic remains significant.
- Maya Ben-Yami
- , Vanessa Skiba
- & Niklas Boers
-
Article
| Open AccessHigh monoclonal neutralization titers reduced breakthrough HIV-1 viral loads in the Antibody Mediated Prevention trials
Antibody Mediated Prevention (AMP) trials showed that the broadly neutralizing antibody VRC01 could prevent some HIV-1 acquisitions. Here the authors use VRC01 levels and the sensitivity of each acquired HIV virus to predict viral loads in the AMP studies and show that VRC01 influenced viral loads, though potency was lower in vivo than expected.
- Daniel B. Reeves
- , Bryan T. Mayer
- & Srilatha Edupuganti
-
Article
| Open AccessOn-chip phonon-magnon reservoir for neuromorphic computing
Developing efficient reservoir computing hardware that combines optically excited acoustic and spin waves with high spatial density remains a challenge. In this work, the authors propose a design capable of recognizing visual shapes drawn by a laser within remarkably confined spaces, down to 10 square microns.
- Dmytro D. Yaremkevich
- , Alexey V. Scherbakov
- & Manfred Bayer
-
Article
| Open AccessStructural plasticity for neuromorphic networks with electropolymerized dendritic PEDOT connections
Neural networks are powerful tools for solving complex problems, but finding the right network topology for a given task remains an open question. Here, the authors propose a bio-inspired artificial neural network hardware able to self-adapt to solve new complex tasks, by autonomously connecting nodes using electropolymerization.
- Kamila Janzakova
- , Ismael Balafrej
- & Fabien Alibart
-
Article
| Open AccessCollaborative and privacy-preserving retired battery sorting for profitable direct recycling via federated machine learning
Unsorted retired batteries pose recycling challenges due to diverse cathodes. Here, the authors propose a privacy-preserving machine learning system that enables accurate sorting with minimal data, important for a sustainable battery recycling industry.
- Shengyu Tao
- , Haizhou Liu
- & Hongbin Sun
-
Article
| Open AccessEarly warning signals have limited applicability to empirical lake data
Abrupt regime shifts could in theory be predicted from early warning signals. Here, the authors show that true critical transitions are challenging to classify in lake planktonic systems, due to mismatches between trophic levels, and reveal uneven performance of early warning signal detection methods.
- Duncan A. O’Brien
- , Smita Deb
- & Christopher F. Clements
-
Article
| Open AccessTransformEHR: transformer-based encoder-decoder generative model to enhance prediction of disease outcomes using electronic health records
Using AI to predict disease can improve interventions slow down or prevent disease. Here, the authors show that generative AI models built on the framework of Transformer, the model that also empowers ChatGPT, can achieve state-of-the-art performance on disease predictions based on longitudinal electronic records.
- Zhichao Yang
- , Avijit Mitra
- & Hong Yu
-
Article
| Open AccessEmulator-based Bayesian inference on non-proportional scintillation models by compton-edge probing
Scintillators are widely used for radiation detection and require proper calibration in such applications. Here the authors discuss a Bayesian inference and machine learning method in combination with the Compton-edge probing that can describe the non-proportional scintillation response of inorganic scintillators.
- David Breitenmoser
- , Francesco Cerutti
- & Sabine Mayer
-
Article
| Open AccessData-driven grading of acute graft-versus-host disease
Acute GVHD severity grading is based on target organ assessments. Here, the authors show that data-driven grading can identify 12 distinct grades with specific aGVHD phenotypes, which are associated with clinical outcomes, and that their method outperformed conventional gradings.
- Evren Bayraktar
- , Theresa Graf
- & Amin T. Turki
-
Article
| Open AccessLearning few-shot imitation as cultural transmission
The modelling of human-like behaviours is one of the challenges in the field of Artificial Intelligence. Inspired by experimental studies of cultural evolution, the authors propose a reinforcement learning approach to generate agents capable of real-time third-person imitation.
- Avishkar Bhoopchand
- , Bethanie Brownfield
- & Lei M. Zhang
-
Article
| Open AccessAll electromagnetic scattering bodies are matrix-valued oscillators
The usual treatment of wave scattering theory relies on a formalism that does not easily allow for probing optimal spectral response. Here, the authors show how an alternative formalism, encoding fundamental principles of causality and passivity, can be used to make sense of complex scattered fields’ structures.
- Lang Zhang
- , Francesco Monticone
- & Owen D. Miller
-
Article
| Open AccessThe D-Mercator method for the multidimensional hyperbolic embedding of real networks
Embedding of complex networks in the latent geometry allows for a better understanding of their features. The authors propose a framework for mapping complex networks into high-dimensional hyperbolic space to capture their intrinsic dimensionality, navigability and community structure.
- Robert Jankowski
- , Antoine Allard
- & M. Ángeles Serrano
-
Article
| Open AccessAssessing the value of integrating national longitudinal shopping data into respiratory disease forecasting models
Novel indicators of infectious disease prevalence could improve real-time surveillance and support healthcare planning. Here, the authors show that sales data for non-prescription medications from a UK high street retailer can improve the accuracy of models forecasting mortality from respiratory infections.
- Elizabeth Dolan
- , James Goulding
- & Laila J. Tata
-
Article
| Open AccessOn-tissue dataset-dependent MALDI-TIMS-MS2 bioimaging
There is a need for dataset-dependent MS2 acquisition in trapped ion mobility spectrometry imaging. Here the authors report spatial ion mobility-scheduled exhaustive fragmentation (SIMSEF) which enables on-tissue metabolite and lipid annotation in mass spectrometry bioimaging studies, and use this to visualise the chemical space in rat brains.
- Steffen Heuckeroth
- , Arne Behrens
- & Robin Schmid
-
Article
| Open AccessImitation dynamics on networks with incomplete information
Studies of the evolution of cooperation often assume information use that is inconsistent with empirical observations. Here, the authors’ research on general imitation dynamics reveals that cooperation is fostered by individuals using less personal information and more social information.
- Xiaochen Wang
- , Lei Zhou
- & Aming Li
-
Article
| Open AccessImpact of vaccinations, boosters and lockdowns on COVID-19 waves in French Polynesia
In this study, the authors develop a mathematical modelling framework to estimate the impacts of non-pharmaceutical interventions and vaccination on COVID-19 incidence. The model accounts for changes in SARS-CoV-2 variant and population immunity, and here they use it to investigate epidemic dynamics in French Polynesia.
- Lloyd A. C. Chapman
- , Maite Aubry
- & Adam J. Kucharski
-
Article
| Open AccessConstructing temporal networks with bursty activity patterns
Many real-world systems are characterized by bursty dynamics with interchanging periods of intense activity and quiescence. The authors propose a method to construct temporal networks that match a given activity pattern, and apply it to empirical bursty patterns.
- Anzhi Sheng
- , Qi Su
- & Joshua B. Plotkin
-
Article
| Open AccessRelational visual representations underlie human social interaction recognition
Humans are adept at recognizing social interactions in visual scenes. Here, the authors develop a computational model of this ability, and show that humans can make complex social interaction judgments using relational visual representations.
- Manasi Malik
- & Leyla Isik
-
Article
| Open AccessA statistical framework for differential pseudotime analysis with multiple single-cell RNA-seq samples
Pseudotime analysis is prevalent in single-cell RNA-seq, but it remains challenging to perform it across multiple samples and experimental conditions. Here, the authors develop Lamian, a computational framework for multi-sample pseudotime analysis that adjusts for biological and technical variation to detect gene program changes along cell trajectories and across conditions.
- Wenpin Hou
- , Zhicheng Ji
- & Hongkai Ji
-
Article
| Open AccessExploiting redundancy in large materials datasets for efficient machine learning with less data
Big data is crucial for machine learning, but the redundancies in the datasets are rarely studied. Here the authors reveal significant redundancy in large materials datasets, showing that up to 95% of data can be removed without impacting prediction accuracy.
- Kangming Li
- , Daniel Persaud
- & Jason Hattrick-Simpers
-
Article
| Open AccessReactivity of complex communities can be more important than stability
Ecosystems must be able to bounce back from perturbations to persist without species extinctions. This study uses theoretical modelling to show the importance of reactivity—how species respond in the short term to perturbations—for assessing the health of complex ecosystems, revealing that it can be a better predictor of extinction risk than stability.
- Yuguang Yang
- , Katharine Z. Coyte
- & Aming Li
-
Article
| Open AccessTraining large-scale optoelectronic neural networks with dual-neuron optical-artificial learning
Optoelectronic neural networks are a promising avenue in AI computing for parallelization, power efficiency, and speed. Here, the authors present a dual-neuron optical-artificial learning approach for training large-scale diffractive neural networks, achieving VGG-level performance on ImageNet in simulation with a network that is 10 times larger than existing ones.
- Xiaoyun Yuan
- , Yong Wang
- & Lu Fang
-
Article
| Open AccessParallel window decoding enables scalable fault tolerant quantum computation
In order to be useful for future large-scale quantum computing, quantum error correction needs to allow for fast enough classical decoding time, while at the moment the slowdown is exponential in the size of the code. Here, the authors remove this roadblock, showing how to parallelize decoding and make the slowdown polynomial.
- Luka Skoric
- , Dan E. Browne
- & Earl T. Campbell
-
Article
| Open AccessExtracting medicinal chemistry intuition via preference machine learning
Over their careers, medicinal chemists develop a gut feeling for what is a promising molecule. Here, the authors use machine learning models to learn this intuition and show that it can be successfully applied in several drug discovery scenarios.
- Oh-Hyeon Choung
- , Riccardo Vianello
- & José Jiménez-Luna
-
Article
| Open AccessExploring decarbonization pathways for USA passenger and freight mobility
Rapid adoption of zero-emission vehicles with a concurrent transition to clean electricity is essential to achieve U.S. transportation decarbonization goals. Managing travel demand can ease this transition by reducing the need for clean electricity supply. @cghoehne, @nrel, #NRELMobility
- Christopher Hoehne
- , Matteo Muratori
- & Ookie Ma
-
Article
| Open AccessHierarchical AI enables global interpretation of culture plates in the era of digital microbiology
DeepColony is a multi-level AI solution for the interpretation of bacterial culturing images in clinical microbiology laboratory automations. Here, the authors show it allows presumptive identification and quantitation of relevant pathogens at both colony- and plate-level.
- Alberto Signoroni
- , Alessandro Ferrari
- & Karissa Culbreath
-
Article
| Open AccessA human-machine collaborative approach measures economic development using satellite imagery
A human-AI collaborative computer vision algorithm produces grid-level economic statistics using satellite images and lightweight human annotation, revealing granular development patterns in North Korea and five other least developed Asian countries.
- Donghyun Ahn
- , Jeasurk Yang
- & Sungwon Park
-
Article
| Open AccessKnowledge-driven design of solid-electrolyte interphases on lithium metal via multiscale modelling
The application of Li metal electrodes in rechargeable batteries is limited by inherent high reactivity. Here, the authors provide model-based insights into the composition and formation mechanisms of the solid-electrolyte interphase on the µs-scale and suggest design strategies for the interphase.
- Janika Wagner-Henke
- , Dacheng Kuai
- & Ulrike Krewer
-
Article
| Open AccessMutant fixation in the presence of a natural enemy
Studies on mutant invasion typically assume populations in isolation, rather than part of an ecological community. Here, the authors use computational models to investigate how enemy-victim interactions influence properties of mutant invasion, showing that selection is substantially weakened.
- Dominik Wodarz
- & Natalia L. Komarova
-
Article
| Open AccessAutomatic correction of performance drift under acquisition shift in medical image classification
Automatic correction of performance drift caused by changes in image acquisition is key for safe AI deployment. Here, the authors present a solution that restores the expected clinical performance of image classification systems in breast screening and histopathology.
- Mélanie Roschewitz
- , Galvin Khara
- & Ben Glocker
-
Article
| Open AccessRemote inspection of adversary-controlled environments
Physical unclonable functions (PUFs) normally ensure authentication of small physical objects. Here, instead, the authors observe that also rooms and buildings can serve as PUFs. They apply this insight to monitor the integrity of enclosed environments, such as art galleries, bank vaults, or data centers.
- Johannes Tobisch
- , Sébastien Philippe
- & Ulrich Rührmair