SEARCH · PubMed Health

Results for “Variational autoencoder”

Explore indexed PubMed citations for clinical trials, systematic reviews and public health research. Read source abstracts and follow each citation to its original PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

14 recordsLinked to original sources

PubMed2026

SIVA: diagonal integration of spatial multi-omics data via spatially informed variational autoencoders and anchor guidance.

MOTIVATION: Understanding cellular states and regulatory programs requires integrative analysis of multiple omics layers. Although recent spatial sequencing technologies allow molecular profiling of cells within their tissue context, paired spatial multi-omics assays are still limited by technical complexity and cost. This creates a pressing need for diagonal integration methods that enable joint analysis of unpaired spatial omics datasets. RESULTS: We propose SIVA, a deep generative framework based on Spatially-Informed Variational Autoencoders with Anchor Guidance, for diagonal integration of spatial multi-modal data. SIVA employs modality-specific variational autoencoders (VAEs) with a hybrid latent embedding that integrates Gaussian process and standard Gaussian priors, enabling joint modeling of spatially structured variation and dominant underlying data distributions across modalities. To facilitate cross-modal alignment in the absence of one-to-one cell correspondence, SIVA adopts a dual integration strategy combining global distribution alignment via Maximum Mean Discrepancy and local correspondence guidance using mutual nearest neighbor anchors. Extensive experiments across multiple cross-slice integration scenarios demonstrate that SIVA achieves robust and accurate integration of unpaired spatial omics datasets, consistently outperforming existing methods. AVAILABILITY AND IMPLEMENTATION: The source codes are available at https://github.com/PelenJiang/SIVA.

Autoencoder↗

PubMed2026

Unifying multimodal single-cell data with a mixture-of-experts β-variational autoencoder framework.

Multimodal single-cell assays profile complementary layers of cell state, but integration is complicated by modality mismatch, sparsity, and uneven cohort coverage. Here, we present Unified Variational Inference (UniVI), a scalable mixture-of-experts β-variational autoencoder that learns a shared latent space while preserving modality-specific structure. UniVI couples modality-specific encoders/decoders with a shared latent prior and a symmetric cross-modal alignment objective, enabling consistent integration of paired measurements without curated feature-link graphs or preannotated reference atlases; optional supervised heads can be added when labels are available. Across paired RNA-protein (CITE-seq) and RNA-chromatin (10x Genomics Multiome, SHARE-seq) data spanning human PBMCs and mouse back skin-a nonhematopoietic tissue with continuous differentiation hierarchies-UniVI produces coherent embeddings, improves label transfer, and enables cross-modal reconstruction and denoising. Extending to trimodal measurements, UniVI maintains robust three-way alignment among RNA, chromatin accessibility, and surface proteins (TEA-seq), and accommodates DNA methylation in a paired scNMT-seq mouse gastrulation proof-of-concept under beta-binomial likelihoods. Performance degrades gracefully under severe cell type imbalance and in the presence of modality-exclusive populations. In an acute myeloid leukemia mosaic design, a paired RNA-protein bridge anchors independent RNA-only and protein+genotype cohorts, revealing genotype-associated neighborhoods that sharpen with mutation-aware fine-tuning. UniVI thus provides a flexible, interpretable framework for multimodal integration across paired, trimodal, and mosaic study designs and supports practical reference-to-query projection in partially observed studies.

Journal Article↗

PubMed2026

ARCADIA reveals spatially dependent transcriptional programs through integration of scRNA-seq and spatial proteomics.

MOTIVATION: Cellular states are strongly influenced by spatial context, but single-cell RNA sequencing (scRNA-seq) loses information about local tissue organization, while spatial proteomic assays capture limited marker panels that constrain transcriptomic inference. Integrating these modalities can elucidate how spatial niches shape transcriptional programs, yet existing approaches depend on either feature-level correspondence such as gene-protein linkage or cell-level barcode pairing, which is often unavailable. RESULTS: We present ARCADIA (ARchetype-based Clustering and Alignment with Dual Integrative Autoencoders), a generative framework for cross-modal integration that operates without cell barcode pairing and does not assume direct feature-to-feature correspondence. ARCADIA identifies modality-specific archetypes, that is, convex combinations of cells representing extreme phenotypic states, and aligns these anchors across modalities by minimizing the discrepancy between their cell-type composition profiles. The aligned archetypes define a shared coordinate system that anchors dual variational autoencoders (VAEs) trained with cross-modal geometric regularization, preserving archetype structure and spatial neighborhood information while enabling bidirectional translation between modalities. On semi-synthetic CITE-seq data, ARCADIA outperforms existing weak-linkage methods. Applied to independent human tonsil scRNA-seq and CODEX data, ARCADIA reconstructs known tissue architecture and reveals spatially dependent transcriptional programs linking B-cell maturation and T-cell activation or exhaustion to microenvironmental niches. AVAILABILITY AND IMPLEMENTATION: Source code is accessible at https://github.com/azizilab/ARCADIA_public. Reproducibility scripts and data are available at https://github.com/azizilab/arcadia_reproducibility.

Proteomics↗

PubMed2025

In silico generation of synthetic cancer genomes using generative AI.

Understanding how genomic alterations drive cancer is key to advancing precision oncology. To detect these alterations, accurate algorithms are used; however, due to privacy concerns, few deeply sequenced cancer genomes can be shared, limiting benchmarking and representing a major obstacle to the improvement of analytic tools. To address this, we developed OncoGAN, a generative AI model combining adversarial networks and variational autoencoders to create realistic synthetic cancer genomes. Trained on large-scale genomic datasets, OncoGAN accurately reproduces somatic mutations, copy number alterations, and structural variants across cancer types while preserving donors' privacy. The synthetic genomes reflect tumor-specific mutational signatures and positional mutation patterns. Using DeepTumour, we validated the synthetic data's fidelity, showing high concordance between generated and predicted tumors. Moreover, augmenting the training data with synthetic genomes improved DeepTumour's accuracy, underscoring OncoGAN's potential to generate shareable datasets with known ground truths for benchmarking and enhancement of cancer genome analysis tools.

Humans↗

PubMed2026

Deep generative models in biological sequence and structure analysis and design.

Deep generative models have transformed biological sequence modeling from predictive analysis toward increasingly controllable design. Early biological applications of Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) established latent representation learning and sequence synthesis, while recent advances in transformer-based language models, discrete diffusion, flow-matching, and multimodal generative frameworks have substantially expanded the scope of biological design. This review examines generative models for DNA, RNA, and protein sequence design, emphasizing how different model classes represent biological constraints, operate over discrete and continuous spaces, and integrate sequence, structure, and function. We compare VAEs, GANs, autoregressive and masked language models, diffusion models, and flow-based approaches across genomics, transcriptomics, and proteomics, with particular attention to controllability, long-range dependency modeling, structural grounding, generalization, and experimental utility. We further examine evaluation strategies, out-of-distribution generalization, and closed-loop design-build-test-learn workflows that connect in silico generation with empirical validation. We distinguish fundamental modality-dependent constraints including sequence discreteness, context length, structural coupling, and physical or thermodynamic requirements from architecture-dependent advantages that reflect the current state of the field. Current studies suggest that long-context models are particularly useful for genome-scale representation and sequence modeling, whereas structure-aware diffusion, flow-based, and inverse-folding approaches provide better frameworks for geometry-constrained RNA and protein design. This perspective provides a critical framework for understanding the present capabilities, limitations, and convergence of generative approaches toward reliable and experimentally grounded biological design.

Biological sequence analysis↗

PubMed2021

Deep generative neural network for accurate drug response imputation.

Drug response differs substantially in cancer patients due to inter- and intra-tumor heterogeneity. Particularly, transcriptome context, especially tumor microenvironment, has been shown playing a significant role in shaping the actual treatment outcome. In this study, we develop a deep variational autoencoder (VAE) model to compress thousands of genes into latent vectors in a low-dimensional space. We then demonstrate that these encoded vectors could accurately impute drug response, outperform standard signature-gene based approaches, and appropriately control the overfitting problem. We apply rigorous quality assessment and validation, including assessing the impact of cell line lineage, cross-validation, cross-panel evaluation, and application in independent clinical data sets, to warrant the accuracy of the imputed drug response in both cell lines and cancer samples. Specifically, the expression-regulated component (EReX) of the observed drug response achieves high correlation across panels. Using the well-trained models, we impute drug response of The Cancer Genome Atlas data and investigate the features and signatures associated with the imputed drug response, including cell line origins, somatic mutations and tumor mutation burdens, tumor microenvironment, and confounding factors. In summary, our deep learning method and the results are useful for the study of signatures and markers of drug response.

Antineoplastic Agents↗

PubMed2026

Yomix: an interactive tool for the exploration of low-dimensional embeddings in omics data.

SUMMARY: In the analysis of diverse omics data, a common and important preliminary step involves computing low-dimensional embeddings using techniques such as PCA, UMAP, t-SNE, or variational autoencoders. These embeddings provide a global overview of sample distributions and their relationships, often serving as the basis for formulating biological hypotheses. To facilitate rapid and intuitive exploration of such low-dimensional embeddings, we developed Yomix, an interactive omics-agnostic visualization and data exploration tool. Yomix enables users to flexibly define subsets of interest using a lasso selection tool, instantly compute their feature signatures, and compare their distributions. Yomix is a fast and efficient tool for interactive exploration of diverse omics datasets. AVAILABILITY AND IMPLEMENTATION: Yomix and its documentation are publicly available at https://github.com/perrin-isir/yomix.

Software↗

PubMed2026

EscaPRRS-ORF5: a structure-aware evolutionary framework for prioritizing immune escape-prone variants in porcine reproductive and respiratory syndrome virus.

MOTIVATION: Porcine Reproductive and Respiratory Syndrome Virus (PRRSV) is a rapidly evolving RNA virus causing significant economic losses, posing a formidable challenge to vaccine efficacy due to its high mutational variability and immune escape. As the viral mutants evolve, their ability to sustain in population is driven by a range of host biology factors such as receptor binding, fusion, and uncoating. Existing tools that predict viral fitness and escape propensities rely heavily on extensive, up-to-date sequence data and lack integration of biochemical host interactions, limiting mechanistic understanding of the mutational landscape. We introduce Esca, a sequence-only toolchain framework that identifies immune escape-prone residues by exhaustively scanning each residue position for all amino acid substitutions using a Bayesian Variational Autoencoder (VAE) trained on protein language model embeddings. We demonstrate Esca on the GP5(ORF5) glycoprotein of PRRSV (EscaPRRS-ORF5) by training on ESM-2 embeddings of 32 146 GP5 sequences (2015-2022) spanning 140 sub-lineages. RESULTS: Despite being trained only on GP5 sequence data, EscaPRRS-ORF5 recovered 85.7% of the surface-exposed receptor binding interfaces as escape-prone regions. We use a mutation-sensitive fitness scoring scheme that goes beyond Hamming distances, to predict antibody escape tendencies, supporting surveillance of (re) emerging PRRSV variants. We do not claim that ORF5 alone captures PRRSV evolution or serves as a surveillance endpoint; rather, Esca offers a scalable path toward whole-genome, structure-aware surveillance. AVAILABILITY AND IMPLEMENTATION: EscaPRRS-ORF5 is freely available at https://doi.org/10.6084/m9.figshare.32661033 with an interactive Colab notebook at https://colab.research.google.com/drive/1TEgzAhPwvNAZ01VXeJbIFibfri2jnDA5? usp=sharing.

Porcine respiratory and reproductive syndrome viru↗

PubMed2026

Enterocutaneous Fistula-Associated Sepsis and Mortality: Development and Validation of a Multimodal Artificial Intelligence Prediction Model.

BACKGROUND: Predicting enterocutaneous fistula (ECF)-associated sepsis and mortality poses significant challenges in digital health care due to the disease's complexity and heterogeneous clinical manifestations. Current approaches that rely on single-modal data or traditional scoring systems often fail to capture the intricate immune-inflammatory dynamics and multisystem involvement in patients with ECF. OBJECTIVE: This study aims to develop an artificial intelligence (AI)-driven multimodal fusion model integrating clinical, imaging, and transcriptomic data for early prediction of ECF-associated sepsis and 28-day mortality, addressing the limitations of conventional single-dimensional models. METHODS: This study leveraged publicly available datasets (Medical Information Mart for Intensive Care III [MIMIC-III], electronic Intensive Care Unit [eICU], and The Cancer Genome Atlas) to construct a multimodal framework. Clinical parameters were processed using Extreme Gradient Boosting, abdominal imaging features were extracted via convolutional neural networks, and transcriptomic profiles were analyzed with variational autoencoders. A Transformer-based fusion network was employed for joint prediction and validated through cross-validation and external testing. Key features were identified using Shapley Additive Explanations and Local Interpretable Model-Agnostic Explanations interpretability algorithms, while immune regulatory mechanisms were explored via weighted gene co-expression network analysis. RESULTS: The multimodal model achieved an area under the curve (AUC) of 0.89 for predicting sepsis and 28-day mortality, outperforming unimodal models (clinical-only model, AUC 0.72, and imaging-only model, AUC 0.78). Critical predictors included Sequential Organ Failure Assessment score, lactate levels, intra-abdominal free fluid on imaging, and immunoregulatory genes (programmed death-ligand 1 [PD-L1] and indoleamine 2,3-dioxygenase 1 [IDO1]). Mechanistic analysis revealed distinct immune reprogramming in patients with sepsis, characterized by increased regulatory T cells and M2 macrophages, along with downregulated cluster of differentiation 8+ (CD8+) T cells. CONCLUSIONS: This multimodal AI model offers an innovative digital solution in medical informatics, enabling precise early risk stratification for ECF-associated sepsis. By integrating multisource data and providing interpretable insights into immune-inflammatory pathways, the model enhances health care quality for patients with ECF and paves the way for personalized intervention strategies.

Humans↗

PubMed2026

GENKI: A generative framework for scalable and robust metabolic kinetic modeling.

GENKI (Generative ENsemble KPI-Informed) is a variational autoencoder-based framework for large-scale kinetic modeling of metabolism. Developed for metabolic engineering applications, GENKI is designed to improve the recovery of kinetically feasible models that reproduce experimentally observed phenotypes under genetic and environmental perturbations. The framework is trained on feasible kinetic model ensembles and uses phenotype-based key performance indicators (KPIs), derived from multi-omics and bioprocess data, to label and enrich models according to their agreement with mutant and condition-specific observations. This enables targeted generation of biologically relevant parameter sets with improved predictive performance. Crucially, GENKI recovers kinetic parameter sets that jointly reproduce wild-type and multiple perturbed physiologies within a single model. We apply GENKI to large-scale kinetic models of Escherichia coli and Saccharomyces cerevisiae under enzyme perturbations and oxygen shifts. In both systems, GENKI enriches kinetic ensembles with models that more accurately reproduce experimentally observed physiologies across multiple perturbations and conditions. GENKI therefore provides a practical framework for perturbation-aware kinetic model refinement within iterative Design-Build-Test-Learn workflows.

DBTL↗

PubMed2025

JASMINE: A powerful representation learning method for enhanced analysis of incomplete multi-omics data.

Integrative analysis of multi-omics data provides a more comprehensive and nuanced view of a subject's biological state. However, high-dimensionality and ubiquitous modality missingness present significant analytical challenges. Existing methods for incomplete multi-omics data are scarce, do not fully leverage both modality-specific and shared information, and produce task-biased representations. We propose JASMINE, a self-supervised representation learning method for incomplete multi-omics data that preserves both modality-specific and joint information and enhances sample similarity structure. JASMINE produces embeddings that achieve superior performance across multiple tasks for two different incomplete multi-omics datasets while requiring only a single round of training per dataset.

missing data↗

PubMed2024

A deep learning framework for denoising and ordering scRNA-seq data using adversarial autoencoder with dynamic batching.

Single-cell RNA sequencing (scRNA-seq) provides high resolution of cell-to-cell variation in gene expression and offers insights into cell heterogeneity, differentiating dynamics, and disease mechanisms. However, technical challenges such as low capture rates and dropout events can introduce noise in data analysis. Here, we present a deep learning framework, called the dynamic batching adversarial autoencoder (DB-AAE), for denoising scRNA-seq datasets. First, we describe steps to set up the computing environment, training, and tuning. Then, we depict the visualization of the denoising results. For complete details on the use and execution of this protocol, please refer to Ko et al.1.

Deep Learning↗

PubMed2025

PROTRIDER: protein abundance outlier detection from mass spectrometry-based proteomics data with a conditional autoencoder.

MOTIVATION: Detection of gene regulatory aberrations enhances our ability to interpret the impact of inherited and acquired genetic variation for rare disease diagnostics and tumor characterization. While numerous methods for calling RNA expression outliers from RNA-sequencing data have been proposed, the establishment of protein expression outliers from mass spectrometry data is lacking. RESULTS: Here, we propose and assess various modeling approaches to call protein expression outliers across three datasets from rare disease diagnostics and oncology. We use as independent evidence the enrichment for outlier calls in matched RNA-seq samples and the enrichment for rare variants likely disrupting protein expression. We show that controlling for hidden confounders and technical covariates, while simultaneously modeling the occurrence of missing values, is largely beneficial and can be achieved using conditional autoencoders. Moreover, we find that the differences between experimental and fitted log-transformed intensities by such models exhibit heavy tails that are poorly captured with the Gaussian distribution and report stronger statistical calibration when instead using the Student's t-distribution. Our resulting method, PROTRIDER, outperformed baseline approaches based on raw log-intensities Z-scores, PCA, and isolation-based anomaly detection with Isolation forests. The application of PROTRIDER reveals significant enrichments of AlphaMissense pathogenic variants in protein expression outliers. Overall, PROTRIDER provides a method to confidently identify aberrantly expressed proteins applicable to rare disease diagnostics and cancer proteomics. AVAILABILITY AND IMPLEMENTATION: PROTRIDER is freely available at github.com/gagneurlab/PROTRIDER and also available on Zenodo under the DOI zenodo.15569781.

Proteomics↗

PubMed2025

scMultiNODE: Integrative and Scalable Framework for Multi-Modal Temporal Single-Cell Data.

Measuring single-cell genomic profiles at different timepoints enables our understanding of cell development. This understanding is more comprehensive when we perform an integrative analysis of multiple measurements (or modalities) across various developmental stages. However, obtaining such measurements from the same set of single cells is resource-intensive, restricting our ability to study them jointly. We introduce scMultiNODE, an unsupervised integration model that combines gene expression and chromatin accessibility measurements in developing single cells, while preserving cell type variations and cellular dynamics. First, scMultiNODE uses a scalable, Quantized Gromov-Wasserstein optimal transport to align a large number of cells across different measurements. Next, it utilizes neural ordinary differential equations to explicitly model cell development with a regularization term to learn a dynamic latent space. Experiments on six real-world developmental single-cell datasets demonstrate that scMultiNODE can integrate temporally profiled multi-modal single-cell measurements more effectively than existing methods that focus on cell type variations and often overlook cellular dynamics. We also demonstrate that scMultiNODE's joint latent space facilitates several insightful downstream analyses of single-cell development, including the investigation of complex cell trajectories and the enabling of cross-modal label transfer. The data and code are publicly available at https://github.com/rsinghlab/scMultiNODE.

autoencoders↗