E. M. Van Allen

Genomic heterogeneity and ploidy identify patients with intrinsic resistance to PD-1 blockade in metastatic melanoma

This study identifies genomic heterogeneity and ploidy as markers of intrinsic resistance to PD-1 blockade in metastatic melanoma, with a decision tree model predicting resistance with high confidence.

Spatially aware deep learning reveals tumor heterogeneity patterns that encode distinct kidney cancer states

The paper uses spatially aware deep learning to identify tumor heterogeneity patterns in kidney cancer, revealing distinct states associated with different histological subtypes.

Intertumoral lineage diversity and immunosuppressive transcriptional programs in well-differentiated gastroenteropancreatic neuroendocrine tumors

This study analyzes single-cell transcriptomes of gastroenteropancreatic neuroendocrine tumors to identify lineage diversity and immunosuppressive programs in tumor and immune cells.

Building tools for machine learning and artificial intelligence in cancer research: best practices and a case study with the PathML toolkit for computational pathology

The paper introduces PathML, a computational pathology toolkit designed for scalability, standardization, and ease of use in cancer research, with applications demonstrated across diverse use-cases.

Examining Batch Effect in Histopathology as a Distributionally Robust Optimization Problem

This paper shows that using abstention in a patch-based classifier improves performance in histopathology tasks while reducing reliance on spurious features.

A patient-driven clinicogenomic partnership through the Metastatic Prostate Cancer Project

The paper describes a patient-driven initiative that collects clinicogenomic data from metastatic prostate cancer patients, revealing consistent patient-reported data and genomic insights from cfDNA samples.

Integrative Clinical and Molecular Characterization of Translocation Renal Cell Carcinoma

This study characterizes translocation renal cell carcinoma (tRCC) through integrated clinical and molecular analysis of 152 patients, identifying key features like MiT/TFE fusions, NRF2-driven antioxidant response, and differential treatment outcomes.

9p21 Loss Defines the Evolutionary Patterns of Aggressive Renal Cell Carcinomas

This study establishes a mouse model of renal cell carcinoma showing that 9p21 loss drives aggressive tumor evolution with chromosomal instability and metastasis.

Clinical interpretation of integrative molecular profiles to guide precision cancer medicine

This paper introduces MOAlmanac, a clinical interpretation algorithm that integrates genomic and transcriptional data to improve precision cancer treatment decisions by considering second-order molecular features.