Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2025.05.16.654457

Robust Deep Denoising of Soft X-Ray Tomography Data for Biological Research: Targeting Tilt Series Versus Reconstructed Tomograms

Chueh, S.·Simpson, J. C.·Kapishnikov, S.
View original source ↗Export metadata ↓

Abstract

1.Soft X-ray microscopy (SXM) is a powerful tool for nanoscale 3D imaging of hydrated, intact cells. However, its application is limited by pixel-wise-correlated noise inherent in the imaging process. While the deep-learning-based framework Noise2Inverse has been proposed for tomography denoising, the lack of robust validation for newly revealed features raises concerns regarding their practical biological utility. We argue that denoising the raw tilt series, instead of on the reconstructed tomogram, offers a significant advantage by leveraging the tomographic reconstruction process to mitigate local prediction errors through averaging. Consequently, features present in the tomogram reconstructed from a denoised tilt series exhibit higher credibility, as falsely predicted details on certain tilt series slices are likely to be averaged out. Nevertheless, denoising the tilt series remains challenging due to the spatially correlated noise that occurs in bioimaging. Existing self-supervised methods relying on a single noisy image struggle with such noise, while the Noise2Noise framework necessitates paired noisy datasets for training. This study addresses these challenges by investigating practical imaging workflows in SXM and related bioimaging modalities to identify existing imaging resources as training data for tilt series denoising. We compare the denoising performance when applied to tilt series versus reconstructed tomograms and evaluate the efficacy of chosen methods on real biological specimens to assess their applicability within practical SXM research. Our findings establish a robust and efficient denoising strategy for SXM by directly addressing the complexities of noise in the raw tilt series. HighlightsO_LITargeting tilt series for denoising inherently validates the correctness of the denoised tomogram via the reconstruction process. C_LIO_LIExisting multi-frame imaging schemes provide necessary resources for training Noise2Noise framework for tilt series denoising. C_LIO_LINoise2Noise applied to tilt series reveals finer and more reliable details than direct denoising on reconstructed tomograms (Noise2Inverse). C_LIO_LIDenoising tilt series minimizes inference time compared to Noise2Inverse in soft X-ray tomography. C_LI

Explore related subjects

bioengineeringPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Chueh, S., Simpson, J. C., Kapishnikov, S.. 2025-05-21. Robust Deep Denoising of Soft X-Ray Tomography Data for Biological Research: Targeting Tilt Series Versus Reconstructed Tomograms. https://doi.org/10.1101/2025.05.16.654457

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

RNASeek: A Cross-Phyla Generative Foundation Model for Multipurpose RNA Modeling and Reinforcement Learning-Based Design

RNA plays central roles in regulating information flow and provides a versatile substrate for engineering biological functions. While large language models (LLMs) have transformed natural language processing and protein design, a general framework connecting RNA foundation models to functional sequence design remains limited. Here, we present RNASeek, a 1.6-billion-parameter generative foundation model built on a DeepSeek architecture and trained on a cross-phyla transcriptomic corpus for RNA sequence representation and generation. Natural-language tokens enable flexible conditional prediction and sequence design using a unified backbone. RNASeek captures species-specific transcript features and intron-exon boundaries in a zero-shot setting. We then fine-tune RNASeek to predict ribozyme self-cleavage activity and viral mRNA stability, revealing interpretable sequence features associated with function, including ribozyme loop flexibility and stem stability, as well as AU-rich motifs associated with mRNA stability. We use these functional predictors as reward models and apply Group Relative Policy Optimization (GRPO) to update the generation policy of RNASeek toward sequences with desired properties. GRPO-guided generation produces faster-cleaving ribozymes and stability-enhancing 3' UTRs while satisfying user-specified IUPAC constraints. Experimentally validated RNASeek-generated ribozymes achieve wild-type levels of activity, while RNASeek-generated 3' UTR sequences exceed the performance of the training data and benchmarked AI-generated 3' UTRs. Together, RNASeek establishes a unified pretrain-predict-optimize framework that connects learned RNA function to controllable de novo sequence design and provides a general strategy for engineering regulatory RNAs with desired properties.

bioengineering↗
bioRxiv2026

Joint Vector Flow Mapping and Segmentation: Ill-Posedness,Differentiable Bayesian Inference, and Synthetic Vortex-FlowBenchmarks

Vector flow mapping (VFM) reconstructs left-ventricular (LV) blood velocity from color-Doppler echocardiography by combining the measured beamwise component with physical and regularizing constraints. Analysis of the discrete VFM formulation shows that the inverse problem is intrinsically ill posed: the occurrence of singular modes can be predicted from the geometry of the segmented blood-pool domain, the imposed boundary conditions, and the degree of smoothing. These modes can propagate uncertainty along entire transverse bands of the reconstructed velocity field, yet conventional VFM neither quantifies this uncertainty nor allows for correcting the blood-pool segmentation. We introduce Bayesian VFM (B--VFM), a hierarchical framework that jointly infers radial and transverse velocities, a probabilistic blood-pool mask, their spatially resolved uncertainties, and hyperparameters weighting Doppler and segmentation fidelity, mass conservation, boundary conditions, and smoothness. The discretized posterior admits a closed-form gradient and exact Hessian, enabling computationally efficient, gradient-based MAP estimation, sampling, and direct analysis of ill-posed modes. Posterior inference combines Gibbs sampling of conjugate Gamma-distributed hyperparameters with conditional maximum-a-posteriori estimation and a Laplace approximation for the high-dimensional velocity and mask fields. To accommodate systematic departures from planar mass conservation, B-VFM can learn the covariance of the planar divergence residual from an ensemble of flows and incorporate it as a structured model-discrepancy prior. Independent chains converged reproducibly, while covariance priors learned from flow ensembles illustrated how model discrepancies can be incorporated into the inference. B--VFM was evaluated using Lamb-Chaplygin dipoles under ideal conditions and with Doppler corruption, Doppler voids, and segmentation defects, and using the Hicks-Moffatt family of spherical vortices to assess violations of planar mass conservation. The method produced smooth reconstructions, localized uncertainty near unreliable measurements and regions of model inconsistency, and used flow information to correct segmentation errors. Within the tested vortex family, the data-informed planar divergence prior reduced velocity bias and mask distortion. B--VFM thus provides an uncertainty-aware reconstruction method and a flexible foundation for future VFM formulations incorporating additional priors, observations, and physical models. Future work will evaluate the method using clinical data and more complex three-dimensional benchmark flows.

bioengineering↗
bioRxiv2026

Computational design of a versatile, zero-radius proximity labeling enzyme

The ability to map protein interactomes and organelle proteomes is foundational for achieving a molecular understanding of living cells. Proximity labeling (PL) provides a powerful strategy for this, but existing enzymes and photocatalysts are limited by their spatial resolution, reliance on biotin, and/or in vivo compatibility. Here we report FlexID, an engineered promiscuous ligase that catalyzes the rapid attachment of diverse small-molecule probes to proximal endogenous proteins. Critically, FlexID operates through a zero-radius, direct-contact mechanism, offering superior spatial precision compared to existing PL tools. We engineered FlexID by combining the strengths of sequence- and structure-trained computational models to enhance its catalytic activity and structural stability. Biophysical analysis revealed that specific conformational changes in FlexID improve its ability to recognize diverse target proteins while simultaneously preventing the premature release of the reactive intermediate. We demonstrate FlexID's versatility through in vivo proximity labeling, comprehensive organelle proteome mapping, and a high-throughput, fluorescence-based screen for molecular glues. Our work shows that computational methods can be harnessed to create mechanistically distinct PL enzymes and establishes FlexID as a flexible, high-resolution tool for mapping protein interactions and proteomes in living cells.

bioengineering↗