Transactions of Tianjin University

, Volume 23, Issue 3, pp 237–244 | Cite as

Use of Support Vector Regression Based on Mean Impact Value Model to Identify Active Compounds in a Combination of Curcuma longa L. and Glycyrrhiza extracts

  • Jianlan Jiang
  • Qingjie Tan
  • Weifeng Li
  • Xinyun Du
  • Ningzhi Liu
Research article


A support vector regression based on the mean impact value (MIV) model was constructed to identify the bioactive compounds inhibiting proliferation of HeLa cells in a combination of turmeric (Curcuma longa L.) and liquorice (Glycyrrhiza) extracts. The quantitative chemical fingerprint from 50 batches of turmeric and liquorice extracts was established using high performance liquid chromatography hyphenated to an ultraviolet visible detector. Qualitative results were obtained using ultra performance liquid chromatography coupled with electrospray ionization quadrupole time-of-flight tandem mass spectrometry. A total of 46 peaks (peaks 1–15 from turmeric and 16–46 from liquorice) were selected as “common peaks” for analysis. The inhibitory effect of the combined extracts on HeLa cells was measured by MTT (3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide) assay. It was found that 15 compounds (peaks: 8, 12, 30, 24, 46, 11, 14, 9, 3, 1, 44, 18, 7, 45 and 43) possessing high absolute MIV exhibited a significant correlation with the cytotoxicity against HeLa cells; most of these have already been confirmed with potential cytotoxicity in previous research. The important potential application of the present model can be extended to help discover active compounds from complex herbal medicine prior to traditional bioassay-guided separation. It is considered that this could be a useful tool for re-developing herbal medicine based on the use of these active compounds.


Curcuma longa L. Glycyrrhiza Active compound identification Support vector regression Mean impact value 



The authors are grateful to the financial support provided by the National Natural Science Foundation of China (No. 81102900).

Supplementary material

12209_2017_44_MOESM1_ESM.doc (478 kb)
Supplementary material 1 (DOC 478 kb)


  1. 1.
    Wang Y, Wang X, Cheng Y (2006) A computational approach to botanical drug design by modeling quantitative composition–activity relationship. Chem Biol Drug Des 68(3):166–172CrossRefGoogle Scholar
  2. 2.
    Harvey A (2000) Strategies for discovering drugs from previously unexplored natural products. Drug Discov Today 5(7):294–300CrossRefGoogle Scholar
  3. 3.
    Cheng YY, Wang Y, Wang XW (2006) A causal relationship discovery-based approach to identifying active components of herbal medicine. Comput Biol Chem 30(2):148–154CrossRefMATHGoogle Scholar
  4. 4.
    Jiang JL, Jin XL, Zhang H et al (2012) Identification of antitumor constituents in curcuminoids from Curcuma longa L. based on the composition-activity relationship. J Pharm Biomed Anal 70:664–670CrossRefGoogle Scholar
  5. 5.
    Jiang JL, Su X, Zhang H et al (2013) A novel approach to active compounds identification based on support vector regression model and mean impact value. Chem Biol Drug Des 81(5):650–657CrossRefGoogle Scholar
  6. 6.
    Wang XY, Zhang H, Chen LL et al (2013) Liquorice, a unique “guide drug” of traditional Chinese medicine: a review of its role in drug interactions. J Ethnopharmacol 150(3):781–790CrossRefGoogle Scholar
  7. 7.
    Jiang JL, Ding HT, Su X et al (2012) Identification of anti-tumor ingredients in curcuma volatile oil based on composition–activity relationship. Chin J Anal Chem 40:1488–1493 (in Chinese) Google Scholar
  8. 8.
    Ruby AJ, Kuttan G, Dinesh Babu K et al (1995) Anti-tumour and antioxidant activity of natural curcuminoids. Cancer Lett 94(1):79–83CrossRefGoogle Scholar
  9. 9.
    Chung WT, Lee SH, Dai Kim J et al (2001) Effect of the extracts from Glycyrrhiza uralensis Fisch on the growth characteristics of human cell lines: anti-tumor and immune activation activities. Cytotechnology 37(1):55–64CrossRefGoogle Scholar
  10. 10.
    Li HD, Liang YZ, Xu QS (2009) Support vector machines and its applications in chemistry. Chemom Intell Lab Syst 95(2):188–198CrossRefGoogle Scholar
  11. 11.
    Chen C, Li SX, Wang SM et al (2011) A support vector machine based pharmacodynamic prediction model for searching active fraction and ingredients of herbal medicine: Naodesheng prescription as an example. J Pharm Biomed Anal 56(2):443–447CrossRefGoogle Scholar
  12. 12.
    Jiang JL, Su X, Ding HT et al (2013) A novel approach to evaluate the quality and identify the active compounds of the essential oil from Curcuma longa L. Anal Lett 46(8):1213–1228CrossRefGoogle Scholar
  13. 13.
    Kennedy J (2010) Particle swarm optimization. Springer, New YorkGoogle Scholar
  14. 14.
    Fu ZG, Qi MF, Jing Y (2012) Regression forecast of main steam flow based on mean impact value and support vector regression. In: Regression forecast of main steam flow based on mean impact value and support vector regression. Power and Energy Engineering Conference (APPEEC), Asia-Pacific, IEEE, pp.1–5Google Scholar
  15. 15.
    Chang CC, Lin CJ (2007) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):389–396Google Scholar
  16. 16.
    Ahmed Hamdi OA, Syed Abdul Rahman SN, Awang K et al (2013) Cytotoxic constituents from the rhizomes of Curcuma zedoaria. Sci World J 2014(1):321943Google Scholar
  17. 17.
    Cheng SB, Wu LC, Hsieh YC et al (2012) Supercritical carbon dioxide extraction of aromatic turmerone from Curcuma longa Linn. induces apoptosis through reactive oxygen species-triggered intrinsic and extrinsic pathways in human hepatocellular carcinoma HepG2 cells. J Agric Food Chem 60(38):9620–9630CrossRefGoogle Scholar
  18. 18.
    Aratanechemuge Y, Komiya T, Moteki H et al (2002) Selective induction of apoptosis by ar-turmerone isolated from turmeric (Curcuma longa L) in two human leukemia cell lines, but not in human stomach cancer cell line. Int J Mol Med 9(5):481–484Google Scholar
  19. 19.
    Lee SK, Hong CH, Huh SK et al (2002) Suppressive effect of natural sesquiterpenoids on inducible cyclooxygenase (COX-2) and nitric oxide synthase (iNOS) activity in mouse macrophage cells. J Environ Pathol Toxicol Oncol 21(2):141–148Google Scholar
  20. 20.
    Simon A, Allais DP, Duroux JL et al (1998) Inhibitory effect of curcuminoids on MCF-7 cell proliferation and structure-activity relationships. Cancer Lett 129(1):111–116CrossRefGoogle Scholar
  21. 21.
    Nci D (1996) Clinical development plan: curcumin. J Cell Biochem 26:72–85Google Scholar
  22. 22.
    Smejkal K, Svacinová J, Slapetova T et al (2010) Cytotoxic activities of several geranyl-substituted flavanones. J Nat Prod 73(4):568–572CrossRefGoogle Scholar
  23. 23.
    Park SY, Lim SS, Kim JK et al (2010) Hexane-ethanol extract of Glycyrrhiza uralensis containing licoricidin inhibits the metastatic capacity of DU145 human prostate cancer cells. Br J Nutr 104(09):1272–1282CrossRefGoogle Scholar
  24. 24.
    Fukai T, Marumo A, Kaitou K et al (2002) Anti-helicobacter pylori flavonoids from licorice extract. Life Sci 71(12):1449–1463CrossRefGoogle Scholar

Copyright information

© Tianjin University and Springer-Verlag Berlin Heidelberg 2017

Authors and Affiliations

  • Jianlan Jiang
    • 1
  • Qingjie Tan
    • 1
  • Weifeng Li
    • 1
  • Xinyun Du
    • 1
  • Ningzhi Liu
    • 1
  1. 1.Key Laboratory of Systems Bioengineering, Ministry of Education, Tianjin Key Laboratory of Biological and Pharmaceutical Engineering, School of Chemical Engineering and TechnologyTianjin UniversityTianjinChina

Personalised recommendations