A. Kamoun

Deep Learning Allows Assessment of Risk of Metastatic Relapse from Invasive Breast Cancer Histological Slides

This paper develops a deep learning model to assess metastatic relapse risk in ER+/HER2-negative breast cancer patients using histological slides, showing improved prognostic performance over clinical factors.

Integrated molecular and pharmacological characterization of patient-derived xenografts from bladder and ureteral cancers identifies new potential therapies.

The paper develops patient-derived xenografts (PDXs) for bladder and ureteral cancers, identifies molecular subtypes, and shows that combined FGFR/EGFR inhibition is more effective than single-agent therapy for FGFR3-mutant tumors.

PACpAInt: a deep learning approach to identify molecular subtypes of pancreatic adenocarcinoma on histology slides

PACpAInt uses deep learning to identify molecular subtypes of pancreatic adenocarcinoma on histology slides, revealing prognostic heterogeneity and novel subtypes.

FGFR3 activating mutations induce luminal-like papillary bladder tumor formation and favor a male gender bias.

This study shows FGFR3-S249C mutations drive luminal-like papillary bladder tumors in mice and correlate with male gender bias and AR activity in human tumors.

PPARG is a tumor suppressor in basal bladder tumors offering new potential therapeutic opportunities.

The paper identifies PPARγ as a tumor suppressor in basal bladder tumors and suggests therapeutic opportunities through PPARγ activation.

A consensus molecular classification of muscle-invasive bladder cancer

The paper identifies six consensus molecular classes of muscle-invasive bladder cancer using transcriptomic data and classification systems, providing a framework for future biomarker validation.