Eliezer M. Van Allen

GENESIS predicts single-cell perturbation responses from experimental conditions, outperforming existing models and approaching experimental reproducibility.

This study identifies conserved neuronal-like and secretory programs in GEP-NETs and links them to spatial microenvironmental niches and metastatic potential.

This study identifies fusion-driven oncogenic programs in translocation renal cell carcinoma (tRCC) that shape an immunosuppressive tumor microenvironment, explaining its reduced immunotherapy response.

This study identifies tumor-myeloid crosstalk as a driver of cisplatin resistance in bladder cancer and proposes PARP14 inhibition as a therapeutic strategy.

This paper shows that Ewing sarcoma cells have reduced POLθ expression and MMEJ activity due to EWS-FLI1 or EWSR1 disruption, making them sensitive to inhibitors of FA, NHEJ, or HR pathways.

This study shows that immunogenic tumor mass dormancy, not cell-level quiescence, persists in residual melanoma lesions after immunotherapy, with active tumor cells and immune interactions.

This study identifies a loss of osteoblastic lineage fidelity in metastatic osteosarcoma through single-nucleus RNA sequencing, linking it to disease progression and potential therapeutic targets.

This study evaluates agentic AI's ability to support biological discovery in autonomous and human-AI copilot settings using multi-omic cancer datasets.

The paper identifies genomic features associated with response or resistance to Gem/Doce in BCG-unresponsive NMIBC using whole-exome sequencing and phylogenetic analysis.

The paper identifies polygenic risk factors and rare variants in unexplained familial cancers using whole genome sequencing and family history data.

UniversalEPI predicts cell type-specific and differential chromatin interactions using DNA sequence and ATAC-seq data, showing robust performance across cell types and conditions.

The paper introduces Cat-VRS, a framework for computable representation of genomic variant categories to improve data interoperability and clinical interpretation.

The paper expands P-NET, a deep learning framework that uses biological pathways for genomic and transcriptomic predictions, showing competitive performance and interpretability.

SpatialFusion identifies spatial niches through pathway activation patterns, revealing pre-malignant and malignant microenvironments in cancer tissues.

The paper evaluates how dataset characteristics affect biologically-informed neural network performance using simulations and empirical testing with prostate cancer data.

The paper identifies an IFN response-high epigenetic program linked to BAP1 deficiency in kidney cancer using single nucleus ATAC sequencing across multiple cohorts.

This study identifies epigenetic dysregulation of metabolic programs in liposarcoma, linking IGF1 loss and PPARG2 deficiency to dedifferentiation and proposing IGF1R-targeted therapy.

The paper compares single-cell RNA profiling technologies using different sample types to assess their performance in tumor specimens.

This study evaluates twelve single-cell foundation models for cancer-related tasks and finds they offer limited clinical outcome prediction advantages over simpler models.

The paper uses DNA lesion segregation to estimate tumor initiating events and shows early cancer drivers have a fitness advantage exceeding 30%.

The paper introduces statistical tools to analyze immune cluster patterns in prostate cancer and finds high-grade tumors show more immune infiltration and active immune features.

The paper analyzes multiomic data from primary and metastatic esophageal adenocarcinoma tumors to identify cell states and their spatial interactions, linking them to clinical outcomes.

The paper identifies immune spatial organization as a biomarker predicting metastasis risk in high-grade prostate cancer using computational pathology and H&E slides.

The paper introduces BEANIE, a nonparametric method to improve differential enrichment analysis in single-cell transcriptomics by accounting for sample-specific biology and robustness of signatures across cohorts.

This study identifies rare germline structural variants as risk factors for pediatric solid tumors, particularly neuroblastoma, by analyzing genome sequencing data from affected children and controls.

The paper identifies epigenomic signatures in sarcomatoid renal cell carcinoma (sRCC) that predict response to immune checkpoint inhibitors and are detectable in plasma, enabling non-invasive diagnosis.

This study analyzes structural variants in melanoma subtypes, identifying distinct genomic properties and molecular drivers that may inform therapeutic strategies.

This study identifies germline rare variants associated with clear and non-clear cell RCC, accounting for population stratification, and finds distinct risk patterns and somatic associations.

This study uses low-pass whole genome sequencing to impute variants and construct polygenic risk scores for breast cancer in an underrepresented Arab population, finding associations with family history and age of presentation.