Lorenz Lamm

Cryo-electron tomography provides unique insights into macromolecular complexes in their native environments, yet membrane analysis remains a major bottleneck due to low signal-to-noise ratios, missing wedge artifacts and the complexity of membrane-associated particles. Existing tools often require extensive manual annotation, struggle with generalization across datasets and lack integrated solutions for segmentation, particle localization and quantitative analysis. We introduce MemBrain v2, a deep-learning-enabled framework that unifies these tasks into a streamlined pipeline. MemBrain-seg leverages a diverse, collaboratively generated training dataset and specialized model training strategies to achieve generalizable membrane segmentation across variable tomographic conditions. MemBrain-pick enables data-efficient localization of membrane-bound particles by integrating geometric constraints with deep learning, reducing the need for extensive manual annotation. MemBrain-stats provides quantitative insights into particle distributions, computing spatial metrics to analyze intramembrane particle organization. MemBrain v2 integrates seamlessly into cryo-electron tomography workflows, providing an accessible and structured approach to membrane analysis.

Summary This study shows that an artificial intelligence tool can identify patterns of reduced bone mineral density in routine CT scans that would otherwise remain unreported. Compared to radiologists, the AI system flagged substantially more cases with potential signs of reduced bone mineral density, offering a scalable approach to support earlier identification of individuals who may benefit from further assessment. Purpose Osteoporosis often goes unrecognized in routine computed tomography (CT) scans performed for unrelated indications, leading to diagnosis only after a fragility fracture occurs. We present an artificial intelligence (AI)-based tool for opportunistic bone mineral density (BMD) assessment on contrast-enhanced and native CT scans of the entire spine to enable detection of patterns suggestive of reduced BMD. Methods We trained a neural network to classify BMD of individual vertebrae as normal, osteopenic, or osteoporotic, using labels derived from Dual-Energy X-ray Absorptiometry (DXA) T-scores as the reference standard. The training dataset included 1084 sagittal spine CT series from 526 patients across multiple US and German centers, encompassing cervical, thoracic, and lumbar regions. The model was evaluated on an independent holdout set of 270 patients. Additionally, in a retrospective analysis of 354 patients who later sustained fragility fractures, the AI model was applied to contrast or native CT scans acquired 12–24 months prior to the fracture event to assess how often the AI model would flag patterns suggestive of reduced BMD in patients who subsequently sustained fragility fractures. Results On the independent holdout set, the algorithm achieved a specificity of 84% and a sensitivity of 67%. In the retrospective study, the AI model flagged patterns of reduced BMD in 184 of 354 patients (87 osteoporotic, 97 osteopenic), while radiologists had reported reduced BMD in only 41 cases. Conclusion To the best of our knowledge, this AI model is the first to classify BMD across the entire spine on both contrast and native CT scans. It demonstrates robust real-world performance and offers a promising approach for scalable opportunistic BMD screening in routine CT imaging.

Quantitative fluorescence microscopy is frequently confounded by spatially varying illumination and temporal intensity drift. Although BaSiC is a widely adopted retrospective correction method, it can fail when foreground content is strongly correlated across images—a common regime in time-lapse, tiled and volumetric acquisitions—and its application often requires manual parameter tuning that limits reproducibility and scalability. We introduce BaSiCPy, a foreground-aware implementation of BaSiC that improves illumination profile estimation under correlated foreground structures, provides automatic hyperparameter selection and accelerates large-scale processing through GPU support. BaSiCPy is distributed as an open-source Python package with graphical and programmatic interfaces, facilitating integration into contemporary bioimage analysis workflows.

Thylakoid membranes coordinate the light reactions of photosynthesis across multiple scales, coupling the architecture of an elaborate membrane network to the spatial organization of individual protein complexes embedded within this network. Previously, we used in situ cryo-electron tomography (cryo-ET) to reveal the native thylakoid architecture of the green alga Chlamydomonas reinhardtii (Engel et al., 2015) and then map the molecular organization of these thylakoids with single-molecule precision (Wietrzynski et al., 2020). However, it remains to be shown how generalizable this green algal blueprint is to the thylakoids of vascular plants, which possess distinct membrane architecture subdivided into grana stacks interconnected by non-stacked stromal lamellae. Here, we continue our cryo-ET investigation to reveal the molecular architecture of thylakoids within intact chloroplasts isolated from spinach (Spinacia oleracea). We visualize the fine ultrastructural details of grana membranes, as well as interactions between thylakoids and plastoglobules. We apply AI-based computational approaches (Lamm et al., 2024) to quantify the organization of photosynthetic complexes within the plane of the thylakoid membrane and across adjacent stacked membranes. Our analysis reveals that the molecular organization of thylakoid membranes in vascular plants and green algae is strikingly similar. We find that PSII organization is non-crystalline and has uniform concentration both within the membrane plane and across stacked grana membranes. Similar to C. reinhardtii, we observe strict lateral heterogeneity of PSII and PSI at the boundary between appressed and non-appressed thylakoid domains, with no evidence for a distinct grana margin region where these complexes have been proposed to intermix. Based on these measurements, we support a simple two-domain model for the molecular organization of thylakoid membranes in both green algae and plants.

Thylakoid membranes coordinate the light reactions of photosynthesis across multiple scales, coupling the architecture of an elaborate membrane network to the spatial organization of individual protein complexes embedded within this network. Previously, we used in situ cryo-electron tomography (cryo-ET) to reveal the native thylakoid architecture of the green alga Chlamydomonas reinhardtii [1] and then map the molecular organization of these thylakoids with single-molecule precision [2]. However, it remains to be shown how generalizable this green algal blueprint is to the thylakoids of vascular plants, which possess distinct membrane architecture subdivided into grana stacks interconnected by non-stacked stromal lamellae. Here, we continue our cryo-ET investigation to reveal the molecular architecture of thylakoids within intact chloroplasts isolated from spinach (Spinacia oleracea). We visualize the fine ultrastructural details of grana membranes, as well as interactions between thylakoids and plastoglobules. We apply and further develop AI-based computational approaches for automated membrane segmentation and membrane protein picking [3], enabling us to quantify the organization of photosynthetic complexes within the plane of the thylakoid membrane and across adjacent stacked membranes. Our analysis reveals that, despite different 3D architecture, the molecular organization of thylakoid membranes in vascular plants and green algae is strikingly similar. In contrast to isolated plant thylakoids, where semi-crystalline arrays of photosystem II (PSII) appear to hold some membranes together, we find in intact chloroplasts that PSII is non-crystalline and has uniform concentration both within the membrane plane and across stacked grana membranes. Similar to C. reinhardtii, we observe strict lateral heterogeneity of PSII and PSI at the boundary between appressed and non-appressed thylakoid domains, with no evidence for a distinct grana margin region where these complexes have been proposed to intermix. Based on these measurements, we support a simple two-domain model for the molecular organization of thylakoid membranes in both green algae and plants.

Mitochondria regenerate adenosine triphosphate (ATP) through oxidative phosphorylation. This process is carried out by five membrane-bound complexes collectively known as the respiratory chain, working in concert to transfer electrons and pump protons. The precise organization of these complexes in native cells is debated. We used in situ cryo–electron tomography to visualize the native structures and organization of several major mitochondrial complexes in Chlamydomonas reinhardtii cells. ATP synthases and respiratory complexes segregate into curved and flat crista membrane domains, respectively. Respiratory complexes I, III, and IV assemble into a respirasome supercomplex, from which we determined a native 5-angstrom (Å) resolution structure showing binding of electron carrier cytochrome c . Combined with single-particle cryo–electron microscopy at 2.4-Å resolution, we model how the respiratory complexes organize inside native mitochondria.

In situ cryo-electron tomography (cryo-ET) has emerged as the method of choice to investigate structures of biomolecules in their native context. However, challenges remain in the efficient production of large-scale cryo-ET datasets, as well as the community sharing of this information-rich data. Here, we applied a cryogenic plasma-based focused ion beam (cryo-PFIB) instrument for high-throughput milling of the green alga Chlamydomonas reinhardtii , a useful model organism for in situ visualization of numerous fundamental cellular processes. Combining cryo-PFIB sample preparation with recent advances in cryo-ET data acquisition and processing, we generated a dataset of 1829 reconstructed and annotated tomograms, which we provide as a community resource to drive method development and inspire biological discovery. To assay the quality of this dataset, we performed subtomogram averaging (STA) of both soluble and membrane-bound complexes ranging in size from >3 MDa to ∼200 kDa, including 80S ribosomes, Rubisco, nucleosomes, microtubules, clathrin, photosystem II, and mitochondrial ATP synthase. The majority of these density maps reached sub-nanometer resolution, demonstrating the potential of this C. reinhardtii dataset, as well as the promise of modern cryo-ET workflows and open data sharing towards visual proteomics.

Thylakoid membranes coordinate the light reactions of photosynthesis across multiple scales, coupling the architecture of an elaborate membrane network to the spatial organization of individual protein complexes embedded within this network. Previously, we used in situ cryo-electron tomography (cryo-ET) to reveal the native thylakoid architecture of the green alga Chlamydomonas reinhardtii [1] and then map the molecular organization of these thylakoids with single-molecule precision [2]. However, it remains to be shown how generalizable this green algal blueprint is to the thylakoids of vascular plants, which possess distinct membrane architecture subdivided into grana stacks interconnected by non-stacked stromal lamellae. Here, we continue our cryo-ET investigation to reveal the molecular architecture of thylakoids within intact chloroplasts isolated from spinach ( Spinacia oleracea ). We visualize the fine ultrastructural details of grana membranes, as well as interactions between thylakoids and plastoglobules. We apply and further develop AI-based computational approaches for automated membrane segmentation and membrane protein picking [3], enabling us to quantify the organization of photosynthetic complexes within the plane of the thylakoid membrane and across adjacent stacked membranes. Our analysis reveals that, despite different 3D architecture, the molecular organization of thylakoid membranes in vascular plants and green algae is strikingly similar. In contrast to isolated plant thylakoids, where semi-crystalline arrays of photosystem II (PSII) appear to hold some membranes together, we find in intact chloroplasts that PSII is non-crystalline and has uniform concentration both within the membrane plane and across stacked grana membranes. Similar to C. reinhardtii , we observe strict lateral heterogeneity of PSII and PSI at the boundary between appressed and non-appressed thylakoid domains, with no evidence for a distinct grana margin region where these complexes have been proposed to intermix. Based on these measurements, we support a simple two-domain model for the molecular organization of thylakoid membranes in both green algae and plants.

Motivation: Visualization and annotation of segmented surfaces is of paramount importance for studying membrane proteins in their native cellular environment by cryogenic electron tomography (cryo-ET). Yet, analyzing membrane proteins and their organization is challenging due to their small sizes and the need to consider local context constrained to the membrane surface. Results: To interactively visualize, annotate, and analyze proteins in cellular context from cryo-ET data, we have developed Surforama, a Python package and napari plugin. For interactive visualization of membrane proteins in tomograms, Surforama renders the local densities projected on the surface of the segmentations. Suforama additionally provides tools to annotate and analyze particles on the membrane surfaces. Finally, for compatibility with other tools in the cryo-ET analysis ecosystem, results can be exported as RELION-formatted STAR files. As a demonstration, we performed subtomogram averaging and neighborhood analysis of photosystem II proteins in thylakoid membranes from the green alga Chlamydomonas reinhardtii. Availability and implementation: Python package, code and examples are available at: https://github.com/cellcanvas/surforama

Cryo-electron tomography (cryo-ET) allows to visualize the cellular context at macromolecular level. To date, the impossibility of obtaining a reliable ground truth is limiting the application of deep learning-based image processing algorithms in this field. As a consequence, there is a growing demand of realistic synthetic datasets for training deep learning algorithms. In addition, besides assisting the acquisition and interpretation of experimental data, synthetic tomograms are used as reference models for cellular organization analysis from cellular tomograms. Current simulators in cryo-ET focus on reproducing distortions from image acquisition and tomogram reconstruction, however, they can not generate many of the low order features present in cellular tomograms. Here we propose several geometric and organization models to simulate low order cellular structures imaged by cryo-ET. Specifically, clusters of any known cytosolic or membrane bound macromolecules, membranes with different geometries as well as different filamentous structures such as microtubules or actin-like networks. Moreover, we use parametrizable stochastic models to generate a high diversity of geometries and organizations to simulate representative and generalized datasets, including very crowded environments like those observed in native cells. These models have been implemented in a multiplatform open-source Python package, including scripts to generate cryo-tomograms with adjustable sizes and resolutions. In addition, these scripts provide also distortion-free density maps besides the ground truth in different file formats for efficient access and advanced visualization. We show that such a realistic synthetic dataset can be readily used to train generalizable deep learning algorithms.