A Novel Epigenetic Machine Learning Model to Define Risk of Progression for Hepatocellular Carcinoma Patients

被引:10
作者
Bedon, Luca [1 ,2 ]
Dal Bo, Michele [1 ]
Mossenta, Monica [1 ,3 ]
Busato, Davide [1 ,3 ]
Toffoli, Giuseppe [1 ]
Polano, Maurizio [1 ]
机构
[1] IRCCS, Ctr Riferimento Oncol Aviano CRO, Expt & Clin Pharmacol Unit, I-33081 Aviano, PN, Italy
[2] Univ Trieste, Dept Chem & Pharmaceut Sci, Via L Giorgieri 1, I-34127 Trieste, Italy
[3] Univ Trieste, Dept Life Sci, I-34127 Trieste, Italy
关键词
hepatocellular carcinoma; epigenetic; prediction model; tumor microenvironment; hepatocellular carcinoma DNA methylation; COLORECTAL-CANCER; DNA METHYLATION; DIAGNOSIS; DISPOSITION; PROGNOSIS; BIOMARKER; PROTEINS; FEATURES; PACKAGE; IMPACT;
D O I
10.3390/ijms22031075
中图分类号
Q5 [生物化学]; Q7 [分子生物学];
学科分类号
071010 ; 081704 ;
摘要
Although extensive advancements have been made in treatment against hepatocellular carcinoma (HCC), the prognosis of HCC patients remains unsatisfied. It is now clearly established that extensive epigenetic changes act as a driver in human tumors. This study exploits HCC epigenetic deregulation to define a novel prognostic model for monitoring the progression of HCC. We analyzed the genome-wide DNA methylation profile of 374 primary tumor specimens using the Illumina 450 K array data from The Cancer Genome Atlas. We initially used a novel combination of Machine Learning algorithms (Recursive Features Selection, Boruta) to capture early tumor progression features. The subsets of probes obtained were used to train and validate Random Forest models to predict a Progression Free Survival greater or less than 6 months. The model based on 34 epigenetic probes showed the best performance, scoring 0.80 accuracy and 0.51 Matthews Correlation Coefficient on testset. Then, we generated and validated a progression signature based on 4 methylation probes capable of stratifying HCC patients at high and low risk of progression. Survival analysis showed that high risk patients are characterized by a poorer progression free survival compared to low risk patients. Moreover, decision curve analysis confirmed the strength of this predictive tool over conventional clinical parameters. Functional enrichment analysis highlighted that high risk patients differentiated themselves by the upregulation of proliferative pathways. Ultimately, we propose the oncogenic MCM2 gene as a methylation-driven gene of which the representative epigenetic markers could serve both as predictive and prognostic markers. Briefly, our work provides several potential HCC progression epigenetic biomarkers as well as a new signature that may enhance patients surveillance and advances in personalized treatment.
引用
收藏
页码:1 / 25
页数:25
相关论文
共 94 条
[1]   User's guide to correlation coefficients [J].
Akoglu, Haldun .
TURKISH JOURNAL OF EMERGENCY MEDICINE, 2018, 18 (03) :91-93
[2]   Epigenetic events involved in organic cation transporter 1-dependent impaired response of hepatocellular carcinoma to sorafenib [J].
Al-Abdulla, Ruba ;
Lozano, Elisa ;
Macias, Rocio I. R. ;
Monte, Maria J. ;
Briz, Oscar ;
O'Rourke, Colm J. ;
Serrano, Maria A. ;
Banales, Jesus M. ;
Avila, Matias A. ;
Martinez-Chantar, Maria L. ;
Geier, Andreas ;
Andersen, Jesper B. ;
Marin, Jose J. G. .
BRITISH JOURNAL OF PHARMACOLOGY, 2019, 176 (06) :787-800
[3]   Comprehensive and Integrative Genomic Characterization of Hepatocellular Carcinoma [J].
Ally, Adrian ;
Balasundaram, Miruna ;
Carlsen, Rebecca ;
Chuah, Eric ;
Clarke, Amanda ;
Dhalla, Noreen ;
Holt, Robert A. ;
Jones, Steven J. M. ;
Lee, Darlene ;
Ma, Yussanne ;
Marra, Marco A. ;
Mayo, Michael ;
Moore, Richard A. ;
Mungall, Andrew J. ;
Schein, Jacqueline E. ;
Sipahimalani, Payal ;
Tam, Angela ;
Thiessen, Nina ;
Cheung, Dorothy ;
Wong, Tina ;
Brooks, Denise ;
Robertson, A. Gordon ;
Bowlby, Reanne ;
Mungall, Karen ;
Sadeghi, Sara ;
Xi, Liu ;
Covington, Kyle ;
Shinbrot, Eve ;
Wheeler, David A. ;
Gibbs, Richard A. ;
Donehower, Lawrence A. ;
Wang, Linghua ;
Bowen, Jay ;
Gastier-Foster, Julie M. ;
Gerken, Mark ;
Helsel, Carmen ;
Leraas, Kristen M. ;
Lichtenberg, Tara M. ;
Ramirez, Nilsa C. ;
Wise, Lisa ;
Zmuda, Erik ;
Gabriel, Stacey B. ;
Meyerson, Matthew ;
Cibulskis, Carrie ;
Murray, Bradley A. ;
Shih, Juliann ;
Beroukhim, Rameen ;
Cherniack, Andrew D. ;
Schumacher, Steven E. ;
Saksena, Gordon .
CELL, 2017, 169 (07) :1327-+
[4]   Permutation importance: a corrected feature importance measure [J].
Altmann, Andre ;
Tolosi, Laura ;
Sander, Oliver ;
Lengauer, Thomas .
BIOINFORMATICS, 2010, 26 (10) :1340-1347
[5]   The prognostic correlation of AFP level at diagnosis with pathological grade, progression, and survival of patients with hepatocellular carcinoma [J].
Bai, Dou-Sheng ;
Zhang, Chi ;
Chen, Ping ;
Jin, Sheng-Jie ;
Jiang, Guo-Qing .
SCIENTIFIC REPORTS, 2017, 7
[6]   B regulatory cells in cancer [J].
Balkwill, Frances ;
Montfort, Anne ;
Capasso, Melanie .
TRENDS IN IMMUNOLOGY, 2013, 34 (04) :169-173
[7]   The Mcm Complex: Unwinding the Mechanism of a Replicative Helicase [J].
Bochman, Matthew L. ;
Schwacha, Anthony .
MICROBIOLOGY AND MOLECULAR BIOLOGY REVIEWS, 2009, 73 (04) :652-683
[8]   Independent filtering increases detection power for high-throughput experiments [J].
Bourgon, Richard ;
Gentleman, Robert ;
Huber, Wolfgang .
PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2010, 107 (21) :9546-9551
[9]  
Bray F, 2018, CA-CANCER J CLIN, V68, P394, DOI [10.3322/caac.21492, 10.3322/caac.21609]
[10]   Random forests [J].
Breiman, L .
MACHINE LEARNING, 2001, 45 (01) :5-32