Jennifer Beane

This study identifies four molecular archetypes of lung adenocarcinoma premalignant lesions using bulk RNA and exome sequencing, linking proliferation-associated features to aggressive tumor outcomes.

FourierMIL uses Fourier filtering and multiple instance learning to analyze whole-slide images, outperforming existing methods in tumor classification.

The paper introduces GPAS to analyze gene co-expression modules in NSCLC, identifying lineage plasticity and aggressiveness patterns across different cancer subtypes.

This study identifies hsa-miR-149-5p as a regulator of immune evasion in progressive bronchial premalignant lesions through integrative analysis of RNA and miRNA sequencing data.

This paper develops a graph attention-based framework that fuses pathology images and gene expression data to predict cancer survival, showing improved performance over existing methods.

The paper establishes a database of lung cancer mouse models to improve data comparison and translational relevance by aligning mouse mutations with human lung cancer mutations.

This paper introduces GRAPE-Net, a graph-based model that stratifies bronchial premalignant lesions using histopathology images, showing improved classification accuracy for lung cancer subtypes.

The paper identifies miRNAs and isomiRs associated with COPD and ILD through integrative network analysis of RNA-seq and SNP data from lung tissue samples.

The paper introduces XTABLE, an open-source tool for analyzing PML transcriptomic data, and uses it to study chromosomal instability as a biomarker for LUSC progression and pathway onset.

The paper introduces a method to analyze differential miRNA regulation across multiple groups, identifying context-specific targets in immune cells and cancer subtypes.

This study uses single-cell RNA sequencing to analyze smoking effects on bronchial epithelial cell types, identifying molecular changes and a novel subpopulation linked to premalignant lesions.