1
|
Deng Y, Yao Y, Wang Y, Yu T, Cai W, Zhou D, Yin F, Liu W, Liu Y, Xie C, Guan J, Hu Y, Huang P, Li W. An end-to-end deep learning method for mass spectrometry data analysis to reveal disease-specific metabolic profiles. Nat Commun 2024; 15:7136. [PMID: 39164279 PMCID: PMC11335749 DOI: 10.1038/s41467-024-51433-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2024] [Accepted: 08/07/2024] [Indexed: 08/22/2024] Open
Abstract
Untargeted metabolomic analysis using mass spectrometry provides comprehensive metabolic profiling, but its medical application faces challenges of complex data processing, high inter-batch variability, and unidentified metabolites. Here, we present DeepMSProfiler, an explainable deep-learning-based method, enabling end-to-end analysis on raw metabolic signals with output of high accuracy and reliability. Using cross-hospital 859 human serum samples from lung adenocarcinoma, benign lung nodules, and healthy individuals, DeepMSProfiler successfully differentiates the metabolomic profiles of different groups (AUC 0.99) and detects early-stage lung adenocarcinoma (accuracy 0.961). Model flow and ablation experiments demonstrate that DeepMSProfiler overcomes inter-hospital variability and effects of unknown metabolites signals. Our ensemble strategy removes background-category phenomena in multi-classification deep-learning models, and the novel interpretability enables direct access to disease-related metabolite-protein networks. Further applying to lipid metabolomic data unveils correlations of important metabolites and proteins. Overall, DeepMSProfiler offers a straightforward and reliable method for disease diagnosis and mechanism discovery, enhancing its broad applicability.
Collapse
Affiliation(s)
- Yongjie Deng
- Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
| | - Yao Yao
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China
- Metabolic Innovation Platform, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
| | - Yanni Wang
- Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
| | - Tiantian Yu
- Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China
- Metabolic Innovation Platform, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
| | - Wenhao Cai
- Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
| | - Dingli Zhou
- Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China
| | - Feng Yin
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China
| | - Wanli Liu
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China
| | - Yuying Liu
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China
| | - Chuanbo Xie
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China
| | - Jian Guan
- Department of Radiology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China
| | - Yumin Hu
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China.
- Metabolic Innovation Platform, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China.
| | - Peng Huang
- State Key Laboratory of Oncology in South China, Guangdong Provincial Clinical Research Center for Cancer, Sun Yat-sen University Cancer Center, Guangzhou, China.
- Metabolic Innovation Platform, Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China.
| | - Weizhong Li
- Zhongshan School of Medicine, Sun Yat-sen University, Guangzhou, China.
- Sun Yat-Sen University School of Medicine, Sun Yat-Sen University, Shenzhen, China.
- Key Laboratory of Tropical Disease Control of Ministry of Education, Sun Yat-sen University, Guangzhou, China.
| |
Collapse
|
2
|
Sun B, Fang Y, Yang H, Meng F, He C, Zhao Y, Zhao K, Zhang H. The combination of deep learning and pseudo-MS image improves the applicability of metabolomics to congenital heart defect prenatal screening. Talanta 2024; 275:126109. [PMID: 38648686 DOI: 10.1016/j.talanta.2024.126109] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2024] [Revised: 04/09/2024] [Accepted: 04/12/2024] [Indexed: 04/25/2024]
Abstract
To investigate the metabolic alterations in maternal individuals with fetal congenital heart disease (FCHD), establish the FCHD diagnostic models, and assess the performance of these models, we recruited two batches of pregnant women. By metabolomics analysis using Ultra High-performance Liquid Chromatography-Mass/Mass (UPLC-MS/MS), a total of 36 significantly altered metabolites (VIP >1.0) were identified between FCHD and non-FCHD groups. Two logistic regression models and four support vector machine (SVM) models exhibited strong performance and clinical utility in the training set (area under the curve (AUC) = 1.00). The convolutional neural network (CNN) model also demonstrated commendable performance and clinical utility (AUC = 0.89 in the training set). Notably, in the validation set, the performance of the CNN model (AUC = 0.66, precision = 0.714) exhibited better robustness than the six models above (AUC≤0.50). In conclusion, the CNN model based on pseudo-MS images holds promise for real-world and clinical applications due to its better repeatability.
Collapse
Affiliation(s)
- Borui Sun
- Institute of Reproductive Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China
| | - Yiwei Fang
- Institute of Reproductive Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China; Center for Reproductive Medicine, Department of Obstetrics and Gynecology, Peking University Third Hospital, No. 49, North Garden Road, Haidian district, Beijing, 100191, China; National Clinical Research Center for Obstetrics and Gynecology, Peking University Third Hospital, Beijing, 100191, China; State Key Laboratory of Female Fertility Promotion, Department of Obstetrics and Gynecology, Peking University Third Hospital, Beijing, 100191, China; Key Laboratory of Assisted Reproduction, Ministry of Education, Peking University, Beijing, 100191, China; Beijing Key Laboratory of Reproductive Endocrinology and Assisted Reproductive Technology, Beijing, 100191, China.
| | - Hui Yang
- Department of Obstetrics, Maternal and Child Health Hospital of Hubei Province, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430070, China
| | - Fan Meng
- Institute of Reproductive Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China
| | - Chao He
- Institute of Reproductive Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China
| | - Yun Zhao
- Department of Obstetrics, Maternal and Child Health Hospital of Hubei Province, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430070, China.
| | - Kai Zhao
- Institute of Reproductive Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China.
| | - Huiping Zhang
- Institute of Reproductive Health, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, 430030, China.
| |
Collapse
|
3
|
Bernardo RA, Roque JV, de Oliveira Júnior CI, Lima NM, Machado LS, Duarte GRM, Costa NL, Sorgi CA, Soares FFL, Vaz BG, Chaves AR. Exploring salivary lipid profile changes in COVID-19 patients: Insights from mass spectrometry analysis. Talanta 2024; 269:125522. [PMID: 38091738 DOI: 10.1016/j.talanta.2023.125522] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/27/2023] [Revised: 11/27/2023] [Accepted: 12/04/2023] [Indexed: 01/05/2024]
Abstract
The most common COVID-19 testing relies on the use of nasopharyngeal swabs. However, this sampling step is very uncomfortable and is one of the biggest challenges regarding population testing. In the present study, the use of saliva as an alternative sample for COVID-19 diagnosis was investigated. Therefore, high-resolution mass spectrometry analysis and chemometric approaches were applied to salivary lipid extracts. Two data organizations were used: classical MS data and pseudo-MS image datasets. The latter transformed MS data into pseudo-images, simplifying data interpretation. Classification models achieved high accuracy, with pseudo-MS image data performing exceptionally well. PLS-DA with OPSDA successfully separated COVID-19 and healthy groups, serving as a potential diagnostic tool. The most important lipids for COVID-19 classification were elucidated and include sphingolipids, ceramides, phospholipids, and glycerolipids. These lipids play a crucial role in viral replication and the inflammatory response. While pseudo-MS image data excelled in classification, it lacked the ability to annotate important variables, which was performed using classical MS data. These findings have the potential to improve clinical diagnosis using rapid, non-invasive testing methods and accurate high-volume results.
Collapse
Affiliation(s)
- Ricardo A Bernardo
- Instituto de Química, Universidade Federal de Goiás, 74690-900, Goiânia, GO, Brazil; Departamento de Química, Universidade Federal do Paraná, 81531-980, Curitiba, PR, Brazil.
| | - Jussara V Roque
- Instituto de Química, Universidade Federal de Goiás, 74690-900, Goiânia, GO, Brazil
| | - Charles I de Oliveira Júnior
- Instituto de Química, Universidade Federal de Goiás, 74690-900, Goiânia, GO, Brazil; Departamento de Química, Universidade Federal de Jataí, 75804-020, Jataí, GO, Brazil
| | | | - Lucas Santos Machado
- Instituto de Química, Universidade Federal de Goiás, 74690-900, Goiânia, GO, Brazil
| | | | - Nádia L Costa
- Faculdade de Odontologia, Universidade Federal de Goiás, 74605-020, Goiânia, GO, Brazil
| | - Carlos A Sorgi
- Departamento de Química, Faculdade de Filosofia, Ciências e Letras de Ribeirão Preto, Universidade de São Paulo, 14015-130, Ribeirão Preto, SP, Brazil
| | - Frederico F L Soares
- Departamento de Química, Universidade Federal do Paraná, 81531-980, Curitiba, PR, Brazil
| | - Boniek G Vaz
- Instituto de Química, Universidade Federal de Goiás, 74690-900, Goiânia, GO, Brazil
| | - Andréa R Chaves
- Instituto de Química, Universidade Federal de Goiás, 74690-900, Goiânia, GO, Brazil; Departamento de Química, Universidade Federal de Jataí, 75804-020, Jataí, GO, Brazil.
| |
Collapse
|