Rebecca C. Poulos

OnCorr analyzes mRNA-protein correlations across pan-cancer datasets to improve precision oncology by providing a web tool for integrating transcriptomics data with protein information.

ProCanFDL uses federated deep learning to subtype cancers using proteomic data while preserving privacy, achieving performance gains over local models.

This study shows that combining EYA and PLK1 inhibitors is effective in treating neurological cancers by inducing cell death and targeting cancer stem cells.

This paper introduces DeePathNet, a Transformer-based model that integrates cancer pathways with multi-omic data to improve drug response prediction and cancer classification.

The paper presents a pan-cancer proteomic map of 949 cell lines, revealing protein-specific biomarkers of cancer vulnerabilities and showing proteomic data's superior predictive power for drug response.

The paper analyzes POLE exonuclease domain mutants in colorectal cancer, identifying mutation spectra differences and a specific TP53 mutation enrichment.

The paper identifies mutation-methylation associations in cancer genomes, linking CpG methylation to mutation patterns and driver formation across cancer types.