Stefan G. Stark

VIP-OT traces drug response heterogeneity in single cells using vibrational imaging and optimal transport to predict post-treatment metabolic states from pre-treatment spectra.

This paper introduces a method to predict single-cell perturbation responses using neural optimal transport, showing improved performance over existing methods on drug-treated cells.

SECEDO detects subclones in tumors using SNVs from ultra-low coverage single-cell DNA sequencing, achieving high accuracy in synthetic and real datasets.

pmVAE learns interpretable single-cell representations by incorporating pathway structure, improving detection of perturbation-targeted pathways in single-cell RNA-seq data.

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.

The paper identifies hundreds of genes deregulated by SVs in cancer, showing increased expression linked to SV breakpoints and enhancer elements.

This paper introduces a Bayesian nonparametric method to find genetic-clinical associations across cancer types, showing it recovers known associations and outperforms classical methods.

The paper analyzes RNA alterations across 27 cancer types using whole-genome sequencing data, identifying gene expression associations with DNA variants and structural fusions.