Bryan E. Welm

This paper demonstrates that multiparametric QPI can assess drug sensitivity in patient-derived breast cancer models, including cryopreserved samples, revealing cellular heterogeneity and resistance mechanisms.

This paper introduces ScreenDL, a deep learning model that predicts effective cancer therapies using tumor omic and drug screening data, outperforming existing methods in preclinical trials.

This paper develops chemotherapy-specific predictors for triple-negative breast cancer using patient-derived xenografts and multi-omic data, achieving high AUROC scores for response prediction.

The paper presents a pan-cancer PDX histology image repository with genomic and pathological annotations for deep learning analysis of tumor regions and xenograft-transplant lymphoproliferative disorder prediction.

This study shows ETV4 is essential for estrogen signaling and growth in endometrial cancer cells by enabling ER binding and nuclear translocation.

The paper reparameterizes PAM50 gene expression into tumor dimensions and identifies a breast cancer susceptibility locus at 12q15 through genetic analysis of high-risk pedigrees.

The paper integrates functional assay data with sequence analysis to improve BRCA1 variant classification, adding 146 variants to the Ex-UV database.