Copyright
©The Author(s) 2020. Published by Baishideng Publishing Group Inc. All rights reserved.
Establishment of a pattern recognition metabolomics model for the diagnosis of hepatocellular carcinoma
Peng-Cheng Zhou, Lun-Quan Sun, Li Shao, Lun-Zhao Yi, Ning Li, Xue-Gong Fan
Peng-Cheng Zhou, Ning Li, Xue-Gong Fan, Hunan Key Laboratory of Viral Hepatitis and Department of Infectious Diseases, Xiangya Hospital, Central South University, Changsha 410008, Hunan Province, China
Peng-Cheng Zhou, Department of Infectious Diseases and Infection Control Center, The third Xiangya Hospital, Central South University, Changsha 410013, Hunan Province, China
Peng-Cheng Zhou, Infection Control Center, Xiangya Hospital, Central South University, Changsha 410008, Hunan Province, China
Lun-Quan Sun, Center for Molecular Medicine, Xiangya Hospital, Central South University, Changsha 410008, Hunan Province, China
Li Shao, Institute of Translational Medicine, The Affiliated Hospital, Hangzhou Normal University, Hangzhou 311121, Zhejiang Province, China
Lun-Zhao Yi, Yunnan Food Safety Research Institute, Kunming University of Science and Technology, Kunming 650500, Yunnan Province, China
Ning Li, Department of Blood Transfusion, Xiangya Hospital, Central South University, Changsha 410008, Hunan Province, China
Author contributions: Li N and Fan XG contributed to the experimental design and contributed equally to this work; Zhou PC collected the serum samples; Yi LZ performed the UPLC-MS analysis; Zhou PC, Sun LQ and Shao L contributed to the data analysis and wrote the original draft; all authors have read and approved the manuscript.
Supported by National Natural Science Foundation of China, No. 81800472 and No. 81670538; the Science Foundation of Hunan Health Commission, No. B2019184.
Institutional review board statement: The study was approved by the Ethics Committee of Xiangya Hospital, Central South University (Changsha, China).
Informed consent statement: The patients gave informed consent.
Conflict-of-interest statement: The authors have declared that no competing interests exist.
Data sharing statement: Technical appendix, statistical code, and dataset available from the corresponding author at xgfan@hotmail.com.
STROBE statement: The authors have read the STROBE Statement-checklist of items, and the manuscript was prepared and revised according to the STROBE Statement-checklist of items.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/
Corresponding author: Xue-Gong Fan, MD, PhD, Professor, Hunan Key Laboratory of Viral Hepatitis and Department of Infectious Diseases, Xiangya Hospital, Central South University, No. 87 Xiangya Road, Changsha 410008, Hunan Province, China.
xgfan@hotmail.com
Received: March 19, 2020
Peer-review started: March 19, 2020
First decision: April 18, 2020
Revised: May 27, 2020
Accepted: July 22, 2020
Article in press: July 22, 2020
Published online: August 21, 2020
Processing time: 155 Days and 4.4 Hours
ARTICLE HIGHLIGHTS
Research background
Early diagnosis of hepatocellular carcinoma (HCC) offers patients a better chance for long-term survival. The current biomarkers are far from satisfactory as they lack sensitivity and specificity. The emergence of metabolomics has provided a powerful tool for discovering novel biomarkers. In previous studies, we established a pattern recognition metabolomics method based on sequential feature selection combined with linear discriminant analysis for differential diagnosis.
Research motivation
There is an urgent and unmet desire for novel screening methods and new biomarkers for the diagnosis of HCC. Whether the pattern recognition method mentioned above could be used to establish a metabolomics model for the diagnosis of HCC is still unknown.
Research objectives
We aimed to use the pattern recognition method to develop a metabolomics diagnostic model and identify new biomarkers for HCC screening.
Research methods
We used ultra-performance liquid chromatography-mass spectroscopy to characterize the serum metabolome of HCC and cirrhosis patients. We then processed the multivariate data using sequential feature selection combined with linear discriminant analysis.
Research results
The concentrations of most metabolites, including proline, were lower in patients with HCC, whereas hydroxypurine levels were higher in these patients. As ordinary analysis models failed to discriminate hepatocellular carcinoma from cirrhosis, pattern recognition analysis was used to establish a pattern recognition model that included hydroxypurine and proline. The leave-one-out cross-validation accuracy and area under curve (AUC) were 95.00% and 0.90 (95% confidence interval (CI): 0.81–0.99) for the training set, respectively, and 78.95% and 0.84 (95%CI: 0.67–1.00) for the validation set, respectively. The Z test revealed that the AUC of the model was significantly higher than the AUC (P < 0.05) in both the training and validation sets.
Research conclusions
Hydroxypurine and proline might be novel biomarkers for HCC, and the disease could be diagnosed by the metabolomics model based on pattern recognition.
Research perspectives
This study determined the applicability of the pattern recognition metabolomics model for the diagnosis of HCC. Two novel biomarkers for HCC were also found. Future studies should verify the validity of the model and the applicability of the biomarkers in the early diagnosis of patients with HCC.
