imputation

LGTM: Gaussian Process Modulated Neural Topic Modeling for Longitudinal Microbiome

LGTM couples a neural topic model with additive basis-function Gaussian processes, learning microbial co-abundance topics and how covariates relate to their trajectories in longitudinal gut microbiome data.

GROMTools: scalable individual-level GReX imputation for mega-biobank-scale cohorts

GROMTools, a sparse-weight C++/R engine streaming PLINK2 genotypes, reproduces PrediXcan and PLINK2 GReX imputations with about 100-fold less CPU time and 33-fold less peak memory.

CycloCross: Adversarial single-cell RNA-seq data translation across species

Translating cells between mouse, macaque and human scRNA-seq with a CycleGAN, without ortholog mapping, preserved developmental time structure, imputed missing states and produced more realistic synthetic cells than scGAN.

Benchmarking of bulk transcriptomic harmonization tools in a multi-platform B-cell lymphoma cohort identifies feature-specific quantile normalization and surrogate variable analysis as top-performing methods

Across 7,174 multi-platform lymphoma transcriptomes, only surrogate variable analysis and feature-specific quantile normalization corrected batch effects while keeping subtype and normal B-cell differences; top-scoring MNN erased biomarker correlations.

Generative machine learning unlocks the first proteome-wide image of human cells

A conditional latent diffusion transformer predicts immunofluorescence images of 12,800 human proteins from nucleus, ER and microtubule stains, outperforming PUPS and CELL-Diff, including on an unseen drug-treated cell line.

Tensile Expansion Mass Spectrometry for single cell metabolomics imaging

Tensile stretching of live, unfixed OVCAR8 cells on a fibronectin-functionalized double-network hydrogel expands them about 1.7x linearly, enabling single-cell MALDI metabolite imaging on unmodified commercial instruments.

A pangenome-graph approach for mapping and imputing barley sequences

Pan20, a Practical Haplotype Graph of 20 barley genomes, assigns sequences MorexV3 coordinates and imputes genotyping-by-sequencing (GBS) reads at 0.06% base-call error versus 0.32% for variant calling.

OmicsPred as a centralised resource for genetic prediction of multi-omic traits

OmicsPred collects 3,339,469 genetic prediction models for transcript, protein and metabolite traits with harmonised metadata and MetaXcan/PGSC-Calculator files, plus multi-ancestry Million Veterans Program phenome-wide association results.

STPath: A Generative Foundation Model for Integrating Spatial Transcriptomics and Whole Slide Images

A masked-expression Transformer trained on 983 paired H&E and spatial transcriptomics slides predicts 38,984 genes from histology without fine-tuning, leading HEST-Bench and improving survival and mutation prediction.

Spatial and single-cell expression analyses reveal complex expression domains in early wheat spike development

Combining 99-gene smFISH across 48,225 cells with scRNA-seq of 26,009 cells maps 21 spatial expression domains and imputes 74,464 genes in early tetraploid wheat spikes.

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.

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.

Family-GWAS reveals effects of environment and mating on genetic associations

Family-based GWAS meta-analysis of 34 phenotypes shows standard GWAS effects carry sizeable confounding uncorrelated with direct genetic effects, while assortative mating likely inflates SNP heritability and genetic correlations.

Increasing the throughput of sensitive proteomics by plexDIA

Multiplexing nonisobaric isotopologous mass tags (mTRAQ) with data-independent acquisition and DIA-NN increases sensitive proteomics throughput 3-fold while cutting missing data below 3% in bulk and single cells.

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.

Sequencing of 53,831 diverse genomes from the NHLBI TOPMed Program

Over 400 million variants, 97% below 1% frequency, emerge from deep whole-genome sequencing of 53,831 diverse TOPMed participants; TOPMed haplotypes enable imputation down to ~0.01% frequency.

Comprehensive integration of single cell data

Seurat v3 finds scored mutual-nearest-neighbor anchors in canonical correlation space to integrate scRNA-seq batches and transfer labels, protein levels and transcriptome-wide expression across modalities.

Whole exome sequencing and characterization of coding variation in 49,960 individuals in the UK Biobank

Exomes of 49,960 UK Biobank participants reveal 231,631 predicted loss-of-function variants (>10-fold more than imputed data); burden tests implicate PIEZO1, MEPE, and COL6A1 in disease traits.

Zero-preserving imputation of scRNA-seq data using low-rank approximation

Truncated SVD plus a per-gene threshold at the most negative value fills dropouts while leaving biological zeros alone, and runs on 50,000 cells in about 40 minutes.

Multi-Omics factor analysis - a framework for unsupervised integration of multi-omic data sets

MOFA, a sparse Bayesian factor model with mixed likelihoods, separates shared from modality-specific multi-omic variation, recovering IGHV, trisomy 12 and oxidative-stress axes in 200 leukaemia samples.

BGEN: a binary file format for imputed genotype and haplotype data

Encoding imputed genotype probabilities at 8 bits in BGEN gave compact files, ~240 million probabilities parsed per second and association results near-identical to 20-bit data (UK BiLEVE chromosome 22).

K-nearest neighbor smoothing for high-throughput single-cell RNA-Seq data

Aggregating UMI counts from a cell's nearest neighbours, chosen step-wise on variance-stabilised profiles, cuts technical noise enough that PCA and hierarchical clustering resolve cell types and T cell subsets.

Genome-wide genetic data on ~500,000 UK Biobank participants

Quality-controlled genotypes for 488,377 UK Biobank participants at 805,426 markers, imputed to ~96 million variants, plus ancestry PCs, kinship (30.3% have close relatives enrolled) and HLA calls.