imputation

A Unified Framework for Batch Correction and Imputation in Modern Mass Spectrometry Proteomics

NMFBatch reduces technical variation and preserves biological structure in proteomics data through batch correction and imputation.

Recovering biological structure in sparse single-cell proteomics with GIRAFI

GIRAFI improves sparse single-cell proteomics by imputing missing values and revealing cell states using graph-informed statistical learning, outperforming existing methods and recovering biological structure.

DGAT: A Dual-Graph Attention Network for Inferring Spatial Protein Landscapes from Transcriptomics

DGAT imputes spatial protein expression from transcriptomics-only data, revealing cell states and tissue organization not visible from RNA alone.

slideimp: Efficient Imputation for DNA Methylation Data

slideimp provides efficient imputation methods for DNA methylation data, achieving faster runtime and lower memory usage while maintaining accuracy.

Aberration-aware 3D localization microscopy via self-supervised neural-physics learning

This paper introduces LUNAR, a self-supervised neural-physics learning framework for 3D localization microscopy that improves robustness to optical aberrations and high-density molecule localization.

Evaluation of fluorescent proteins for compatibility with STED microscopy systems using two-color spectroscopies

The paper evaluates fluorescent proteins for STED microscopy compatibility using two-color spectroscopy, showing improved 3D resolution in compatible proteins.

Inferring absolute counts from proportions by constraining multivariate normal distributions

This paper introduces MCI, a method to estimate absolute counts from proportional data using multivariate normal distributions, and demonstrates its effectiveness on white blood cell counts and single-cell mRNA data.

Deep Computational Anatomy via Latent-Aligned Multiview Normalizing Flows

The paper introduces LAMNr flows for multimodal data analysis, enabling shared latent subspaces and cross-view imputation, with applications in biological imaging.

Machine learning cross-platform proteomic imputation enables protein quality scoring and replication of epidemiological associations

This paper develops a machine learning framework to impute cross-platform proteomic data, improving replication of epidemiological findings and protein quality scoring.

RiboPipe: efficient per-transcript codon-resolution ribo-seq coverage imputation for low-coverage transcripts

RiboPipe imputes codon-resolution Ribo-seq coverage for low-coverage transcripts using a unified framework that improves accuracy and efficiency.

CAPTAIN: A multimodal foundation model pretrained on co-assayed single-cell RNA and protein

CAPTAIN is a multimodal foundation model trained on single-cell RNA and protein data, improving multi-omics integration and uncovering protein-driven intercellular dynamics.

JUMPlion improves quantitative DIA proteomics through ion-level recovery of missing values

JUMPlion improves DIA proteomics by recovering missing ion-level values, enhancing protein quantification accuracy in low-input and single-cell analyses.

GatorSC: Multi-Scale Cell and Gene Graphs with Mixture-of-Experts Fusion for Single-Cell Transcriptomics

GatorSC improves single-cell transcriptomic analysis by integrating multi-scale cell and gene graphs with a Mixture-of-Experts fusion framework, outperforming existing methods in clustering, imputation, and annotation.

Unbend: Correction of local beam-induced sample motion in cryo-EM images using a 3D spline model

Unbend improves cryo-EM image correction by addressing localized sample motion with a 3D spline model, enhancing signal-to-noise ratio and particle detection.

Optimal Reference Panel Design in Ancient DNA Imputation from Coalescent Theory, Simulation, and Real Data Application with an Ancient Reference Panel

This paper evaluates optimal reference panels for ancient DNA imputation using coalescent theory, simulations, and a real dataset, finding that including ancient samples improves imputation accuracy for rare variants.

Unified imputation of missing data modalities and features in multi-omic data via shared representation learning

MIMIR is a deep learning framework that imputes missing modalities and features in multi-omic data using shared representation learning, outperforming existing methods on pan-cancer data.

Mosaic integration of spatial multi-omics with SpaMosaic

SpaMosaic integrates spatial multi-omics data using contrastive learning and graph neural networks, improving spatial domain identification and missing modality imputation across diverse datasets.

Repetition-controllable gain-managed nonlinear fiber amplifier enables ultrashort, multiphoton imaging with reduced photodamage

The paper introduces a repetition-controllable gain-managed nonlinear fiber amplifier that enables label-free multiphoton imaging with reduced photodamage in live cells and tissues.

Machine Learning Predictions Surpass Individual mRNAs as a Proxy of Single-cell Protein Expression

The paper compares machine learning models for predicting single-cell protein expression from RNA-seq data to mRNA levels, finding that models outperform mRNA as a proxy.

Using machine learning to overcome mosquito collections missing data for malaria modeling

The paper uses machine learning to impute missing mosquito data and improve malaria incidence predictions in Bolivar State, Venezuela, but finds it ineffective for P. falciparum.

CanVAS: A Harmonized and Imputed Canine Variant Atlas1

CanVAS harmonizes and imputes canine genotype data from multiple sources to create a unified resource for genetic studies.

Singletrack: An Algorithm for Improving Memory Consumption and Performance of Gap-Affine Sequence Alignment

Singletrack improves memory efficiency and performance for gap-affine sequence alignment without sacrificing accuracy.

Generating, curating, and evaluating trnL reference sequence databases: Benchmarking OBITools3/ecoPCR, RESCRIPt, and MetaCurator

The paper evaluates three trnL reference sequence databases generated using different curation tools and assesses their classification performance across trnL regions.

DNA-Functionalized Nanoparticles for Multicolor Cathodoluminescence Imaging

This paper develops DNA-functionalized lanthanide nanoparticles for multicolor cathodoluminescence imaging in biological samples, showing retention of CL emission after EM preparation steps.

Volumetric Scattering Microscopy

This paper introduces Volumetric Scattering Microscopy (VSM), a computational framework for 3D fluorescence imaging in scattering biological media, achieving high-fidelity volumetric reconstruction across various samples.

Doubling the Field of View in Common-Path Digital Holographic Microscopy via Wavelength Scanning and Polarization Gratings

The paper presents a method to double the field of view in common-path digital holographic microscopy by using wavelength scanning and polarization gratings to separate overlapping object beams.

Maximizing photon utilization in spectroscopic single-molecule localization microscopy using symmetrically dispersed dual-wedge prisms

This paper introduces a symmetrically dispersed dual-wedge prism design for spectroscopic single-molecule localization microscopy, improving lateral and spectral precision.

Fiber optical parametric amplification of low-photon-flux microscopy signals

This paper demonstrates fiber optical parametric amplification to boost low-photon-flux microscopy signals, achieving higher sensitivity and bandwidth than conventional detectors.

An atlas of genetic effects on the monocyte methylome across European and African populations

The paper constructs a multi-ancestry methylome atlas of purified monocytes, identifies population-specific methylation quantitative trait loci, and performs methylome-wide association studies for 41 traits, revealing novel associations for type 2 diabetes.

Hydrogel Fiber Endomicroscopy

This paper introduces HYFEN, a hydrogel-based endomicroscopy platform that enables flexible, biocompatible, and subcellular-scale fluorescence imaging with improved resolution and performance compared to conventional silica-based fibers.