Category: Article

Global graph features unveiled by unsupervised geometric deep learning on ArXiv

GAUDI leverages a hierarchical graph-convolutional variational autoencoder architecture, where an encoder progressively compresses the graph into a low-dimensional latent space, and a decoder reconstructs the graph from the latent embedding. (Image by M. Granfors and J. Pineda.)
Global graph features unveiled by unsupervised geometric deep learning
Mirja Granfors, Jesús Pineda, Blanca Zufiria Gerbolés, Joana B. Pereira, Carlo Manzo, Giovanni Volpe
arXiv: 2503.05560

Graphs provide a powerful framework for modeling complex systems, but their structural variability makes analysis and classification challenging. To address this, we introduce GAUDI (Graph Autoencoder Uncovering Descriptive Information), a novel unsupervised geometric deep learning framework that captures both local details and global structure. GAUDI employs an innovative hourglass architecture with hierarchical pooling and upsampling layers, linked through skip connections to preserve essential connectivity information throughout the encoding-decoding process. By mapping different realizations of a system – generated from the same underlying parameters – into a continuous, structured latent space, GAUDI disentangles invariant process-level features from stochastic noise. We demonstrate its power across multiple applications, including modeling small-world networks, characterizing protein assemblies from super-resolution microscopy, analyzing collective motion in the Vicsek model, and capturing age-related changes in brain connectivity. This approach not only improves the analysis of complex graphs but also provides new insights into emergent phenomena across diverse scientific domains.

Optical Label-Free Microscopy Characterization of Dielectric Nanoparticles published in Nanoscale

Propagation of scattered light through a scattering microscope, illustrating typical nanoparticles studied. (Image by B. García Rodriguez.)
Optical Label-Free Microscopy Characterization of Dielectric Nanoparticles
Berenice Garcia Rodriguez, Erik Olsén, Fredrik Skärberg, Giovanni Volpe, Fredrik Höök, Daniel Sundås Midtvedt
Nanoscale, 17, 8336-8362 (2025)
arXiv: 2409.11810
doi: 10.1039/D4NR03860F

In order to relate nanoparticle properties to function, fast and detailed particle characterization, is needed. The ability to characterize nanoparticle samples using optical microscopy techniques has drastically improved over the past few decades; consequently, there are now numerous microscopy methods available for detailed characterization of particles with nanometric size. However, there is currently no “one size fits all” solution to the problem of nanoparticle characterization. Instead, since the available techniques have different detection limits and deliver related but different quantitative information, the measurement and analysis approaches need to be selected and adapted for the sample at hand. In this tutorial, we review the optical theory of single particle scattering and how it relates to the differences and similarities in the quantitative particle information obtained from commonly used microscopy techniques, with an emphasis on nanometric (submicron) sized dielectric particles. Particular emphasis is placed on how the optical signal relates to mass, size, structure, and material properties of the detected particles and to its combination with diffusivity-based particle sizing. We also discuss emerging opportunities in the wake of new technology development, with the ambition to guide the choice of measurement strategy based on various challenges related to different types of nanoparticle samples and associated analytical demands.

Retina electronic paper with video-rate-tunable 45000 pixels per inch on ArXiv

High-resolution display of “The Kiss” on Retina E-Paper vs. iPhone 15: Photographs comparing the display of “The Kiss” on an iPhone 15 and Retina E-paper. The surface area of the Retina E-paper is ~ 1/4000 times smaller than the iPhone 15. (Image by the Authors of the manuscript.)
Retina electronic paper with video-rate-tunable 45000 pixels per inch
Ade Satria Saloka Santosa, Yu-Wei Chang, Andreas B. Dahlin, Lars Osterlund, Giovanni Volpe, Kunli Xiong
arXiv: 2502.03580

As demand for immersive experiences grows, displays are moving closer to the eye with smaller sizes and higher resolutions. However, shrinking pixel emitters reduce intensity, making them harder to perceive. Electronic Papers utilize ambient light for visibility, maintaining optical contrast regardless of pixel size, but cannot achieve high resolution. We show electrically tunable meta-pixels down to ~560 nm in size (>45,000 PPI) consisting of WO3 nanodiscs, allowing one-to-one pixel-photodetector mapping on the retina when the display size matches the pupil diameter, which we call Retina Electronic Paper. Our technology also supports video display (25 Hz), high reflectance (~80%), and optical contrast (~50%), which will help create the ultimate virtual reality display.

Diffusion models for super-resolution microscopy: a tutorial published in Journal of Physics: Photonics

Super-resolution by diffusion models: low-resolution images of microtubules (left) are transformed to high-resolution (right) by diffusion model. Dataset courtesy: BioSR Dataset. (Image by H. Bachimamchi.)
Diffusion models for super-resolution microscopy: a tutorial
Harshith Bachimanchi, Giovanni Volpe
Journal of Physics: Photonics 7, 013001 (2025)
doi: 10.1088/2515-7647/ada101
arXiv: 2409.16488

Diffusion models have emerged as a prominent technique in generative modeling with neural networks, making their mark in tasks like text-to-image translation and super-resolution. In this tutorial, we provide a comprehensive guide to build denoising diffusion probabilistic models from scratch, with a specific focus on transforming low-resolution microscopy images into their corresponding high-resolution versions in the context of super-resolution microscopy. We provide the necessary theoretical background, the essential mathematical derivations, and a detailed Python code implementation using PyTorch. We discuss the metrics to quantitatively evaluate the model, illustrate the model performance at different noise levels of the input low-resolution images, and briefly discuss how to adapt the tutorial for other applications. The code provided in this tutorial is also available as a Python notebook in the supplementary information.

Accelerating Plasmonic Hydrogen Sensors for Inert Gas Environments by Transformer-Based Deep Learning published in ACS Sensors

Schematic illustration of the plasmonic H2 sensing principle, where the sorption of hydrogen into hydride-forming metal nanoparticles induces a change in their localized surface plasmon resonance frequency, which leads to a color change that is resolved in a spectroscopic measurement in the visible light spectral range. (Image by the Authors of the manuscript.)
Accelerating Plasmonic Hydrogen Sensors for Inert Gas Environments by Transformer-Based Deep Learning
Viktor Martvall, Henrik Klein Moberg, Athanasios Theodoridis, David Tomeček, Pernilla Ekborg-Tanner, Sara Nilsson, Giovanni Volpe, Paul Erhart, Christoph Langhammer
ACS Sensors 10, 376–386 (2025)
arXiv: 2312.15372
doi: 10.1021/acssensors.4c02616

Rapidly detecting hydrogen leaks is critical for the safe large-scale implementation of hydrogen technologies. However, to date, no technically viable sensor solution exists that meets the corresponding response time targets under technically relevant conditions. Here, we demonstrate how a tailored long short-term transformer ensemble model for accelerated sensing (LEMAS) speeds up the response of an optical plasmonic hydrogen sensor by up to a factor of 40 and eliminates its intrinsic pressure dependence in an environment emulating the inert gas encapsulation of large-scale hydrogen installations by accurately predicting its response value to a hydrogen concentration change before it is physically reached by the sensor hardware. Moreover, LEMAS provides a measure for the uncertainty of the predictions that are pivotal for safety-critical sensor applications. Our results advertise the use of deep learning for the acceleration of sensor response, also beyond the realm of plasmonic hydrogen detection.

Roadmap on machine learning glassy dynamics published in Nature Review Physics

Visual summary of the scope of the review. (Image by the Authors.)
Roadmap on machine learning glassy dynamics
Gerhard Jung, Rinske M. Alkemade, Victor Bapst, Daniele Coslovich, Laura Filion, François P. Landes, Andrea J. Liu, Francesco Saverio Pezzicoli, Hayato Shiba, Giovanni Volpe, Francesco Zamponi, Ludovic Berthier & Giulio Biroli
Nature Review Physics (2025)
doi: 10.1038/s42254-024-00791-4
arxiv: 2311.14752

Unravelling the connections between microscopic structure, emergent physical properties and slow dynamics has long been a challenge when studying the glass transition. The absence of clear visible structural order in amorphous configurations complicates the identification of the key physical mechanisms underpinning slow dynamics. The difficulty in sampling equilibrated configurations at low temperatures hampers thorough numerical and theoretical investigations. We explore the potential of machine learning (ML) techniques to face these challenges, building on the algorithms that have revolutionized computer vision and image recognition. We present both successful ML applications and open problems for the future, such as transferability and interpretability of ML approaches. To foster a collaborative community effort, we also highlight the ‘GlassBench’ dataset, which provides simulation data and benchmarks for both 2D and 3D glass formers. We compare the performance of emerging ML methodologies, in line with benchmarking practices in image and text recognition. Our goal is to provide guidelines for the development of ML techniques in systems displaying slow dynamics and inspire new directions to improve our theoretical understanding of glassy liquids.

Connecting genomic results for psychiatric disorders to human brain cell types and regions reveals convergence with functional connectivity published in Nature Communications

Brain region connectivity. (Image by the Authors of the manuscript.)
Connecting genomic results for psychiatric disorders to human brain cell types and regions reveals convergence with functional connectivity
Shuyang Yao, Arvid Harder, Fahimeh Darki, Yu-Wei Chang , Ang Li, Kasra Nikouei, Giovanni Volpe, Johan N Lundström, Jian Zeng , Naomi Wray, Yi Lu, Patrick F Sullivan, Jens Hjerling-Leffler
Nature Communications 16, 395 (2025)
doi: 10.1038/s41467-024-55611-1
medRxiv: 10.1101/2024.01.18.24301478

Identifying cell types and brain regions critical for psychiatric disorders and brain traits is essential for targeted neurobiological research. By integrating genomic insights from genome-wide association studies with a comprehensive single-cell transcriptomic atlas of the adult human brain, we prioritized specific neuronal clusters significantly enriched for the SNP-heritabilities for schizophrenia, bipolar disorder, and major depressive disorder along with intelligence, education, and neuroticism. Extrapolation of cell-type results to brain regions reveals the whole-brain impact of schizophrenia genetic risk, with subregions in the hippocampus and amygdala exhibiting the most significant enrichment of SNP-heritability. Using functional MRI connectivity, we further confirmed the significance of the central and lateral amygdala, hippocampal body, and prefrontal cortex in distinguishing schizophrenia cases from controls. Our findings underscore the value of single-cell transcriptomics in understanding the polygenicity of psychiatric disorders and suggest a promising alignment of genomic, transcriptomic, and brain imaging modalities for identifying common biological targets.

Spatial clustering of molecular localizations with graph neural networks on ArXiv

MIRO employs a recurrent graph neural network to refine SMLM point clouds by compressing clusters around their center, enhancing inter-cluster distinction and background separation for efficient clustering. (Image by J. Pineda.)
Spatial clustering of molecular localizations with graph neural networks
Jesús Pineda, Sergi Masó-Orriols, Joan Bertran, Mattias Goksör, Giovanni Volpe and Carlo Manzo
arXiv: 2412.00173

Single-molecule localization microscopy (SMLM) generates point clouds corresponding to fluorophore localizations. Spatial cluster identification and analysis of these point clouds are crucial for extracting insights about molecular organization. However, this task becomes challenging in the presence of localization noise, high point density, or complex biological structures. Here, we introduce MIRO (Multimodal Integration through Relational Optimization), an algorithm that uses recurrent graph neural networks to transform the point clouds in order to improve clustering efficiency when applying conventional clustering techniques. We show that MIRO supports simultaneous processing of clusters of different shapes and at multiple scales, demonstrating improved performance across varied datasets. Our comprehensive evaluation demonstrates MIRO’s transformative potential for single-molecule localization applications, showcasing its capability to revolutionize cluster analysis and provide accurate, reliable details of molecular architecture. In addition, MIRO’s robust clustering capabilities hold promise for applications in various fields such as neuroscience, for the analysis of neural connectivity patterns, and environmental science, for studying spatial distributions of ecological data.

Cross-modality transformations in biological microscopy enabled by deep learning published in Advanced Photonics

Cross-modality transformation and segmentation. (Image by the Authors of the manuscript.)
Cross-modality transformations in biological microscopy enabled by deep learning
Dana Hassan, Jesús Domínguez, Benjamin Midtvedt, Henrik Klein Moberg, Jesús Pineda, Christoph Langhammer, Giovanni Volpe, Antoni Homs Corbera, Caroline B. Adiels
Advanced Photonics 6, 064001 (2024)
doi: 10.1117/1.AP.6.6.064001

Recent advancements in deep learning (DL) have propelled the virtual transformation of microscopy images across optical modalities, enabling unprecedented multimodal imaging analysis hitherto impossible. Despite these strides, the integration of such algorithms into scientists’ daily routines and clinical trials remains limited, largely due to a lack of recognition within their respective fields and the plethora of available transformation methods. To address this, we present a structured overview of cross-modality transformations, encompassing applications, data sets, and implementations, aimed at unifying this evolving field. Our review focuses on DL solutions for two key applications: contrast enhancement of targeted features within images and resolution enhancements. We recognize cross-modality transformations as a valuable resource for biologists seeking a deeper understanding of the field, as well as for technology developers aiming to better grasp sample limitations and potential applications. Notably, they enable high-contrast, high-specificity imaging akin to fluorescence microscopy without the need for laborious, costly, and disruptive physical-staining procedures. In addition, they facilitate the realization of imaging with properties that would typically require costly or complex physical modifications, such as achieving superresolution capabilities. By consolidating the current state of research in this review, we aim to catalyze further investigation and development, ultimately bringing the potential of cross-modality transformations into the hands of researchers and clinicians alike.

Playing with Active Matter published in American Journal of Physics

One exemplar of the HEXBUGS used in the experiment. (Image by the Authors of the manuscript.)
Playing with Active Matter
Angelo Barona Balda, Aykut Argun, Agnese Callegari, Giovanni Volpe
Americal Journal of Physics 92, 847–858 (2024)
doi: 10.1119/5.0125111
arXiv: 2209.04168

In the past 20 years, active matter has been a very successful research field, bridging the fundamental physics of nonequilibrium thermodynamics with applications in robotics, biology, and medicine. Active particles, contrary to Brownian particles, can harness energy to generate complex motions and emerging behaviors. Most active-matter experiments are performed with microscopic particles and require advanced microfabrication and microscopy techniques. Here, we propose some macroscopic experiments with active matter employing commercially available toy robots (the Hexbugs). We show how they can be easily modified to perform regular and chiral active Brownian motion and demonstrate through experiments fundamental signatures of active systems such as how energy and momentum are harvested from an active bath, how obstacles can sort active particles by chirality, and how active fluctuations induce attraction between planar objects (a Casimir-like effect). These demonstrations enable hands-on experimentation with active matter and showcase widely used analysis methods.