IDEAS home Printed from https://ideas.repec.org/a/nat/natcom/v15y2024i1d10.1038_s41467-024-51433-3.html
   My bibliography  Save this article

An end-to-end deep learning method for mass spectrometry data analysis to reveal disease-specific metabolic profiles

Author

Listed:
  • Yongjie Deng

    (Sun Yat-sen University)

  • Yao Yao

    (Sun Yat-sen University Cancer Center
    Sun Yat-sen University)

  • Yanni Wang

    (Sun Yat-sen University)

  • Tiantian Yu

    (Sun Yat-sen University
    Sun Yat-sen University Cancer Center
    Sun Yat-sen University)

  • Wenhao Cai

    (Sun Yat-sen University)

  • Dingli Zhou

    (Sun Yat-sen University)

  • Feng Yin

    (Sun Yat-sen University Cancer Center)

  • Wanli Liu

    (Sun Yat-sen University Cancer Center)

  • Yuying Liu

    (Sun Yat-sen University Cancer Center)

  • Chuanbo Xie

    (Sun Yat-sen University Cancer Center)

  • Jian Guan

    (The First Affiliated Hospital of Sun Yat-sen University)

  • Yumin Hu

    (Sun Yat-sen University Cancer Center
    Sun Yat-sen University)

  • Peng Huang

    (Sun Yat-sen University Cancer Center
    Sun Yat-sen University)

  • Weizhong Li

    (Sun Yat-sen University
    Sun Yat-Sen University
    Sun Yat-sen University)

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.

Suggested Citation

  • Yongjie Deng & Yao Yao & Yanni Wang & Tiantian Yu & Wenhao Cai & Dingli Zhou & Feng Yin & Wanli Liu & Yuying Liu & Chuanbo Xie & Jian Guan & Yumin Hu & Peng Huang & Weizhong Li, 2024. "An end-to-end deep learning method for mass spectrometry data analysis to reveal disease-specific metabolic profiles," Nature Communications, Nature, vol. 15(1), pages 1-17, December.
  • Handle: RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-51433-3
    DOI: 10.1038/s41467-024-51433-3
    as

    Download full text from publisher

    File URL: https://www.nature.com/articles/s41467-024-51433-3
    File Function: Abstract
    Download Restriction: no

    File URL: https://libkey.io/10.1038/s41467-024-51433-3?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Xiaotao Shen & Ruohong Wang & Xin Xiong & Yandong Yin & Yuping Cai & Zaijun Ma & Nan Liu & Zheng-Jiang Zhu, 2019. "Metabolic reaction network-based recursive metabolite annotation for untargeted metabolomics," Nature Communications, Nature, vol. 10(1), pages 1-14, December.
    2. Yangzi Chen & Bohong Wang & Yizi Zhao & Xinxin Shao & Mingshuo Wang & Fuhai Ma & Laishou Yang & Meng Nie & Peng Jin & Ke Yao & Haibin Song & Shenghan Lou & Hang Wang & Tianshu Yang & Yantao Tian & Pen, 2024. "Metabolomic machine learning predictor for diagnosis and prognosis of gastric cancer," Nature Communications, Nature, vol. 15(1), pages 1-13, December.
    3. Taiyun Kim & Owen Tang & Stephen T. Vernon & Katharine A. Kott & Yen Chin Koay & John Park & David E. James & Stuart M. Grieve & Terence P. Speed & Pengyi Yang & Gemma A. Figtree & John F. O’Sullivan , 2021. "A hierarchical approach to removal of unwanted variation for large-scale metabolomics data," Nature Communications, Nature, vol. 12(1), pages 1-10, December.
    4. Yao Yao & Xueping Wang & Jian Guan & Chuanbo Xie & Hui Zhang & Jing Yang & Yao Luo & Lili Chen & Mingyue Zhao & Bitao Huo & Tiantian Yu & Wenhua Lu & Qiao Liu & Hongli Du & Yuying Liu & Peng Huang & T, 2023. "Metabolomic differentiation of benign vs malignant pulmonary nodules with high specificity via high-resolution mass spectrometry analysis of patient sera," Nature Communications, Nature, vol. 14(1), pages 1-12, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Yingxin Lin & Yue Cao & Elijah Willie & Ellis Patrick & Jean Y. H. Yang, 2023. "Atlas-scale single-cell multi-sample multi-condition data integration using scMerge2," Nature Communications, Nature, vol. 14(1), pages 1-13, December.
    2. Xiaotao Shen & Hong Yan & Chuchu Wang & Peng Gao & Caroline H. Johnson & Michael P. Snyder, 2022. "TidyMass an object-oriented reproducible analysis framework for LC–MS data," Nature Communications, Nature, vol. 13(1), pages 1-12, December.
    3. Zhiqiang Pang & Lei Xu & Charles Viau & Yao Lu & Reza Salavati & Niladri Basu & Jianguo Xia, 2024. "MetaboAnalystR 4.0: a unified LC-MS workflow for global metabolomics," Nature Communications, Nature, vol. 15(1), pages 1-15, December.
    4. Ruohong Wang & Yandong Yin & Jingshu Li & Hongmiao Wang & Wanting Lv & Yang Gao & Tangci Wang & Yedan Zhong & Zhiwei Zhou & Yuping Cai & Xiaoyang Su & Nan Liu & Zheng-Jiang Zhu, 2022. "Global stable-isotope tracing metabolomics reveals system-wide metabolic alternations in aging Drosophila," Nature Communications, Nature, vol. 13(1), pages 1-14, December.
    5. Hanyu Rao & Changwei Liu & Aiting Wang & Chunxiao Ma & Yue Xu & Tianbao Ye & Wenqiong Su & Peijun Zhou & Wei-Qiang Gao & Li Li & Xianting Ding, 2023. "SETD2 deficiency accelerates sphingomyelin accumulation and promotes the development of renal cancer," Nature Communications, Nature, vol. 14(1), pages 1-15, December.
    6. Jiali Lv & Chang Pan & Yuping Cai & Xinyue Han & Cheng Wang & Jingjing Ma & Jiaojiao Pang & Feng Xu & Shuo Wu & Tianzhang Kou & Fandong Ren & Zheng-Jiang Zhu & Tao Zhang & Jiali Wang & Yuguo Chen, 2024. "Plasma metabolomics reveals the shared and distinct metabolic disturbances associated with cardiovascular events in coronary artery disease," Nature Communications, Nature, vol. 15(1), pages 1-13, December.
    7. Mingdu Luo & Yandong Yin & Zhiwei Zhou & Haosong Zhang & Xi Chen & Hongmiao Wang & Zheng-Jiang Zhu, 2023. "A mass spectrum-oriented computational method for ion mobility-resolved untargeted metabolomics," Nature Communications, Nature, vol. 14(1), pages 1-15, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:nat:natcom:v:15:y:2024:i:1:d:10.1038_s41467-024-51433-3. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.nature.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.