Jonas Maaskola

TERRA is a foundation model for spatial transcriptomics that predicts tissue behavior under perturbation and identifies multi-scale biological insights across tissues.

CytoVI is a deep generative model for antibody-based single cell technologies that improves integration, imputation, and analysis across different platforms and antibody panels.

MintFlow is a generative AI algorithm that predicts how tissue perturbations reprogram cell states in disease, revealing novel cell populations and therapeutic targets in three human conditions.

This paper introduces a method to combine histology and spatial gene expression data to infer high-resolution transcriptome maps without sequencing or hybridization.

The paper uses spatial transcriptomics to analyze copy number variations in benign and malignant tissues, revealing clonal patterns and suggesting early cancer evolution mechanisms.

The paper introduces a probabilistic framework to analyze spatial transcriptomics data, identifying transcriptomic patterns corresponding to cell types and tissue components in mouse brain samples.