sorry, we can't preview this file

...but you can still download Models.zip
Models.zip (7.51 GB)

Deep Learning Models used in "Intratumoral resolution of driver gene mutation heterogeneity in renal cancer using deep learning"

Download (7.51 GB)
software
posted on 07.06.2022, 05:39 authored by Satwik RajaramSatwik Rajaram, Paul Acosta, Vandana Panwar, Vipul Jarmale, Alana Christie, Jay Jasti, Vitaly Margulis, Dinesh Rakheja, John Cheville, Bradley C Leibovich, Alexander Parker, James Brugarolas, Payal Kapur

This is a zip file containing all the deep learning models used in the paper "Intratumoral resolution of driver gene mutation heterogeneity in renal cancer using deep learning" by Acosta et al in Cancer Research (https://doi.org/10.1158/0008-5472.CAN-21-2318). This work demonstrates that deep learning (DL) models can predict the intratumor heterogeneity in driver mutation status purely from Hematoxylin and Eosin (H&E) stained slides.


Specifically,  we trained and validated DL models that predict the status of three of the most frequently mutated driver genes (BAP1, PBRM1, and SETD2) in clear cell renal cell carcinoma.

The zip file includes models for gene status prediction as well as other DL models used in the publication. These are organized into the following folders:

1. FCN: For the region level gene models

2. MIL: For the slide level gene models

3. Nuclear: For the nuclear segmentation model

4. Tumor: For the tumor region identification model

See related materials in collection at: https://doi.org/10.25452/figshare.plus.c.5983795

Funding

NON-INVASIVE PHYSIOLOGIC PREDICTORS OF AGGRESSIVENESS IN RENAL CELL CARCINOMA

National Cancer Institute

Find out more...

Dissecting the interplay between BAP1 and PBRM1 in renal cancer

Cancer Prevention and Research Institute of Texas

Find out more...

Glomerular Filtration of Sub-nm Gold Nanoparticles

National Institute of Diabetes and Digestive and Kidney Diseases

Find out more...

The University of Texas Southwestern Medical Center SPORE in Kidney Cancer

National Cancer Institute

Find out more...

Understanding TFE3-mediated Tumorigenesis through Analysis of a Novel, Clinically-Relevant Mouse Model of Translocation Renal Cell Carcinoma

Cancer Prevention and Research Institute of Texas

Find out more...

Vascular image-guided optimization of response (VIGOR) to therapy in kidney cancer

National Cancer Institute

Find out more...

Advance CT And Fluorescence Imaging Of Kidney Cancers With Glutathione-mediated Contrast Enhancements

Cancer Prevention and Research Institute of Texas

Find out more...

NIH (P50 CA196516) CPRIT (RP180192) CPRIT (RP180191) NIH (R01CA244579 , R01CA154475 , and R01DK115986) DOD ( W81XWH1910710 ) CPRIT ( RP200233 ). Lyda Hill Department of Bioinformatics

History

Research Institution(s)

University of Texas Southwestern, Mayo Clinic

I confirm there is no human personally identifiable information in the files or description shared

Yes

I confirm the files and description shared may be publicly distributed under the license selected

Yes