Michael T. Lewis

Cellular stemness identifies high-risk ductal carcinoma in situ and offers a therapeutic interception opportunity

This study identifies stemness features in luminal hormone-responsive cells within DCIS that correlate with invasive progression and shows that targeting FOXA1 reduces tumor growth.

Three-dimensional electron microscopy uncovers mitochondrial network remodeling in residual triple negative breast cancer persisting after conventional chemotherapy treatments.

This study uses 3D electron microscopy to analyze mitochondrial network changes in residual triple negative breast cancer after chemotherapy, revealing structural remodeling and lipid droplet interactions associated with chemoresistance.

Mitochondrial translation is a targetable dependency of chemo-refractory triple negative breast cancer

This study identifies OXA1L-dependent mitochondrial translation as a targetable dependency in chemo-refractory TNBC, showing that inhibiting it enhances chemotherapy sensitivity.

eIF3d and eIF3e mediate selective translational control of hypoxia that can be inhibited by novel small molecules

The paper identifies eIF3d and eIF3e as mediators of hypoxia-induced translational control and shows that small molecules can inhibit this process.

Artificial intelligence-enabled automated analysis of transmission electron micrographs to evaluate chemotherapy impact on mitochondrial morphology in triple negative breast cancer

The paper introduces an AI model to analyze mitochondrial morphology in TNBC using TEM images, finding significant structural changes in response to chemotherapy and metastasis.

A precision oncology-focused deep learning framework for personalized selection of cancer therapy

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.

Patient-Derived Xenograft-Guided Prediction of Chemotherapy Response in Triple-Negative Breast Cancer

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.

A pan-cancer PDX histology image repository with genomic and pathological annotations for deep learning analysis

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.