Detalle Publicación

Pilot multi-omic analysis of human bile from benign and malignant biliary strictures: a machine-learning approach

Autores: Urman, J. M. ; Herranz, J. M. ; Uriarte Díaz-Varela, Iker; Rullan, M. ; Oyon, D. ; Gonzalez, B. ; Fernández-Urien Sáinz, Ignacio; Carrascosa Gil, Juan; Bolado, F. ; Zabalza, L. ; Arechederra Calderon, Maria; Alvarez-Sola, G. ; Colyn, L. ; Latasa Sada, María Ujué; Puchades-Carrasco, L. ; Pineda Lucena, Antonio; Iraburu Elizalde, María; Iruarrizaga-Lejarreta, M. ; Alonso, C. ; Sangro Gómez-Acebo, Bruno Carlos; Purroy López, Ana Isabel; Gil, I. ; Carmona, L. ; Cubero, F. J. ; Martinez-Chantar, M. L. ; Banales, J. M. ; Romero, M. R. ; Macias, R. I. R. ; Monte, M. J. ; Marin, J. J. G. ; Vila, J. J. ; Corrales, F. J. ; Berasain Lasarte, María del Carmen; García Fernández de Barrena, Maite; Ávila Zaragoza, Matías Antonio (Autor de correspondencia)
Título de la revista: CANCERS
ISSN: 2072-6694
Volumen: 12
Número: 6
Páginas: 1644
Fecha de publicación: 2020
Cholangiocarcinoma (CCA) and pancreatic adenocarcinoma (PDAC) may lead to the development of extrahepatic obstructive cholestasis. However, biliary stenoses can also be caused by benign conditions, and the identification of their etiology still remains a clinical challenge. We performed metabolomic and proteomic analyses of bile from patients with benign (n= 36) and malignant conditions, CCA (n= 36) or PDAC (n= 57), undergoing endoscopic retrograde cholangiopancreatography with the aim of characterizing bile composition in biliopancreatic disease and identifying biomarkers for the differential diagnosis of biliary strictures. Comprehensive analyses of lipids, bile acids and small molecules were carried out using mass spectrometry (MS) and nuclear magnetic resonance spectroscopy (H-1-NMR) in all patients. MS analysis of bile proteome was performed in five patients per group. We implemented artificial intelligence tools for the selection of biomarkers and algorithms with predictive capacity. Our machine-learning pipeline included the generation of synthetic data with properties of real data, the selection of potential biomarkers (metabolites or proteins) and their analysis with neural networks (NN). Selected biomarkers were then validated with real data. We identified panels of lipids (n= 10) and proteins (n= 5) that when analyzed with NN algorithms discriminated between patients with and without cancer with an unprecedented accuracy.