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 Date: 27 January 2025 Time: 10:00 Place: SciLifeLab Campus Solna, Sweden
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.
Geared mechanism. (Image by G. Wang)Gan Wang defended his PhD thesis on 20 January 2025. Congrats!
The defense took place in PJ, Institutionen för fysik, Origovägen 6b, Göteborg, at 10:00.
Title: Microfabrication technique applications: from passive particle manipulation to active microswimmers, micromachines, and fluidic control
Abstract: Overcoming Brownian motion at the micro- and nanoscale to achieve precise control of objects is crucial for fields such as materials science and biology. Significant progress has been made in trapping and manipulating micro- and nanoscale objects, either by generating gradients through external physical fields or by engineering systems that can harvest energy from their environment for autonomous motion. These techniques rely on the precise application of forces, such as optical and electromagnetic forces, and have found extensive applications across various scientific disciplines. Recent advances in micro- and nanofabrication technologies have greatly enhanced the generation and regulation of these forces, offering new possibilities for manipulating micro- and nanoscale objects.
This thesis applies traditional micro- and nanofabrication techniques, typically used in semiconductor manufacturing, to construct micro- and nanostructures for manipulating forces, primarily critical Casimir forces and optical forces, to achieve precise control over microscale object movement.
I first show the fabrication of periodic micropatterns on a substrate, followed by chemical functionalization to impart hydrophilic and hydrophobic properties. Near the critical temperature of a binary liquid, attractive and repulsive critical Casimir forces are generated between the micropatterns and microparticles. These forces allow the stable trapping of the microparticles on the substrate and the manipulation of their configuration and movement.
Then, my research transitions from passive control to active motion by fabricating metasurfaces capable of modulating optical fields and embedding them within micro-particles (microswimmers). This enables light-momentum exchange under planar laser illumination, resulting in autonomous movement of the microswimmers. By varying the metasurface design as well as the intensity and polarization of the light, complex behaviors can emerge within these microswimmers. Subsequently, My research focused on using these microfabrication techniques to build micromotors integrated on a chip surface. These micromotors couple with other objects through gear structures, creating miniature machines that can execute functional tasks. Finally, by altering the configuration of these machines and the distances between them, I acheived precise, multifunctional control over fluid dynamics, facilitating the transport of micro- and nanoscale objects.
Insights gained from this research suggest innovative manufacturing approaches for scalable manipulation of particles, more intelligent microrobots, and powerful miniaturized on-chip machines, with applications across various fields.
(Photo by A. Ciarlo.)Mathilda Gustafsson joined the Soft Matter Lab on 20 January 2025.
Mathilda is a master student in Complex Adaptive Systems at Chalmers University of Technology.
During her time at the Soft Matter Lab, she will work on a project about tracking bacteria in sequences of microscopic images. In particular she will try to solve problems with overlapping bacteria using recurrent neural networks.
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.
Benjamin Midtvedt, PhD defense. (Photo by H. P. Thanabalan.)Benjamin Midtvedt defended his PhD thesis on 9 January 2025. Congrats!
The defense will take place in PJ, Institutionen för fysik, Origovägen 6b, Göteborg, at 13:00.
Title: Annotation-free deep learning for quantitative microscopy
Abstract: Quantitative microscopy is an essential tool for studying and understanding microscopic structures. However, analyzing the large and complex datasets generated by modern microscopes presents significant challenges. Manual analysis is time-intensive and subjective, rendering it impractical for large datasets. While automated algorithms offer faster and more consistent results, they often require careful parameter tuning to achieve acceptable performance, and struggle to interpret the more complex data produced by modern microscopes. As such, there is a pressing need to develop new, scalable analysis methods for quantitative microscopy. In recent years, deep learning has transformed the field of computer vision, achieving superhuman performance in tasks ranging from image classification to object detection. However, this success depends on large, annotated datasets, which are often unavailable in microscopy. As such, to successfully and efficiently apply deep learning to microscopy, new strategies that bypass the dependency on extensive annotations are required. In this dissertation, I aim to lower the barrier for applying deep learning in microscopy by developing methods that do not rely on manual annotations and by providing resources to assist researchers in using deep learning to analyze their own microscopy data. First, I present two cases where training annotations are generated through alternative means that bypass the need for human effort. Second, I introduce a deep learning method that leverages symmetries in both the data and the task structure to train a statistically optimal model for object detection without any annotations. Third, I propose a method based on contrastive learning to estimate nanoparticle sizes in diffraction-limited microscopy images, without requiring annotations or prior knowledge of the optical system. Finally, I deliver a suite of resources that empower researchers in applying deep learning to microscopy. Through these developments, I aim to demonstrate that deep learning is not merely a “black box” tool. Instead, effective deep learning models should be designed with careful consideration of the data, assumptions, task structure, and model architecture, encoding as much prior knowledge as possible. By structuring these interactions with care, we can develop models that are more efficient, interpretable, and generalizable, enabling them to tackle a wider range of microscopy tasks.
Supervisor: Giovanni Volpe Examiner: Dag Hanstorp Opponent: Ivo Sbalzarini Committee: Susan Cox, Maria Arrate Munoz Barrutia, Ignacio Arganda-Carreras Alternate board member: Måns Henningson
Ivo Sbalzarini (left) and Benjamin Midtvedt (right). (Photo by H. P. Thanabalan.)Benjamin Midtvedt (left), Giovanni Volpe (right), announcement. (Photo by H. P. Thanabalan.)From left to right: Ignacio Arganda, Arrate Muñoz Barrutia, Susan Cox, Benjamin Midtvedt, Giovanni Volpe, Ivo Sbalzarini. (Photo by H. P. Thanabalan.)
Ivo Sbalzarini, talk. (Photo by Y.-W. Chang.)Content-adaptive deep learning for large-scale
fluorescence microscopy imaging
Ivo Sbalzarini
Max Planck Institute of Molecular Cell Biology and Genetics
Center for Systems Biology Dresden https://sbalzarini-lab.org/
Anqi Lyu starts her PhD at the Physics Department of the University of Gothenburg on 8 January 2025.
Anqi has a Master degree in Medical Bioinformatics from University of Verona, Italy.
In her PhD, she will focus on delineating how plasma factors globally influence endothelial cells, with emphasis on their roles in health, ageing and disease, by utilizing computational tools in combination with interdisciplinary approaches.
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.
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.
