Viktor Hendrik Koelzer

This study benchmarks uncertainty estimation in virtual spatial transcriptomics, finding that predicted means largely explain prediction error, and uncertainty provides limited additional information.

The paper identifies an RFX-driven ciliogenic cell state in colorectal cancer that is sensitive to FGFR inhibitors and associated with poor prognosis.

This paper investigates whether histology can improve transcriptomic foundation models by providing cross-modal supervision, but finds limited benefits due to slide-specific structure in gene-expression embeddings.

The paper introduces STMDiT, a diffusion transformer that synthesizes H&E histopathology images from transcriptomic data, improving image quality and transcriptomic fidelity over existing methods.

The paper uses spatial transcriptomic data and a generative model to predict brain vasculature organization from gene co-expression patterns.

This paper introduces a framework that aligns spatial transcriptomics data across multiple samples by integrating transcriptomics correction with deep learning, improving integration performance over existing methods.

DeepSpot2Cell predicts virtual single-cell gene expression from H&E images using spot-level supervision, outperforming previous methods on a new benchmark.

RIPPLET converts somatic DNA variants into gene-impact scores and pathway-perturbation profiles, outperforming multi-omic tools in identifying cancer drivers and predicting drug response without RNA data.

SpotWhisperer links histopathology images to spatial gene expression and text annotations using natural language AI, outperforming existing models on a new benchmark dataset.

DeepSpot predicts spatial transcriptomics from H&E images, improving gene correlations across cancer datasets and generating virtual spatial transcriptomics samples.

The paper uses GANs to edit gene expression data and model pathological processes in spatial transcriptomic datasets.

The paper introduces IST-editing, a GAN-based method to generate high-resolution spatial transcriptomic images of a mouse pup and model morphological transitions.

GILEA uses GAN inversion and latent eigenvalue analysis to profile and edit phenomes from biomedical images, demonstrating its effectiveness with SARS-CoV-2 and skin lesion datasets.

scROSHI identifies cell types without training data by using pre-existing gene sets and hierarchical relationships, outperforming methods in low-data and high-diversity scenarios.

SCIM matches single-cell measurements across technologies by learning a technology-invariant latent space and applying bipartite matching, achieving high accuracy in real-world datasets.