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

Cancers

Marta Iruarrizaga-Lejarreta¹  MaríaJ. Iraburu²  Federico Bolado³  Juan Carrascosa³  Belén González³  Lucía Zabalza³  Daniel Oyón³  Ignacio Fernandez-Urién³  FernandoJ. Corrales³  María Rullán³  JesúsM. Urman³  MaríaL. Martínez-Chantar⁴  Leonor Puchades-Carrasco⁵  Antonio Pineda-Lucena⁵  Isabel Gil⁶  María Arechederra⁶  MaiteG. Fernández-Barrena⁶  Ana Purroy⁶  MatíasA. Avila⁶  Lorena Carmona⁶  Gloria Alvarez-Sola⁷  MartaR. Romero⁷  Iker Uriarte⁷  JesúsM. Banales⁷  Carmen Berasain⁷  JoséM. Herranz⁷  MariaJ. Monte⁷  JuanJ. Vila⁷  RocioI.R. Macias⁷  JoseJ. G. Marín⁷  Cristina Alonso⁸  Bruno Sangro⁸  Leticia Colyn⁹  MaríaU. Latasa⁹  FranciscoJavier Cubero^1,10 

[1]University of Navarra, 31008 Pamplona, Spain

[2]Department of Biochemistry and Genetics, School of Sciences

[3]Department of Gastroenterology and Hepatology, Navarra University Hospital Complex, 31008 Pamplona, Spain

[4]Department of Immunology, Ophtalmology & Ear, Nose and Throat (ENT), Complutense University School of Medicine and 12 de Octubre Health Research Institute (Imas12), 28040 Madrid, Spain

[5]Drug Discovery Unit, Instituto de Investigación Sanitaria La Fe, Hospital Universitario y Politécnico La Fe, 46026 Valencia, Spain

[6]IdiSNA, Navarra Institute for Health Research, 31008 Pamplona, Spain

[7]National Institute for the Study of Liver and Gastrointestinal Diseases, CIBERehd, Carlos III Health Institute, 28029 Madrid, Spain

[8]OWL Metabolomics, Bizkaia Technology Park, 48160 Derio, Spain

[9]Program of Hepatology, Center for Applied Medical Research (CIMA), University of Navarra, 31008 Pamplona, Spain

[10]Proteomics Unit, Centro Nacional de Biotecnología (CNB) Consejo Superior de Investigaciones Científicas (CSIC), 28049 Madrid, Spain

关键词: human bile;    cholangiocarcinoma;    pancreatic adenocarcinoma;    lipidomics;    proteomics;    machine-learning;   

DOI  :  10.3390/cancers12061644

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown