TOWARDS A BRAND NEW WAY TU UNDERSTAND KIDNEY CANCER: AN UNSUPERVISED MACHINE LEARNING APPROACH

ROMEO L; NUÑEZ M; FERRANDO M; LÓPEZ FONTANA C; CARÓN RW; BRUNA FA; PISTONE CREYDT V

Congreso; Reunión Anual de Sociedades de Biociencias.; 2022

Among the different types of cells that surround renal epithelial cells, renal adipose tissue (AT) is one of the most abundant. We demonstrated that human renal adipose tissue from patients with renal tumors (hRAT) regulates the behavior of epithelial cells differently from normal renal adipose tissue (hRAN), through the proteins expression characterization in hRAT vs hRAN. In this work, we evaluated: 1) the differential proteins expression as a whole was sufficient to separate healthy patients from patients with kidney cancer, using unsupervised machine learning algorithms (UMLA); 2) the correlation between adiponectin and leptin expression with clinical characteristics of kidney cancer patients.The biological variables evaluated in Hrat (n=21) and hRAN (n=24) were: adiponectin, AdipoR, leptin, ObR, perilipin and ADAMTS1. The proteins expression by the different ATs were analyzed with UMLA algorithms (t-SNE and UMAP). We selected leptin and adiponectin to study the correlation with clinical characteristics of patients with kidney tumors (sex, age, BMI, smoking, tumor grade, size of the lesion, density of AT, and difficulty in the surgical dissection). The SPSS program was used to statystical analysis, taking a significant p < 0.05.Considering the total of biological variables evaluated in the different AT fragments, we were able to separate healthy from kidney tumor patients by UMLA projection. A decrease in adiponectin expression was found in patients with a more undifferentiated tumor related with smoking habits (p