Title: From Mouse to Human: Cellular Morphometric Subtype Learned From Mouse Mammary Tumors Provides Prognostic Value in Human Breast Cancer

Journal Article · · Frontiers in Oncology
 [1];  [2];  [3];  [1];  [4];  [1];  [3];  [3];  [5];  [5];  [5];  [5];  [3];  [1]
  1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States); Nanjing Medical University (China)
  3. Univ. of California, San Francisco, CA (United States)
  4. Univ. of California, Davis, CA (United States)
  5. Universidad de Salamanca (Spain); Consejo Superior de Investigaciones Cientificas (CSIC), Salamanca (Spain)

Mouse models of cancer provide a powerful tool for investigating all aspects of cancer biology. In this study, we used our recently developed machine learning approach to identify the cellular morphometric biomarkers (CMB) from digital images of hematoxylin and eosin (H&E) micrographs of orthotopic Trp53-null mammary tumors (n = 154) and to discover the corresponding cellular morphometric subtypes (CMS). Of the two CMS identified, CMS-2 was significantly associated with shorter survival (p = 0.0084). We then evaluated the learned CMB and corresponding CMS model in MMTV-Erbb2 transgenic mouse mammary tumors (n = 53) in which CMS-2 was significantly correlated with the presence of metastasis (p = 0.004). We next evaluated the mouse CMB and CMS model on The Cancer Genome Atlas breast cancer (TCGA-BRCA) cohort (n = 1017). Kaplan–Meier analysis showed significantly shorter overall survival (OS) of CMS-2 patients compared to CMS-1 patients (p = 0.024) and added significant prognostic value in multi-variable analysis of clinical and molecular factors, namely, age, pathological stage, and PAM50 molecular subtype. Thus, application of CMS to digital images of routine workflow H&E preparations can provide unbiased biological stratification to inform patient care.

Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
National Cancer Institute (NCI); National Institutes of Health (NIH); USDOD
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
1891477
Journal Information:
Frontiers in Oncology, Journal Name: Frontiers in Oncology Vol. 11; ISSN 2234-943X
Publisher:
Frontiers Research FoundationCopyright Statement
Country of Publication:
United States
Language:
English

References (24)

Stacked Predictive Sparse Decomposition for Classification of Histology Sections journal December 2014
Genetic Profiling of Breast Cancer with and Without Preexisting Metabolic Disease journal February 2020
Molecular portraits of human breast tumours journal August 2000
The immune contexture in human tumours: impact on clinical outcome journal March 2012
Integrated analyses of murine breast cancer models reveal critical parallels with human disease journal July 2019
A mammary-specific model demonstrates the role of the p53 tumor suppressor gene in tumor development journal February 2000
Identification of genetic loci that control mammary tumor susceptibility through the host microenvironment journal March 2015
Atezolizumab and Nab-Paclitaxel in Advanced Triple-Negative Breast Cancer journal November 2018
Comparative oncogenomics identifies breast tumors enriched in functional tumor-initiating cells journal June 2011
Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implications journal September 2001
clusterProfiler: an R Package for Comparing Biological Themes Among Gene Clusters journal May 2012
Biological and genetic properties of the p53 null preneoplastic mammary epithelium journal April 2002
Maftools: efficient and comprehensive analysis of somatic variants in cancer journal October 2018
Image-based consensus molecular subtype (imCMS) classification of colorectal cancer using deep learning journal July 2020
Distinct Luminal-Type Mammary Carcinomas Arise from Orthotopic Trp53-Null Mammary Transplantation of Juvenile versus Adult Mice journal November 2014
Comprehensive Benchmarking and Integration of Tumor Microenvironment Cell Estimation Methods journal December 2019
Murine Microenvironment Metaprofiles Associate with Human Cancer Etiology and Intrinsic Subtypes journal January 2013
The Where, the When, and the How of Immune Monitoring for Cancer Immunotherapies in the Era of Checkpoint Inhibition journal April 2016
Abstract S1-03: Pooled individual patient data analysis of stromal tumor infiltrating lymphocytes in primary triple negative breast cancer treated with anthracycline-based chemotherapy journal February 2016
A genomic analysis of mouse models of breast cancer reveals molecular features ofmouse models and relationships to human breast cancer journal June 2014
Identification of conserved gene expression features between murine mammary carcinoma models and human breast tumors journal January 2007
Unraveling heterogeneous susceptibility and the evolution of breast cancer using a systems biology approach journal February 2015
MuSE: accounting for tumor heterogeneity using a sample-specific error model improves sensitivity and specificity in mutation calling from sequencing data journal August 2016
Tumor immune microenvironment characterization in clear cell renal cell carcinoma identifies prognostic and immunotherapeutically relevant messenger RNA signatures journal November 2016