Article

High-Dimensional Sensitivity Analysis for Genomic Studies: An Adversarial Framework for Learning Worst-Case Latent Confounders

2026-05-29

Abstract excerpt

High-dimensional genomics studies are frequently confounded by unmeasured biological processes that obscure disease-specific signals. While existing workflows can estimate these latent confounders, they fail to quantify how robust a discovery is to varying levels of hypothetical confounding. We introduce sensGAN, a deep-learning adversarial framework that systematically explores the confounding spectrum by learnin...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 8b12624b-0a70-537d-8611-6acb1d573fc5
DOI: 10.64898/2026.05.27.728283

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

High-Dimensional Sensitivity Analysis for Genomic Studies: An Adversarial Framework for Learning Worst-Case Latent ConfoundersDOI 10.64898/2026.05.27.728283Read

Pix2Path: Integrating Spatial Transcriptomics and Digital Pathology with Deep Learning to Score Pathological Risk and Link Gene Expression to Disease MechanismsSemantic proximity Read

Uncovering causal relationships in single-cell omic studies with causarraySemantic proximity Read

A Novel Method to Disentangle Tightly Linked Risk and Resilience Genes for Brain Disorders: Application to Alzheimer’s DiseaseSemantic proximity Read

Sensitivity based model agnostic scalable explanations of deep learningSemantic proximity Read

Explainable Artificial Intelligence for Cross-Dataset Generalizable Biomarker Discovery in Cardiovascular diseases (CVDs)Semantic proximity Read

CauReL: Dynamic Counterfactual Learning for Precision Drug Repurposing in Alzheimer's DiseaseSemantic proximity Read

Generative Augmentation Reveals Previously Overlooked Signals in Transcriptomic DatasetsSemantic proximity Read

DeepEXPOKE: A Deep Learning Framework with Polygenic Risk Scores as Knockoffs for Deconvoluting Genetic and Non-Genetic Exposure Risks in Sepsis and Coronary Heart DiseaseSemantic proximity Read

Learning Genetic Perturbation Effects with Variational Causal InferenceSemantic proximity Read

Predicting LncRNA-Disease Association Based on Generative Adversarial Network.Semantic proximity Read

Multi-omics Data Integration by Generative Adversarial NetworkSemantic proximity Read

Interventionally-guided representation learning for robust and interpretable AI models in cancer medicineSemantic proximity Read