Karin Hrovatin

Pertpy provides a modular framework for analyzing large-scale perturbation single-cell experiments, offering tools for metadata annotation and perturbation distance calculations.

This paper introduces a multimodal foundation model for predicting protein phenotypes using sequence, structure, and natural language, showing competitive performance and novel insights into disease-related proteins.

This study integrates multi-omics data to identify genetic variants and molecular mechanisms associated with type 2 diabetes and highlights potential drug targets.

GraphCompass provides graph analysis methods to compare cell spatial organization across conditions using spatial omics data.

The paper evaluates distance metrics for single-cell RNA-seq data and recommends mean squared error for comparing populations and evaluating gene expression models.

This paper improves scRNA-seq dataset integration by introducing regularization strategies for cVAEs, enhancing batch correction while preserving biological variation.

This paper integrates multiple scRNA-seq datasets to create a mouse islet atlas, revealing new insights into β-cell states and differences across diabetes models.

The paper introduces expiMap, a deep learning model that enables interpretable reference mapping of single-cell transcriptome data by incorporating biologically meaningful gene programs.

The paper identifies milestone genes and regulons in Dictyostelium development through time-series RNA-sequencing, revealing new gene expression patterns and developmental transitions.