Livnat Jerby‐Arnon

This paper introduces GARM, a machine learning framework for predicting genetic perturbation effects, showing it outperforms existing methods and introduces new evaluation criteria.

This study shows that cancer cell phagocytosis by macrophages induces an anti-inflammatory gene regulatory program, promoting immunosuppression and tumor growth.

This paper introduces DR-GEM, a self-supervised meta-algorithm for single-cell data that improves embeddings and annotations by reducing overfitting and noise.

This study identifies GPCRs that enhance NK and T cell infiltration into breast cancer tumors by sensing metabolites, enabling spatially targeted immunotherapies.

This study maps ovarian cancer spatial organization and identifies immune evasion drivers through single-cell spatial transcriptomics and CRISPR screens.

The paper uses Perturb-CITE-Seq to identify novel immune evasion mechanisms in cancer by analyzing multi-modal single-cell data from patient-derived models.

The paper uses Perturb-seq to assess the phenotypic impact of somatic variants in cancer, revealing a continuum of gain-of-function KRAS variants.

The paper introduces DIALOGUE, a method to identify multicellular programs from single-cell data, revealing functional units that mark diseases like Alzheimer's and ulcerative colitis.

The paper develops a toolbox for scRNA-Seq and snRNA-Seq of fresh and frozen human tumors, testing it across eight tumor types and optimizing protocols for different tissue characteristics.