SpringerLink
Log in

An Interpretable Screening Approach Derived Through XGBoost Regression for the Discovery of Hypolipidemic Contributors in Chinese Hawthorn Leaf and its Counterfeit Malus Doumeri Leaf

  • Research
  • Published:
Plant Foods for Human Nutrition Aims and scope Submit manuscript

Abstract

The active ingredient group is a prominent feature reflecting the inherent characteristics of plant-based functional foods. Chinese hawthorn leaf (CHL), a tea substitute possessing intrinsic nutritional properties in anti-hyperlipidemia, was first found to be adulterated with Malus doumeri leaf (MDL) owing to similar commercial labels. In this context, the above-mentioned two contrasting species were explored through phytochemical profiling and activity assessment. The amelioration effect of CHL on free fatty acids-elicited lipid deposition in HepG2 cells was significantly better than that of MDL. Molecular networking-based metabolic profiles identified 68 and 67 components in CHL and MDL, with 33 shared components. Extreme gradient boosting (XGBoost) algorithm with outstanding performance was selected to screen candidate components contributing to hypolipidemic activity, and the output was later interpreted by Shapley additive explanations (SHAP) method. Twelve and eight components were separately screened as hyperlipidemic inhibitors in CHL and MDL, while only four constituents were shared. The bioactivity evaluation of selected ingredients and combinations further confirmed their anti-hyperlipidemia capacity. These findings emphasized the feasibility of filtering bioactivity-related compounds using interpretable machine learning approaches and illustrated that related species may contain different hypolipidemic contributors, even if shared constituents existed.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data Availability

The data that support the findings of this study are available from the corresponding author upon reasonable request.

Abbreviations

CD 3.1:

Compound Discoverer 3.1

CHL:

Chinese hawthorn leaf

FFA:

free fatty acid

GNPS:

Global Natural Products Social

HepG2 cells:

human hepatoblastoma cells

MDL:

Malus doumeri leaf

ML:

machine learning

MSE:

mean square error

OD:

optical density

ORO:

oil red O

PA:

palmitic acid

RSS:

residual sum of squares

SHAP:

Shapley additive explanations

XGBoost:

extreme gradient boosting

References

  1. Pang X, Wang M, Wang S, Zhang J, Du Y, Zhao Y, Zheng X, Ma B (2021) Phenolic compounds from the leaves of Crataegus pinnatifida Bge. var. major N.E. Br. and their lipid-lowering effects. Bioorganic Med Chem Lett 47:128211. https://doi.org/10.1016/j.bmcl.2021.128211.

  2. Yan S, Chen J, Zhu L, Guo T, Qin D, Hu Z, Han S, Zhou Y, Akan OD, Wang J, Luo F, Lin Q (2022) Oryzanol attenuates high fat and cholesterol diet-induced hyperlipidemia by regulating the gut microbiome and amino acid metabolism. J Agric Food Chem 70:6429–6443. https://doi.org/10.1021/acs.jafc.2c00885

    Article  CAS  PubMed  Google Scholar 

  3. Li R, Luan F, Zhao Y, Wu M, Lu Y, Tao C, Zhu L, Zhang C, Wan L (2023) Crataegus pinnatifida: a botanical, ethnopharmacological, phytochemical, and pharmacological overview. J Ethnopharmacol 301:115819. https://doi.org/10.1016/j.jep.2022.115819

    Article  CAS  PubMed  Google Scholar 

  4. Gao PY, Li SS, Liu KC, Sun C, Song SJ, Li LZ (2019) Antiplatelet aggregation and antithrombotic benefits of terpenes and flavones from hawthorn leaf extract isolated using activity-guided method. Food Funct 10:859–866. https://doi.org/10.1039/c8fo01862f

    Article  CAS  PubMed  Google Scholar 

  5. Li LZ, Gao PY, Song SJ, Yuan YQ, Liu CT, Huang XX, Liu QB (2015) Monoterpenes and flavones from the leaves of Crataegus pinnatifida with anticoagulant activities. J Funct Foods 12:237–245. https://doi.org/10.1016/j.jff.2014.11.012

    Article  CAS  Google Scholar 

  6. Hu H, Weng J, Cui C, Tang F, Yu M, Zhou Y, Shao F, Zhu Y (2022) The hypolipidemic effect of hawthorn leaf flavonoids through modulating lipid metabolism and gut microbiota in hyperlipidemic rats. Evid Based Complementary Altern Med 2022:3033311. https://doi.org/10.1155/2022/3033311

    Article  Google Scholar 

  7. Luo M, Yang X, Hu JY, Jiao J, Mu FS, Song ZY, Gai QY, Qiao Q, Ruan X, Fu YJ (2016) Antioxidant properties of phenolic compounds in renewable parts of Crataegus pinnatifida inferred from seasonal variations. J Food Sci 81:C1102–C1109. https://doi.org/10.1111/1750-3841.13291

    Article  CAS  PubMed  Google Scholar 

  8. Xu Y, Deng T, **e L, Qin T, Sun T (2023) Neuroprotective effects of hawthorn leaf flavonoids in Aβ25-35-induced Alzheimer’s disease model. Phytother Res 37:1346–1365. https://doi.org/10.1002/ptr.7690

    Article  CAS  PubMed  Google Scholar 

  9. Wang ZY, **ong H, Duan LY, Wang CF, Du YL, Hong X, Zha HH, Pan HF (2021) UPLC-Q-TOF-MS based metabolomics study of hawthorn leaves in different geographical regions. Anal Methods 13:5458–5466. https://doi.org/10.1039/d1ay01150b

    Article  CAS  PubMed  Google Scholar 

  10. Edwards JE, Brown PN, Talent N, Dickinson TA, Shipley PR (2012) A review of the chemistry of the genus Crataegus. Phytochemistry 79:5–26. https://doi.org/10.1016/j.phytochem.2012.04.006

    Article  CAS  PubMed  Google Scholar 

  11. Li Y, Li Y, Fang Z, Huang D, Yang Y, Zhao D, Hang M, Wang J (2020) The effect of Malus Doumeri leaf flavonoids on oxidative stress injury induced by hydrogen peroxide (H2O2) in human embryonic kidney 293 T cells. BMC Complement Med Ther 20:276. https://doi.org/10.1186/s12906-020-03072-6

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  12. Shen B, Zhou R, Yang Y, Li J, Liang X, Chen L, Huang L, Zhang S (2018) Antimicrobial activity-guided identification of compounds from the deciduous leaves of Malus doumeri by HPLC-ESI-QTOF-MS/MS. Nat Prod Res 33:2515–2520. https://doi.org/10.1080/14786419.2018.1457666

    Article  CAS  PubMed  Google Scholar 

  13. Shen Y, Shen Z, Li P, Chen Z, Wei B, Liu D, Si X, Pan J, Wu D, Li W (2022) Protective activity of Malus Doumeri leaf extract on H2O2-induced oxidative injury in H9C2 rat cardiomyocytes. Front Cardiovasc Med 9:1005306. https://doi.org/10.3389/fcvm.2022.1005306

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  14. Wen L, Zheng G, You L, Abbasi AM, Li T, Fu X, Liu RH (2016) Phytochemical profiles and cellular antioxidant activity of Malus doumeri (bois) chevalier on 2,2′-azobis (2-amidinopropane) dihydrochloride (ABAP)-induced oxidative stress. J Funct Foods 25:242–256. https://doi.org/10.1016/j.jff.2016.06.004

    Article  CAS  Google Scholar 

  15. Xu B, Yang M, Du Y, Zhao S, Li Y, Pan H (2018) Fingerprint and multi-ingredient quantitative analyses for quality evaluation of hawthorn leaves and Guang Hawthorn leaves by UPLC-MS. Rev Bras Farmacogn 28:369–373. https://doi.org/10.1016/j.bjp.2018.03.005

    Article  CAS  Google Scholar 

  16. Fujimura Y, Watanabe M, Morikawa-Ichinose T, Fu**o K, Yamamoto M, Nishioka S, Inoue C, Ogawa F, Yonekura M, Nakasone A, Kumazoe M, Tachibana H (2022) Metabolic profiling for evaluating the dipeptidyl peptidase-IV inhibitory potency of diverse green tea cultivars and determining bioactivity-related ingredients and combinations. J Agric Food Chem 70:6455–6466. https://doi.org/10.1021/acs.jafc.2c01693

    Article  CAS  PubMed  Google Scholar 

  17. Gurumayum N, Sarma P, Khound P, Jana U, Devi R (2023) Nutritional composition and pharmacological activity of Musa balbisiana Colla seed: an insight into phytochemical and cellular bioenergetic profiling. Plant Foods Hum Nutr 78(3):520–525. https://doi.org/10.1007/s11130-023-01080-8

    Article  CAS  PubMed  Google Scholar 

  18. Huang J, Yang SY, Li W, Zhang W, Li Z, Feng Y, Dong S, Lv Z, Du Y, Zhao Y (2022) Valorization of the industrial waste of two uncommon parts from lotus (Nelumbo nucifera Gaertn.): insight to phytochemicals and hypolipidemic potential. Ind Crop Prod 188:115596. https://doi.org/10.1016/j.indcrop.2022.115596

    Article  CAS  Google Scholar 

  19. Gunning D, Stefik M, Choi J, Miller T, Stumpf S, Yang GZ (2019) XAI-Explainable artificial intelligence. Sci Robot 4:7120. https://doi.org/10.1126/scirobotics.aay7120

    Article  Google Scholar 

  20. Deng M, Jia X, Dong L, Liu L, Huang F, Chi J, Ma Q, Zhao D, Zhang M, Zhang R (2022) Structural elucidation of flavonoids from Shatianyu (Citrus grandis L. Osbeck) pulp and screening of key antioxidant components. Food Chem 366:130605. https://doi.org/10.1016/j.foodchem.2021.130605

    Article  CAS  PubMed  Google Scholar 

  21. Guo R, Zhao B, Wang Y, Wu D, Wang Y, Yu Y, Yan Y, Zhang W, Liu Z, Liu X (2018) Cichoric acid prevents free-fatty-acid-induced lipid metabolism disorders via regulating Bmal1 in HepG2 cells. J Agric Food Chem 66:9667–9678. https://doi.org/10.1021/acs.jafc.8b02147

    Article  CAS  PubMed  Google Scholar 

  22. Fox Ramos AE, Evanno L, Poupon E, Champy P, Beniddir MA (2019) Natural products targeting strategies involving molecular networking: different manners, one goal. Nat Prod Rep 36:960–980. https://doi.org/10.1039/c9np00006b

    Article  CAS  PubMed  Google Scholar 

  23. Bar N, Korem T, Weissbrod O et al (2020) A reference map of potential determinants for the human serum metabolome. Nature 588:135–140. https://doi.org/10.1038/s41586-020-2896-2

    Article  ADS  PubMed  Google Scholar 

  24. Huang J, Li Z, Zhang W, Lv Z, Dong S, Feng Y, Liu R, Zhao Y (2023) Explainable machine learning-assisted origin identification: Chemical profiling of five lotus (Nelumbo nucifera Gaertn.) Parts. Food Chem 404:134517. https://doi.org/10.1016/j.foodchem.2022.134517

    Article  CAS  PubMed  Google Scholar 

Download references

Funding

This work was supported by Natural Science Foundation of Shandong Province of China (grant number ZR2023QH054) and Graduate Innovation Foundation of Yantai University (grant number GGIFYTU2335).

Author information

Author notes

  1. Zhen Li and Yuan Du shared as Co-first authors.

Authors and Affiliations

  1. School of Pharmacy, Key Laboratory of Molecular Pharmacology and Drug Evaluation (Yantai University), Collaborative Innovation Center of Advanced Drug Delivery System and Biotech Drugs in Universities of Shandong, Ministry of Education, Yantai University, Yantai, 264005, PR China

    Zhen Li, Yuan Du, Chen Ding, Pufan Yang, Lin Wang & Yan Zhao

Authors
  1. Zhen Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yuan Du
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chen Ding
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Pufan Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Lin Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yan Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Zhen Li: Conceptualization, Visualization, Investigation, Data curation, Writing – original draft. Yuan Du: Methodology, Resources. Chen Ding: Formal analysis, Methodology, Investigation. Pufan Yang: Conceptualization, Investigation. Lin Wang: Project administration, Supervision. Yan Zhao: Conceptualization, Investigation, Funding acquisition, Software, Writing – review & editing. All authors reviewed the manuscript.

Corresponding authors

Correspondence to Lin Wang or Yan Zhao.

Ethics declarations

Ethics Approval

Not applicable.

Consent to Participate

Not applicable.

Consent for Publication

Not applicable.

Competing Interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic Supplementary Material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Li, Z., Du, Y., Ding, C. et al. An Interpretable Screening Approach Derived Through XGBoost Regression for the Discovery of Hypolipidemic Contributors in Chinese Hawthorn Leaf and its Counterfeit Malus Doumeri Leaf. Plant Foods Hum Nutr 79, 209–218 (2024). https://doi.org/10.1007/s11130-024-01148-z

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11130-024-01148-z

Keywords

Search

Navigation