Machine learning determines stemness associated with simple and basal-like canine mammary carcinomas

Abstract

Simple and complex carcinomas are the most common type of malignant Canine Mammary Tumors (CMTs), with simple carcinomas exhibiting aggressive behavior and poorer prognostic. Stemness is an ability associated with cancer initiation and progression, malignancy, and therapeutic resistance, but is still few elucidated in different canine mammary cancer subtypes. Here, we first validated, using CMT samples, a previously published canine one-class logistic regression machine learning algorithm (OCLR) to predict stemness (mRNAsi) in canine cancer cells. Then, we observed that simple carcinomas exhibit higher stemness than other histological subtypes and confirmed that stemness is higher and associated with basal-like tumors and with NMF2 tumor-specific metagene signature. Furthermore, using correlation analysis, we suggested two promise stemness-associated targets in CMTs, POLA2 and APEX1, especially in simple canine mammary tumors. Thus, our work elucidates stemness as a potential mechanism behind the aggressiveness and development of simple canine mammary tumors, describing novel pieces of evidence of a promising strategy to target canine mammary carcinomas, especially the simple subtype.