Pilot Multi-Omic Analysis of Human Bile from Benign and Malignant Biliary Strictures: A Machine-Learning Approach

Impacto

Downloads

Downloads per month over past year

Urman, Jesús M. and Herranz, José M. and Uriarte, Iker and Rullán, María and Oyón, Daniel and González, Belén and Fernandez-Urién, Ignacio and Carrascosa, Juan and Bolado, Federico and Zabalza, Lucía and Arechederra, María and Alvarez-Sola, Gloria and Colyn, Leticia and Latasa, María U. and Puchades-Carrasco, Leonor and Pineda-Lucena, Antonio and Iraburu, María J. and Iruarrizaga-Lejarreta, Marta and Alonso, Cristina and Sangro, Bruno and Purroy, Ana and Gil, Isabel and Carmona, Lorena and Cubero Palero, Francisco Javier and Martínez-Chantar, María L. and Banales, Jesús M. and Romero, Marta R. and Macias, Rocio I.R. and Monte, Maria J. and Marín, Jose J. G. and Vila, Juan J. and Corrales, Fernando J. and Berasain, Carmen and Fernández-Barrena, Maite G. and Avila, Matías A. (2020) Pilot Multi-Omic Analysis of Human Bile from Benign and Malignant Biliary Strictures: A Machine-Learning Approach. Cancers, 12 (6). p. 1644. ISSN 2072-6694

[thumbnail of cancers-12-01644-v3.pdf]
Preview
PDF
Creative Commons Attribution.

3MB

Official URL: https://doi.org/10.3390/cancers12061644




Abstract

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.


Item Type:Article
Uncontrolled Keywords:Human bile; cholangiocarcinoma; pancreatic adenocarcinoma; lipidomics; proteomics; machine-learning
Subjects:Medical sciences > Medicine > Gastroenterology and Hepatology
Medical sciences > Medicine > Oncology
ID Code:67496
Deposited On:25 Aug 2021 07:28
Last Modified:06 Sep 2021 09:22

Origin of downloads

Repository Staff Only: item control page