imputation

omicsGMF: a multi-tool for dimensionality reduction, batch correction and imputation applied to bulk- and single cell proteomics data.

omicsGMF integrates dimensionality reduction, batch correction, and imputation for bulk and single-cell proteomics data, improving statistical power for differential abundance detection.

Imputation strategy for population DNA methylation sequencing data

The paper compares imputation methods for targeted DNA methylation sequencing data in poplar and oak, finding NIPALS, MissForest, and LOESS as the most accurate.

GIMMEcpg: Global Imputation of Mean CpG MEthylation in Real-time

GIMMEcpg is a fast, scalable methylation imputation tool that improves accuracy and efficiency over existing methods, with a machine learning variant offering higher accuracy.

Direct-view oblique plane microscopy

This paper introduces a direct-view oblique plane microscopy technique for mesoscopic imaging, achieving efficient light collection and demonstrating imaging of a brain organoid.

Using the ancestral recombination graph to study the history of rare variants in founder populations

This paper uses ancestral recombination graphs to impute and trace rare variants in founder populations, showing high accuracy in mutation age and regional frequency estimation.

Patterned illumination enables denser deep-learning based single-molecule localization microscopy

This paper introduces SIMCODE, a method combining modulation patterns and deep learning to enhance single-molecule localization microscopy, achieving better resolution and performance in high-density samples.

Inference and visualization of complex genotype-phenotype maps with gpmap-tools

gpmap-tools uses Gaussian processes to infer and visualize genotype-phenotype maps with higher-order epistasis; across 262,144 Shine-Dalgarno variants it reveals register-specific peaks linked by three-nucleotide-offset ridges.

Penalised regression improves imputation of cell-type specific expression using RNA-seq data from mixed cell populations compared to domain-specific methods

This paper compares methods for imputing cell-type specific expression from mixed RNA-seq data, finding that machine learning methods like LASSO and ridge outperform domain-specific methods in recovering differential gene expression.

Up sampled PSF enables high accuracy 3D super-resolution imaging with sparse sampling rate

The paper introduces an up-sampled PSF method for 3D super-resolution imaging with sparse sampling, achieving high accuracy while reducing data volume and expanding field of view.

Agarose Stamped Device: A simple but effective fixation method for Zebrafish Larvae through Customizable 3D Printed Molds for Danio rerio (Zebrafish)

The paper introduces a novel agarose stamping device for immobilizing zebrafish larvae, improving imaging and behavioral studies through reduced stress and increased throughput.

To impute or not to impute in untargeted metabolomics - that is the compositional question

This study evaluates imputation methods for untargeted metabolomics data, finding that kNN and RF imputation perform poorly with missing data, especially MNAR, and that missing data proportion significantly affects accuracy.

Cross-species imputation and comparison of single-cell transcriptomic profiles

The paper introduces Icebear, a neural network framework for cross-species imputation and comparison of single-cell transcriptomic profiles, revealing evolutionary adaptations of X-chromosome upregulation in mammals.

A fully 3D-printed optical microscope for low-cost histological imaging

The paper describes a low-cost 3D-printed optical microscope capable of sub-cellular resolution for histological imaging, using affordable components and open design for replication.

A T2T-CHM13 recombination map and globally diverse haplotype reference panel improves phasing and imputation

This study shows that using a T2T-CHM13 recombination map and haplotype panel improves phasing and imputation accuracy compared to GRCh38.

Tissue Reconstruction with Generative AI

LUNA reconstructs tissue architecture from dissociated single-cell RNA-seq data using spatial priors learned from spatial transcriptomics, validating on mouse brain datasets and disease models.

Lipid-directed covalent fluorescent labeling of plasma membranes for long-term imaging, barcoding and manipulation of cells

This paper introduces MemGraft, a covalent fluorescent labeling method for plasma membranes that enables long-term imaging, barcoding, and manipulation of cells without probe exchange.

Sequencing whole genomes of the West Javanese population in Indonesia reveals novel variants and improves imputation accuracy

The paper improves imputation accuracy for Indonesians by adding West Javanese whole genome sequencing data to existing reference panels.

scRecover: Discriminating true and false zeros in single-cell RNA-seq data for imputation

scRecover imputes dropout zeros in scRNA-seq data while preserving true zeros, improving downstream analysis through accurate zero discrimination.

A New Paradigm for Genome-wide DNA Methylation Prediction Without Methylation Input

MethylProphet predicts whole-genome DNA methylation without methylation input using a gene-guided Transformer model trained on large-scale bisulfite sequencing data.

scGPT-spatial: Continual Pretraining of Single-Cell Foundation Model for Spatial Transcriptomics

Further pretraining a single-cell foundation model on 30 million spatial profiles, with a protocol-aware mixture-of-experts decoder and a neighbourhood objective, supports multi-slide integration, deconvolution and imputation.

Approaching Maximum Resolution in Structured Illumination Microscopy via Accurate Noise Modeling

This paper introduces B-SIM, an unsupervised Bayesian framework for structured illumination microscopy that improves resolution and contrast by accurately modeling noise, outperforming existing methods in both simulated and experimental data.

multiHIVE: Hierarchical Multimodal Deep Generative Model for Single-cell Multiomics Integration

multiHIVE integrates CITE-seq data using a hierarchical deep generative model, improving trajectory inference and gene trend identification.

CANDI: self-supervised, confidence-aware denoising imputation of genomic data

CANDI improves epigenome imputation by predicting raw counts, handling covariates, and providing uncertainty measures using a self-supervised Transformer model.

Mapping cells through time and space with moscot

moscot unifies optimal transport for temporal, spatial and spatiotemporal single-cell mapping, using multimodal cost spaces and low-rank solvers to scale to 1.7 million mouse embryo cells.

An expanded palette of bright and photostable organellar Ca2+ sensors

This paper introduces new organellar Ca2+ sensors with tunable colors and improved brightness and photostability for multiplexed measurements in different organelles.

Wide-field bond-selective fluorescence imaging: from single-molecule to cellular imaging beyond video-rate

This paper introduces WF-BonFIRE, a wide-field bond-selective fluorescence imaging technique that achieves single-molecule sensitivity and kilohertz speeds for live-cell and bacterial imaging.

Rapid and accurate multi-phenotype imputation for millions of individuals

The paper introduces PIXANT, a multi-phenotype imputation method that improves GWAS power by imputing 425 phenotypes for 277,301 individuals, leading to the discovery of 18.4% more GWAS loci.

Integration and querying of multimodal single-cell data with PoE-VAE

This paper introduces a VAE-based model for integrating multimodal single-cell data, showing it can map queries across modalities and improve data imputation and biological discovery.

Using Beads as a Focus Fiduciary to Aid Software-based Autofocus Accuracy in Microscopy

This paper describes using microbeads to improve autofocus accuracy in brightfield microscopy for long-term live cell imaging.

A Novel Efficient Algorithm for Common Variants Genotyping from Low-Coverage Sequencing Data

The paper introduces Limpute, an efficient algorithm for genotyping common variants from low-coverage sequencing data, achieving high imputation accuracy with faster runtime than GLIMPSE2.