Article

Gene–Morphology Alignment via Graph-Constrained Latent Modeling for Molecular Subtype Prediction from Histopathology in Pancreatic Cancer

2026-03-06

Abstract excerpt

1 Molecular subtyping of cancer is traditionally defined in transcriptomic space, yet routine clinical deployment is limited by the availability and cost of sequencing. Meanwhile, histopathology captures rich morphological information that is known to correlate with molecular state but lacks a principled, mechanistic bridge to gene-level representations. We propose a graph-constrained learning framework that align...

Topics

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

Identifiers and source

Literature Corpus work: 17d220b5-a4b6-546f-a48b-e1d0468a68c3
DOI: 10.64898/2026.03.05.26347711

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Gene–Morphology Alignment via Graph-Constrained Latent Modeling for Molecular Subtype Prediction from Histopathology in Pancreatic CancerDOI 10.64898/2026.03.05.26347711Read

Inferring Clinically Relevant Molecular Subtypes of Pancreatic Cancer from Routine Histopathology Using Deep LearningSemantic proximity Read

Graph-Regularised Multi-Omics Autoencoders Improve Stability and Clinical Coherence of Breast Cancer Patient EmbeddingsSemantic proximity Read

Pan-cancer virtual spatial transcriptomics from routine histology with PhoenixSemantic proximity Read

Integrative analysis of genomic and transcriptomic data informs precancer progression in the pancreasSemantic proximity Read

Integrating cellular graph embeddings with tumor morphological features to predict in-silico spatial transcriptomics from H&E imagesSemantic proximity Read

PathOmCLIP: Connecting tumor histology with spatial gene expression via locally enhanced contrastive learning of Pathology and Single-cell foundation modelSemantic proximity Read

SORBET: Automated cell-neighborhood analysis of spatial transcriptomics or proteomics for interpretable sample classification via GNNSemantic proximity Read

miniMTI: minimal multiplex tissue imaging enhances biomarker expression prediction from histologySemantic proximity Read

Adaptive Integration of Heterogeneous Foundation Models to Find Histologically Predictable Genes in Breast CancerSemantic proximity Read

Phenotypic inference from sparse tumor genomes informs an explainable deep-learning model for cancer prognosisSemantic proximity Read