Edit

EMBL | Stanford Life Science Alliance

Creating synergies between EMBL and Stanford’s research communities

Deep Learning-Powered Study of 3D Tissue Structures and Molecular Cuesin Breast Cancer Initiation

Background

Ductal carcinoma in situ (DCIS) is a precursor to the most common form of invasive breast cancer (IDC), yet 30% of these lesions never progress. Nevertheless, patients who are diagnosed with DCIS are still generally treated with breast-conserving surgery or mastectomy with radiation. Thus, lack of biomarkers and structural indicators to predict the development of IDC for DCIS patients currently leads to overtreatment and compromises patient well-being. Ductal morphology and tissue microenvironment have been implicated in the invasiveness of IDC, but their roles in the progression of DCIS have not been thoroughly investigated.


Project

How does tissue microenvironment covaries with their the 3D tissue architecture?

We are interested in the general relationship between 3D tissue architecture and its surrounding tissue milieu. To achieve that, our first objective is to conduct a comprehensive analysis of the structural and molecular characteristics of DCIS progression. We will use the state-of-the-art 3D and 2D imaging technologies (in the Nolan Group at Stanford), and the power of machine learning (in the Krushuk group at EMBL) to overcome prior technical limitations, to create and analyze an extensive atlas that enables the identification of novel predictive biomarkers and critical cellular drivers responsible for DCIS invasion. Beyond this project, the resulting technical and computational pipelines hold great promise for investigating other cancer.

This project is supported by an Exchange Grant, awarded to Yuqi Tan. 

References:

Wolny, A., Cerrone, L., Vijayan, A., Tofanelli, R., Barro, A.V., Louveaux, M., Wenzl, C., Strauss, S., Wilson-Sánchez, D., Lymbouridou, R., et al. (2020). Accurate and versatile 3D segmentation of plant tissues at cellular resolution. eLife 9. 10.7554/eLife.57613.

Goltsev, Y., Samusik, N., Kennedy-Darling, J., Bhate, S., Hale, M., Vazquez, G., Black, S., and Nolan, G.P. (2018). Deep Profiling of Mouse Splenic Architecture with CODEX Multiplexed Imaging. Cell 174, 968-981.e15. 10.1016/j.cell.2018.07.010.

Messal, H.A., Alt, S., Ferreira, R.M.M., Gribben, C., Wang, V.M.-Y., Cotoi, C.G., Salbreux, G., and Behrens, A. (2019). Tissue curvature and apicobasal mechanical tension imbalance instruct cancer morphogenesis. Nature 566, 126–130. 10.1038/s41586-019-0891-2.


Find out more:

Interested in finding out more about working at the interface of metabolism and organelle biology? Get in touch, we would love to hear from you!

Collaborators:


Edit