Actin filaments are fundamental components of the cytoskeleton, essential for maintaining cell shape, enabling motility, and facilitating intracellular transport. Cryo-electron tomography (cryo-ET) enables nanometer-resolution visualization of filament networks in situ; however, low signal-to-noise ratios, missing wedge artifacts, and complex 3D architectures present significant challenges for accurate analysis. Manual filament annotation is highly resource-intensive and prone to variability, underscoring the need for automated approaches. In this study, we develop and evaluate deep learning-based semantic segmentation architectures for accurate segmentation of actin filament networks in cryo-ET data. We systematically assess several architectures-3D U-Net, Attention 3D U-Net, TransUNet 3D, and UNETR-on simulated tomograms with known ground truth. Model performance is quantified using Dice scores and Intersection over Union (IoU) to evaluate segmentation performance under challenging imaging conditions. Our results show that no single deep learning architecture consistently outperforms others, highlighting the importance of accounting for filament arrangement and noise characteristics. By providing a comparative evaluation of these architectures, we demonstrate their effectiveness in detecting filamentous structures and offer guidance for future efforts to improve segmentation performance.

This work provides new evidence of the utility of deep learning-based protein structure prediction approaches, specifically AlphaFold2, in the interpretation of 4-6 Å resolution cryo-EM maps. We describe the dependencies, as well as the strengths and limitations, of integrating experimental and AI-based approaches to building accurate models, even from poorly resolved density maps. The test followed recent work that implemented a refinement protocol in the Phenix program, which successfully refined AlphaFold2 models in high-resolution maps but which at lower resolution relied on simulated "hybrid density maps". To study the noise and imperfections present in experimental cryo-EM maps more realistically, in this work, we selected only experimental map/model pairs in the 4-6 Å resolution range where refinement performance starts to degrade. Most of the AlphaFold2 predicted models are highly accurate, particularly for the 9 larger chains (226-373 residues long) of the 10 cases, exhibiting TM-scores above 0.9. A small chain of 115 residues in length containing three helices was poorly predicted, with a TM-score of 0.52. The observed success of the subsequent refinement step depends significantly on the quality of the AlphaFold2 prediction, the quality of the experimental cryo-EM data, and the quality of the alignment of the model with the density.

filopodia makes identifying filaments within noisy cryo-electron tomograms extremely challenging. In this work, we present a computationally efficient dynamic programming-based framework for tracing arbitrarily oriented actin filaments. Starting from locally determined seed points, it accumulates densities along paths of a particular length within 45° of the three Cartesian coordinate axes. This novel approach covers all possible orientations, so there is no need to assume a dominant direction as in earlier work. For each seed point, the path with the highest density value is selected, and it acts as a candidate filament segment (CFS) that is likely to form a part of a filament when it has a high path density value. The subsequent stages involve identifying groups of CFSs with high path densities by binning and merging them. The merging step considers the relative orientations and distances of CFSs to connect them. In addition, the CFSs are extended to fill the noise-induced gaps to some extent. In the current prototype software, we focused on the proof of the concept, using a noisy simulated tomogram with a known ground truth that closely mimics the appearance of an experimental map. We achieved an almost perfect precision score of 0.999, but this success came at the expense of a lower recall score 0.462 due to false negatives. We discuss the dependencies as well as the limitations of the current filament merging that need to be overcome to achieve a higher recall score in the future.

We propose a fast, dynamic programming-based framework for tracing actin filaments in 3D maps of subcellular components in cryo-electron tomography. The approach can identify high-density filament segments in various orientations, but it takes advantage of the arrangement of actin filaments within cells into more or less tightly aligned bundles. Assuming that the tomogram can be rotated such that the filaments can be oriented to be directed in a dominant direction (i.e., the X, Y, or Z axis), the proposed framework first identifies local seed points that form the origin of candidate filament segments (CFSs), which are then grown from the seeds using a fast dynamic programming algorithm. The CFS length l can be tuned to the nominal resolution of the tomogram or the separation of desired features, or it can be used to restrict the curvature of filaments that deviate from the overall bundle direction. In subsequent steps, the CFSs are filtered based on backward tracing and path density analysis. Finally, neighboring CFSs are fused based on a collinearity criterion to bridge any noise artifacts in the 3D map that would otherwise fractionalize the tracing. We validate our proposed framework on simulated tomograms that closely mimic the features and appearance of experimental maps.

As automated filament tracing algorithms in cryo-electron tomography (cryo-ET) continue to improve, the validation of these approaches has become more incumbent. Having a known ground truth on which to base predictions is crucial to reliably test predicted cytoskeletal filaments because the detailed structure of the filaments in experimental tomograms is obscured by a low resolution, as well as by noise and missing Fourier space wedge artifacts. We present a software tool for the realistic simulation of tomographic maps (TomoSim) based on a known filament trace. The parameters of the simulated map are automatically matched to those of a corresponding experimental map. We describe the computational details of the first prototype of our approach, which includes wedge masking in Fourier space, noise color, and signal-to-noise matching. We also discuss current and potential future applications of the approach in the validation of concurrent filament tracing methods in cryo-ET.

Cryo-electron microscopy (cryo-EM) is an important biophysical technique that produces three-dimensional (3D) density maps at different resolutions. Because more and more models are being produced from cryo-EM density maps, validation of the models is becoming important. We propose a method for measuring local agreement between a model and the density map using the central axis of the helix. This method was tested using 19 helices from cryo-EM density maps between 5.5 Å and 7.2 Å resolution and 94 helices from simulated density maps. This method distinguished most of the well-fitting helices, although challenges exist for shorter helices.

The modeling of large biomolecular assemblies relies on an efficient rendering of their hierarchical architecture across a wide range of spatial level of detail. We describe a paradigm shift currently under way in computer graphics towards the use of more realistic global illumination models, and we apply the so-called ambient occlusion approach to our open-source multi-scale modeling program, Sculptor. While there are many other higher quality global illumination approaches going all the way up to full GPU-accelerated ray tracing, they do not provide size-specificity of the features they shade. Ambient occlusion is an aspect of global lighting that offers great visual benefits and powerful user customization. By estimating how other molecular shape features affect the reception of light at some surface point, it effectively simulates indirect shadowing. This effect occurs between molecular surfaces that are close to each other, or in pockets such as protein or ligand binding sites. By adding ambient occlusion, large macromolecular systems look much more natural, and the perception of characteristic surface features is strongly enhanced. In this work, we present a real-time implementation of screen space ambient occlusion that delivers realistic cues about tunable spatial scale characteristics of macromolecular architecture. Heretofore, the visualization of large biomolecular systems, comprising e.g. hundreds of thousands of atoms or Mega-Dalton size electron microscopy maps, did not take into account the length scales of interest or the spatial resolution of the data. Our approach has been uniquely customized with shading that is tuned for pockets and cavities of a user-defined size, making it useful for visualizing molecular features at multiple scales of interest. This is a feature that none of the conventional ambient occlusion approaches provide. Actual Sculptor screen shots illustrate how our implementation supports the size-dependent rendering of molecular surface features.

In low resolution structures of biological assemblies one can often observe conformational deviations that require a flexible rearrangement of structural domains fitted at the atomic level. We are evaluating interpolation methods for the flexible alignment of atomic models based on coarse models. Spatial interpolation is well established in image-processing and visualization to describe the overall deformation or warping of an object or an image. Combined with a coarse representation of the biological system by feature vectors, such methods can provide a flexible approximation of the molecular structure. We have compared three well-known interpolation techniques and evaluated the results by comparing them with constrained molecular dynamics. One method, inverse distance weighting interpolation, consistently produced models that were nearly indistinguishable on the alpha carbon level from the molecular dynamics results. The method is simple to apply and enables flexing of structures by non-expert modelers. This is useful for the basic interpretation of volumetric data in biological applications such as electron microscopy. The method can be used as a general interpretation tool for sparsely sampled motions derived from coarse models.