imputation

Deformable Mirror based Optimal PSF Engineering for 3D Super-resolution Imaging

This paper develops a framework for generating device-specific optimal PSFs for 3D super-resolution imaging using deformable mirrors, demonstrating superior performance over conventional PSFs.

Super-resolution vibrational imaging using expansion stimulated Raman scattering microscopy

The paper introduces MAGNIFIERS, a technique combining SRS microscopy with expansion microscopy to achieve sub-50 nm resolution and scalable multiplexity for label-free chemical imaging.

Content-aware image restoration improves spatiotemporal resolution in luminescence microscopy.

This paper shows that content-aware image restoration reduces exposure time in luminescence microscopy, improving temporal resolution.

An empirical evaluation of genotype imputation of ancient DNA

This study evaluates genotype imputation for ancient DNA using Beagle 4.0 and 1000 Genomes reference data, showing high accuracy even at low coverage and highlighting the benefits of diverse reference sets and low-coverage samples.

Focus-ISM for Sharp and Gentle Super-Resolved Microscopy

The paper introduces focus-ISM, a method combining STED and ISM to improve super-resolution microscopy for live and thick samples without compromising image quality.

Projecting clumped transcriptomes onto single cell atlases to achieve single cell resolution

scProjection maps multi-modal RNA measurements to scRNA-seq atlases to extract single cell gene expression profiles and improve spatial and multi-modal analysis.

Improved imaging and preservation of lysosome dynamics using silver nanoparticle-enhanced fluorescence

This paper demonstrates that silver nanoparticles enhance lysosome fluorescence, enabling live-cell imaging with reduced phototoxicity and preserved dynamics.

Molecular Aggregation Induced Photoacoustics for NIR-II in vivo Imaging

This paper reports the first molecular aggregation induced photoacoustic effect (MAIPA), demonstrating that molecular aggregation enhances photoacoustic efficiency significantly compared to individual molecules.

Predicting coordinates of peptide features in raw timsTOF data with machine learning for targeted extraction reduces missing values in label-free DDA LC-MS/MS proteomics experiments

Integrated optical device for Structured Illumination Microscopy

The paper presents an integrated optical chip for structured illumination microscopy, enabling high-resolution imaging by generating a hexagonal illumination pattern without alignment.

Fast and robust imputation for miRNA expression data using constrained least squares

The paper introduces a fast and accurate imputation method for miRNA expression data using constrained least squares, outperforming existing methods in speed and accuracy.

Connecting high-resolution 3D chromatin organization with epigenomics

The paper develops a deep learning model, CAESAR, to predict high-resolution 3D chromatin structures from epigenomic data and validates its accuracy across 91 human tissues and cell lines.

resPAINT: Accelerating volumetric super-resolution localisation microscopy by active control of probe emission

The paper introduces resPAINT, a method that enhances volumetric super-resolution microscopy by actively controlling probe emission, achieving up to 50-fold faster localisation rates without sacrificing contrast.

Tomographic-encoded multiphoton (TEMP) microscopy

The paper introduces TEMP microscopy, a novel tomographic technique for fast volumetric imaging with high resolution and reduced photodamage, demonstrating its effectiveness on scattering tissues and mouse brain slices.

High-fidelity 3D live-cell nanoscopy through data-driven enhanced super-resolution radial fluctuation

This paper introduces eSRRF, an enhanced super-resolution imaging method that improves image fidelity and extends to 3D imaging using multi-focus microscopy.

Light-sheet mesoscopy with the Mesolens provides fast sub-cellular resolution imaging throughout large tissue volumes.

The paper develops two light-sheet illuminators for the Mesolens to enable fast, high-resolution imaging of large tissue volumes.

Real-time denoising of fluorescence time-lapse imaging enables high-sensitivity observations of biological dynamics beyond the shot-noise limit

This paper introduces DeepCAD-RT, a real-time denoising method for fluorescence time-lapse imaging that improves signal-to-noise ratio with fewer photons, demonstrated across multiple organisms and biological processes.

Near Infrared-II Fluorescent protein for In-vivo Imaging

The paper introduces IRFP1032, the first NIR-II fluorescent protein, demonstrating superior brightness and enabling high-quality in vivo imaging applications.

FinnGen: Unique genetic insights from combining isolated population and national health register data

Finnish-enriched low-frequency variants, often coding, underlie many GWAS signals across 1,932 register endpoints in 218,792 Finns; a 15-disease meta-analysis with Estonian and UK biobanks adds 30 unreported associations.

GANscan: continuous scanning microscopy using deep learning deblurring

GANscan uses deep learning to restore sharp images from motion-blurred videos captured during continuous scanning, achieving 30x faster throughput than traditional stop-and-stare methods.

A conditional survival distribution-based method for censored data imputation: overcoming the hurdle in machine learning-based survival analysis

This paper introduces a method for imputing censored survival data to improve machine learning analysis in biomedical research.

Regulatory network-based imputation of dropouts in single-cell RNA sequencing data

The paper introduces a network-based method for dropout imputation in scRNA-seq data, showing that different genes benefit from different imputation strategies and introducing the ADImpute R-package.

Improved fluorescent proteins for dual-color post-embedding CLEM

The paper develops improved fluorescent proteins for dual-color post-embedding CLEM, enhancing signal-to-background ratio and reducing autofluorescence background.

BSImp: imputing partially observed methylation patterns for evaluating methylation heterogeneity

BSImp imputes partially observed methylation patterns to evaluate methylation heterogeneity more broadly and accurately than existing methods.

Sub-10 nm fluorescence imaging

This study identifies challenges in achieving sub-10 nm resolution in fluorescence imaging and proposes a method combining time-resolved detection and photoswitching fingerprint analysis to overcome these challenges.

High-throughput widefield fluorescence imaging of 3D samples using deep learning for 2D projection image restoration

This paper combines axial z-sweep imaging with deep learning to restore high-quality 2D projections of 3D biological samples, enabling high-throughput and quantitative analysis.

High-performance Flexible Microelectrode Array with PEDOT:PSS Coated 3D Micro-cones for Electromyographic Recording

This paper develops a flexible 3D microelectrode array with PEDOT:PSS coating for high-quality EMG recording, achieving high SNR and improved impedance.

Curvelet Transform-based Sparsity Promoting Algorithm for Fast Ultrasound Localization Microscopy

This paper introduces a curvelet transform-based sparsity promoting algorithm to accelerate ultrasound localization microscopy by recovering missing microbubble signals from short acquisition times.

Meta-imputation of transcriptome from genotypes across multiple datasets using summary-level data.

This paper introduces SWAM, a meta-imputation method that combines multiple transcriptome imputation models to improve gene expression prediction from genotypes using summary-level data.

SERM: a self-consistent deep learning solution forrapid and accurate gene expression recovery

SERM improves gene expression imputation in scRNA-seq data with higher accuracy and 100-fold faster computation than existing methods.