Xavier Tekpli

This study identifies the loss of chromosome 13q14.2 as a key driver of breast cancer pathogenesis and drug response, showing its impact on tumor survival, cell cycle, and treatment susceptibility.

This study identifies common dysregulated transcriptional networks across cancers linked to loss of enhancer methylation through pan-cancer emQTL analysis.

The paper uses scRNA-seq and explainable machine learning to analyze how tumor microenvironment cell types affect neoadjuvant chemotherapy outcomes in breast cancer.

The paper develops a computational tool to predict drug combinations for TNBC by integrating transcriptional signatures with drug response data.

The paper introduces the HTA index to assess heterogeneity in spatial data, demonstrating its application in spatial transcriptomics, imaging, and GIS.

The paper develops deep learning methods to infer spatial gene expression from pathology whole-slide images and links tumor heterogeneity to survival in breast and lung cancer.

The paper introduces a deep learning model with attention mechanisms to predict DNA methylation from gene expression and sequence data, achieving high correlation and identifying potential methylation-related genes.