Alsu M. Missarova

scEPS integrates GWAS and single-cell data to identify disease-associated cell neighborhoods by testing gene expression variance explained in disease contexts.

PaSCient learns patient-level disease representations from scRNA-seq data, enabling disease classification and downstream analyses like dimensionality reduction and patient subgroup discovery.

The paper develops a framework to decode TLS maturation in NSCLC using spatial omics data and deep learning, identifying two distinct spatial ecosystems linked to patient outcomes.

The paper introduces miloDE, a cluster-free method for differential expression testing in single-cell RNA sequencing data, improving sensitivity and specificity by avoiding discrete clustering.

geneBasis selects an optimal gene panel from scRNA-seq data by iteratively adding genes that maximize manifold distance, outperforming existing methods in resolving cell types and states.

This paper uses spatial transcriptomics to study mouse organogenesis, revealing spatial gene expression patterns and cell fate decisions not captured by single-cell RNA sequencing.

The paper investigates cell-to-cell variation in yeast by analyzing the impact of gene deletions on mitochondrial state and its effects on proliferation, drug resistance, and mutation outcomes.