RT Journal Article
T1 Pilot Multi-Omic Analysis of Human Bile from Benign and Malignant Biliary Strictures: A Machine-Learning Approach
A1 Urman, Jesús M.
A1 Herranz, José M.
A1 Uriarte, Iker
A1 Rullán, María
A1 Oyón, Daniel
A1 González, Belén
A1 Fernandez-Urién, Ignacio
A1 Carrascosa, Juan
A1 Bolado, Federico
A1 Zabalza, Lucía
A1 Arechederra, María
A1 Alvarez-Sola, Gloria
A1 Colyn, Leticia
A1 Latasa, María U.
A1 Puchades-Carrasco, Leonor
A1 Pineda-Lucena, Antonio
A1 Iraburu, María J.
A1 Iruarrizaga-Lejarreta, Marta
A1 Alonso, Cristina
A1 Sangro, Bruno
A1 Purroy, Ana
A1 Gil, Isabel
A1 Carmona, Lorena
A1 Cubero Palero, Francisco Javier
A1 Martínez-Chantar, María L.
A1 Banales, Jesús M.
A1 Romero, Marta R.
A1 Macias, Rocio I.R.
A1 Monte, Maria J.
A1 Marín, Jose J. G.
A1 Vila, Juan J.
A1 Corrales, Fernando J.
A1 Berasain, Carmen
A1 Fernández-Barrena, Maite G.
A1 Avila, Matías A.
AB 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 (1H-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.
PB MDPI
SN 2072-6694
YR 2020
FD 2020-06-21
LK https://hdl.handle.net/20.500.14352/8342
UL https://hdl.handle.net/20.500.14352/8342
LA eng
NO Union Europea. Horizonte 2020
NO Ministerio de Economía y Competitividad (MINECO)/FEDER
NO Ministerio de Ciencia e Innovación (MICCIN)
NO Comunidad de Madrid
NO Instituto de Salud Carlos III (ISCIII) / FEDER
NO Centro de Excelencia Severo Ochoa
NO Fundación Científica de la Asociación Española Contra el Cáncer (AECC Scientific Foundation)
NO Gobierno de Navarra Salud
NO Fundación La Caixa
DS Docta Complutense
RD 10 abr 2025