Robert L. Grossman

The paper introduces QAG, a method to improve LLM accuracy for somatic variant frequencies by integrating with the Genomic Data Commons.

ATAT automates spatial transcriptomics analysis by aligning and traversing tissue samples using self-supervised learning, improving gene expression modeling without manual annotation.

The paper introduces a self-describing format for bulk biomedical data called PFB, showing performance improvements over JSON and SQL for data import/export.

The paper describes AnVIL, a cloud-based platform that enables genomic data analysis without data transfer, improving security, scalability, and collaboration.

This paper shows that digital histopathology batch effects in TCGA data affect DL model accuracy and bias, and proposes a method to address this issue.

The paper describes the pipelines and workflows used to process and harmonize genomic data in the NCI Genomic Data Commons, including data types like somatic mutations and gene expression.

HeartBioPortal2.0 provides a cloud-based platform for analyzing genetic and quantitative traits related to cardiovascular disease across diverse populations.

The paper identifies cancer-specific eQTLs by modeling genotype-tumor purity interactions in heterogeneous tumor gene expression data, showing most risk variants affect tumor microenvironment cells.

The paper describes the PCAWG project's large-scale analysis of cancer whole genomes across multiple computing environments, producing validated consensus variants for downstream research.