Eytan Ruppin

The paper identifies transient isoform remodeling as a key mechanism in early MAPKi resistance in melanoma, showing it is distinct from gene expression changes and linked to splicing regulators and developmental pathways.

Qombucha infers unobserved progenitor methylation profiles in GBM, revealing subtype-specific developmental programs and improved subtype classification.

The paper identifies CLDN3 as a tumor-selective target in SCLC using proteogenomic analysis and validates its therapeutic potential with a monoclonal antibody.

This study identifies hepatobiliary progenitor-like reprogramming in liver metastases, driven by TGF-β and hypoxia, and shows its association with poor survival.

This study defines the spatial architecture of intrahepatic cholangiocarcinoma using single-cell spatial proteomics and a graph-based deep learning framework to identify multicellular spatial patterns and their association with patient outcomes.

This paper develops HEiST, a deep learning method to infer spatial transcriptomes from H&E slides, identifies two prognostic Spatiotypes in HNSC, and shows they predict treatment response better than existing biomarkers.

Path2Space predicts spatial gene expression and tumor microenvironment from histopathology slides, identifying new breast cancer subgroups and improving biomarker prediction.

This study identifies TAZ deficiency as synthetically lethal with BRAF inhibitors in anaplastic thyroid cancer, revealing a mechanism of resistance and a potential therapeutic target.

SLIDE-EX predicts cell type-specific gene expression from breast cancer histopathology images, outperforming bulk RNA-seq deconvolution and slide-based models in chemotherapy response prediction.

Path2Omics predicts gene expression and methylation from histopathology slides across 23 cancer types, outperforming previous models and showing effectiveness in predicting patient outcomes.

This paper develops DECODEM to predict chemotherapy response by integrating deconvolved expression patterns of immune, stromal, and tumor cells in breast cancer, finding that cell-type-specific expression is predictive of response.

This paper develops a machine learning framework, EXPRESSO, to predict treatment response from tumor transcriptomics across multiple cancer types and therapies, showing improved performance over existing methods.

This study develops a bispecific antibody targeting MERTK and EGFR to overcome drug resistance in lung cancer with mutations in exons 19, 20, and 21.

The paper introduces PathStAR, a framework to quantify structural aging from histopathology images, revealing tissue-specific aging trajectories and coordinated deterioration across organs.

This paper introduces EXPAND, an interpretable AI model that predicts breast cancer subtypes and survival using nuclear features, achieving performance comparable to black-box models.

This paper introduces TIME_ACT, a transcriptomic signature predicting immune checkpoint blockade response across cancers, validated using histopathology and multiple cohorts.

The paper identifies synthetic dosage lethality targets for PLK1-overexpressing cancers using genome-wide screens and validates key hits to show their therapeutic potential.

This paper introduces LogiCAR designer, a computational method using single-cell transcriptomics to identify logic-gated antigen combinations for CAR therapy, showing improved efficacy and safety compared to existing approaches.

The paper shows that inducing epithelial traits in breast cancer cells increases autophagy and DNA damage, potentially contributing to tumor dormancy and reactivation.

This study shows that TMPRSS2-ERG fusion promotes resistance to antiandrogens by interacting with GR, suggesting combined GR and AR inhibition could benefit tERG-positive prostate cancer patients.

This study identifies M19-6 as a small molecule that disrupts the eIF4F complex, reducing melanoma growth and metastasis while sparing melanocytes.

ecPath detects ecDNA in tumors using H&E images, achieving good performance in predicting ecDNA status and identifying poor prognoses in low grade glioma patients.

IMMClock predicts immune age of T cells and NK cells using gene expression, showing immune aging is more linked to cellular aging than differentiation and is accelerated in diseases.

The paper identifies resistance-deactivated interactions (RDIs) as predictive biomarkers for ICB response in melanoma by analyzing transcriptomics data from multiple cohorts.

The paper infers tumor immune status and predicts immunotherapy response from blood scRNA-Seq data in HNSCC patients.

This study maps the SCLC tumor microenvironment and identifies cancer-associated fibroblasts as key drivers of neuroendocrine state plasticity and poor prognosis.

This paper introduces Sgootr, a method to infer tumor lineage trees from single-cell methylation data, revealing metastatic progression models and identifying lineage-informative CpG sites.

This study identifies a decoupling signature that reduces the correlation between cytotoxic and exhausted T cell activities, improving the prediction of immunotherapy response in melanoma.

ENLIGHT predicts patient response to targeted and immunotherapies using tumor transcriptomes without prior treatment response data, showing better accuracy than existing transcriptomics-based signatures.

CAMMiQ improves microbial strain-level detection and quantification in single-cell metagenomics by using combinatorial optimization and doubly-unique substrings, outperforming existing methods in accuracy.