Download PDF
Planta Med 2015; 81(06): 450-458
DOI: 10.1055/s-0034-1396206
Original Papers
Georg Thieme Verlag KG Stuttgart · New York

Prediction of Anti-inflammatory Plants and Discovery of Their Biomarkers by Machine Learning Algorithms and Metabolomic Studies

Daniela Aparecida Chagas-Paula
1   AsterBioChem Research Team, Laboratory of Pharmacognosy, School of Pharmaceutical Sciences of Ribeirão Preto, University of São Paulo, Ribeirão Preto, SP, Brazil
,
Tiago Branquinho Oliveira
1   AsterBioChem Research Team, Laboratory of Pharmacognosy, School of Pharmaceutical Sciences of Ribeirão Preto, University of São Paulo, Ribeirão Preto, SP, Brazil
,
Tong Zhang
2   Strathclyde Institute of Pharmacy and Biomedical Sciences, University of Strathclyde, Glasgow, Scotland
,
RuAngelie Edrada-Ebel
2   Strathclyde Institute of Pharmacy and Biomedical Sciences, University of Strathclyde, Glasgow, Scotland
,
Fernando Batista Da Costa
1   AsterBioChem Research Team, Laboratory of Pharmacognosy, School of Pharmaceutical Sciences of Ribeirão Preto, University of São Paulo, Ribeirão Preto, SP, Brazil
› Author Affiliations
Further Information

Publication History

received 22 July 2014
revised 22 October 2014

accepted 14 December 2014

Publication Date:
23 January 2015 (online)

    Permissions and Reprints

Abstract

Nonsteroidal anti-inflammatory drugs are the most used anti-inflammatory medicines in the world. Side effects still occur, however, and some inflammatory pathologies lack efficient treatment. Cyclooxygenase and lipoxygenase pathways are of utmost importance in inflammatory processes; therefore, novel inhibitors are currently needed for both of them. Dual inhibitors of cyclooxygenase-1 and 5-lipoxygenase are anti-inflammatory drugs with high efficacy and low side effects. In this work, 57 leaf extracts (EtOH-H2O 7 : 3, v/v) from Asteraceae species with in vitro dual inhibition of cyclooxygenase-1 and 5-lipoxygenase were analyzed by high-performance liquid chromatography-high-resolution-ORBITRAP-mass spectrometry analysis and subjected to in silico studies using machine learning algorithms. The data from all samples were processed by employing differential expression analysis software coupled to the Dictionary of Natural Products for dereplication studies. The 6052 chromatographic peaks (ESI positive and negative modes) of the extracts were selected by a genetic algorithm according to their respective anti-inflammatory properties; after this procedure, 1241 of them remained. A study using a decision tree classifier was carried out, and 11 compounds were determined to be biomarkers due to their anti-inflammatory potential. Finally, a model to predict new biologically active extracts from Asteraceae species using liquid chromatography-mass spectrometry information with no prior knowledge of their biological data was built using a multilayer perceptron (artificial neural networks) with the back-propagation algorithm using the biomarker data. As a result, a new and robust artificial neural network model for predicting the anti-inflammatory activity of natural compounds was obtained, resulting in a high percentage of correct predictions (81 %), high precision (100 %) for dual inhibition, and low error values (mean absolute error = 0.3), as also shown in the validation test. Thus, the biomarkers of the Asteraceae extracts were statistically correlated with their anti-inflammatory activities and can therefore be useful to predict new anti-inflammatory extracts and their anti-inflammatory compounds using only liquid chromatography-mass spectrometry data.

Key words

Asteraceae - anti-inflammatory - cyclooxygenase - lipoxygenase - machine learning algorithms - metabolomics

Supporting Information

 

  • References

  • 1 Villas-Bôas SG, Mas S, Akesson M, Smedsgaard J, Nielsen J. Mass spectrometry in metabolome analysis. Mass Spectrom Rev 2005; 24: 613-646
    CrossrefPubMedGoogle Scholar
  • 2 Weckwerth W, Morgenthal K. Metabolomics: from pattern recognition to biological interpretation. Drug Discov Today 2005; 10: 1551-1558
    CrossrefPubMedGoogle Scholar
  • 3 Wolfender J, Marti G, Ferreira Queiroz E. Advances in techniques for profiling crude extracts and for the rapid identification of natural products: dereplication, quality control and metabolomics. Curr Org Chem 2010; 14: 1808-1832
    CrossrefPubMedGoogle Scholar
  • 4 Sumner LW, Mendes P, Dixon RA. Plant metabolomics: large-scale phytochemistry in the functional genomics era. Phytochemistry 2003; 62: 817-836
    CrossrefPubMedGoogle Scholar
  • 5 Bedair M, Sumner LW. Current and emerging mass-spectrometry technologies for metabolomics. Trends Anal Chem 2008; 27: 238-250
    CrossrefPubMedGoogle Scholar
  • 6 Newman DJ. Natural products as leads to potential drugs: an old process or the new hope for drug discovery?. J Med Chem 2008; 51: 2589-2599
    CrossrefPubMedGoogle Scholar
  • 7 Newman DJ, Cragg GM. Natural products as sources of new drugs over the last 30 years from 1981 to 2010. J Nat Prod 2012; 75: 311-335
    CrossrefPubMedGoogle Scholar
  • 8 Harvey AL. Natural products in drug discovery. Drug Discov Today 2008; 13: 894-901
    CrossrefPubMedGoogle Scholar
  • 9 De Donno A, Grassi T, Idolo A, Guido M, Papadia P, Caccioppola A, Villanova L, Merendino A, Bagordo F, Fanizzi FP. First-time comparison of the in vitro antimalarial activity of Artemisia annua herbal tea and artemisinin. Trans R Soc Trop Med Hyg 2012; 106: 696-700
    Google Scholar
  • 10 Phillipson JD. Phytochemistry and medicinal plants. Phytochemistry 2001; 56: 237-243
    CrossrefPubMedGoogle Scholar
  • 11 Wagner H. Synergy research: approaching a new generation of phytopharmaceuticals. Fitoterapia 2011; 82: 34-37
    CrossrefPubMedGoogle Scholar
  • 12 Yuliana ND, Khatib A, Choi YH, Verpoorte R. Metabolomics for bioactivity assessment of natural products. Phyther Res 2011; 25: 157-169
    PubMedGoogle Scholar
  • 13 Verpoorte R, Choi YH, Kim HK. Ethnopharmacology and systems biology: a perfect holistic match. J Ethnopharmacol 2005; 100: 53-56
    CrossrefPubMedGoogle Scholar
  • 14 Abdelmohsen UR, Cheng C, Viegelmann C, Zhang T, Grkovic T, Ahmed S, Quinn RJ, Hentschel U, Edrada-Ebel R. Dereplication strategies for targeted isolation of new antitrypanosomal actinosporins A and B from a marine sponge associated-Actinokineospora sp. EG49. Mar Drugs 2014; 12: 1220-1244
    CrossrefPubMedGoogle Scholar
  • 15 Shyur LF, Yang N. Metabolomics for phytomedicine research and drug development. Curr Opin Chem Biol 2008; 12: 66-71
    CrossrefPubMedGoogle Scholar
  • 16 Lang G, Mayhudin NA, Mitova MI, Sun L, van der Sar S, Blunt JW, Cole ALJ, Ellis G, Laatsch H, Munro MHG. Evolving trends in the dereplication of natural product extracts: new methodology for rapid, small-scale investigation of natural product extracts. J Nat Prod 2008; 71: 1595-1599
    CrossrefPubMedGoogle Scholar
  • 17 Nicholson JK, Lindon JC. Metabonomics. Nature 2008; 455: 1054-1056
    CrossrefPubMedGoogle Scholar
  • 18 Viegelmann C, Margassery LM, Kennedy J, Zhang T, OʼBrien C, OʼGara F, Morrissey JP, Dobson ADW, Edrada-Ebel R. Metabolomic profiling and genomic study of a marine sponge-associated Streptomyces sp . Mar Drugs 2014; 12: 3323-3351
    CrossrefPubMedGoogle Scholar
  • 19 Madsen R, Lundstedt T, Trygg J. Chemometrics in metabolomics – a review in human disease diagnosis. Anal Chim Acta 2010; 659: 23-33
    CrossrefPubMedGoogle Scholar
  • 20 Trygg J, Holmes E, Lundstedt T. Chemometrics in metabonomics. J Proteome Res 2007; 6: 469-479
    CrossrefPubMedGoogle Scholar
  • 21 Trygg J, Wold S. Orthogonal projections to latent structures (O-PLS). J Chemom 2002; 16: 119-128
    CrossrefPubMedGoogle Scholar
  • 22 Bylesjö M, Rantalainen M, Cloarec O, Nicholson JK, Holmes E, Trygg J. OPLS discriminant analysis: combining the strengths of PLS-DA and SIMCA classification. J Chemom 2006; 20: 341-351
    CrossrefPubMedGoogle Scholar
  • 23 Boccard J, Kalousis A, Hilario M, Lantéri P, Hanafi M, Mazerolles G, Wolfender JL, Carrupt PA, Rudaz S. Standard machine learning algorithms applied to UPLC-TOF/MS metabolic fingerprinting for the discovery of wound biomarkers in Arabidopsis thaliana . Chemom Intell Lab Syst 2010; 104: 20-27
    CrossrefPubMedGoogle Scholar
  • 24 Back B, Laitinen T, Sere K. Neural networks and genetic algorithms for bankruptcy predictions. Expert Syst Appl 1996; 11: 407-413
    CrossrefPubMedGoogle Scholar
  • 25 Anbarasi M, Anupriya E. Enhanced prediction of heart disease with feature subset selection using genetic algorithm. Int J Eng Sci Technol 2010; 2: 5370-5376
    PubMedGoogle Scholar
  • 26 Leardi R. Genetic algorithms in chemometrics and chemistry: a review. J Chemom 2001; 15: 559-569
    CrossrefPubMedGoogle Scholar
  • 27 Witten IH, Frank E, Hall MA. Data mining: practical machine learning tools and techniques. 3rd. edition. Burlington: Morgan Kaufmann Publishers; 2011: 490-493
    Google Scholar
  • 28 Tong DL, Mintram R. Genetic Algorithm-Neural Network (GANN): a study of neural network activation functions and depth of genetic algorithm search applied to feature selection. Int J Mach Learn Cybern 2010; 1: 75-87
    CrossrefPubMedGoogle Scholar
  • 29 Dʼheygere T, Goethals PLM, Pauw ND. Use of genetic algorithms to select input variables in decision tree models for the prediction of benthic macroinvertebrates. Ecol Model 2003; 160: 291-300
    CrossrefPubMedGoogle Scholar
  • 30 Karegowda AG, Manjunath AS, Jayaram MA. Comparative study of attribute selection using gain ration and correlation based feature selection. Int J Inf Technol Knowl Manag 2010; 2: 271-227
    PubMedGoogle Scholar
  • 31 Machine Learning Group. Class J48. Available at http://weka.sourceforge.net/doc.dev/weka/classifiers/trees/J48.html Accessed October 10, 2014
    PubMedGoogle Scholar
  • 32 Kotsiantis SB. Supervised machine learning: a review of classification techniques. Informatica 2007; 31: 249-268
    PubMedGoogle Scholar
  • 33 Quinlan JR. Improved use of continuous attributes in C4.5. J Artif Intell Res 2006; 4: 77-90
    PubMedGoogle Scholar
  • 34 Endo A, Shibata T, Tanaka H. Comparison of seven algorithms to predict breast cancer survival. Biomed Soft Comput Hum Sci 2008; 13: 11-16
    PubMedGoogle Scholar
  • 35 Zarkami R. Application of classification trees-J48 to model the presence of roach (Rutilus rutilus) in rivers. Casp J Environ Sci 2011; 9: 189-198
    PubMedGoogle Scholar
  • 36 Hecht-Nielsen R. Theory of the backpropagation neural network. International Joint Conference on Neural Networks, Vol. 1. Washington: IEEE; 1989: 593-605
    CrossrefGoogle Scholar
  • 37 Parente L. Pros and cons of selective inhibition of cyclooxygenase-2 versus dual lipoxygenase/cyclooxygenase inhibition: is two better than one?. J Rheumatol 2001; 28: 2375-2382
    PubMedGoogle Scholar
  • 38 Fiorucci S, Meli R, Bucci M, Cirino G. Dual inhibitors of cyclooxygenase and 5-lipoxygenase. A new avenue in anti-inflammatory therapy?. Biochem Pharmacol 2001; 62: 1433-1438
    CrossrefPubMedGoogle Scholar
  • 39 Gaddi A, Cicero AFG, Pedro EJ. Clinical perspectives of anti-inflammatory therapy in the elderly: the lipoxigenase (LOX)/cycloxigenase (COX) inhibition concept. Arch Gerontol Geriatr 2004; 38: 201-212
    PubMedGoogle Scholar
  • 40 Schneider I, Bucar F. Lipoxygenase inhibitors from natural plant sources. Part 1: Medicinal plants with inhibitory activity on arachidonate 5-lipoxygenase and 5-lipoxygenase[sol]cyclooxygenase. Phyther Res 2005; 19: 81-102
    PubMedGoogle Scholar
  • 41 Rao PNP, Knaus EE. Evolution of nonsteroidal anti-inflammatory drugs (NSAIDs): cyclooxygenase (COX) inhibition and beyond. J Pharm Pharm Sci 2008; 11: 81-110
    CrossrefPubMedGoogle Scholar
  • 42 Celotti F, Durand T. The metabolic effects of inhibitors of 5-lipoxygenase and of cyclooxygenase 1 and 2 are an advancement in the efficacy and safety of anti-inflammatory therapy. Prostag Oth Lipid M 2003; 71: 147-162
    CrossrefPubMedGoogle Scholar
  • 43 Schmidt TJ. Toxic activities of sesquiterpene lactones: structural and biochemical aspects. Curr Org Chem 1999; 3: 577-608
    PubMedGoogle Scholar
  • 44 Frédérich M, Jansen C, de Tullio P, Tits M, Demoulin V, Angenot L. Metabolomic analysis of Echinacea spp. by 1H nuclear magnetic resonance spectrometry and multivariate data analysis technique. Phytochem Anal 2010; 21: 61-65
    CrossrefPubMedGoogle Scholar
  • 45 Li Z, Zhi H, Zhang F, Sun H, Zhang L, Jia J, Xing J, Qin X. Metabolomic profiling of the antitussive and expectorant plant Tussilago farfara L. by nuclear magnetic resonance spectroscopy and multivariate data analysis. J Pharmacol Biomed Anal 2013; 75: 158-164
    CrossrefPubMedGoogle Scholar
  • 46 Modarai M, Yang M, Suter A, Kortenkamp A, Heinrich M. Metabolomic profiling of liquid Echinacea medicinal products with in vitro inhibitory effects on cytochrome P450 3A4 (CYP3A4). Planta Med 2010; 76: 378-385
    Article in Thieme ConnectPubMedGoogle Scholar
  • 47 Bórquez J, Kennelly EJ, Simirgiotis MJ. Activity guided isolation of isoflavones and hyphenated HPLC-PDA-ESI-ToF-MS metabolome profiling of Azorella madreporica Clos. from northern Chile. Food Res Int 2013; 52: 288-297
    CrossrefPubMedGoogle Scholar
  • 48 Inui T, Wang Y, Pro SM, Franzblau SG, Pauli GF. Unbiased evaluation of bioactive secondary metabolites in complex matrices. Fitoterapia 2012; 83: 1218-1225
    CrossrefPubMedGoogle Scholar
  • 49 Ching J, Soh WL, Tan CH, Lee J, Tan JC, Yang J, Yap C, Koh H. Identification of active compounds from medicinal plant extracts using gas chromatography-mass spectrometry and multivariate data analysis. J Sep Sci 2012; 35: 53-59
    CrossrefPubMedGoogle Scholar
  • 50 Yuliana ND, Khatib A, Verpoorte R, Choi YH. Comprehensive extraction method integrated with NMR metabolomics: a new bioactivity screening method for plants, adenosine A1 receptor binding compounds in Orthosiphon stamineus Benth. Anal Chem 2011; 83: 6902-6906
    CrossrefPubMedGoogle Scholar
  • 51 Cabrera AC, Prieto JM. Application of artificial neural networks to the prediction of the antioxidant activity of essential oils in two experimental in vitro models. Food Chem 2010; 118: 141-146
    CrossrefPubMedGoogle Scholar
  • 52 Khan J, Wei JS, Ringnér M, Saal LH, Ladanyi M, Westermann F, Berthold F, Schwab M, Antonescu CR, Peterson C, Meltzer PS. Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks. Nat Med 2001; 7: 673-679
    CrossrefPubMedGoogle Scholar
  • 53 Kuhn M. Building predictive models in R using the caret package. J Stat Softw 2008; 28: 1-26
    PubMedGoogle Scholar
  • 54 Macintyre L, Zhang T, Viegelmann C, Martinez IJ, Cheng C, Dowdells C, Abdelmohsen UR, Gernert C, Hentschel U, Edrada-Ebel R. Metabolomic tools for secondary metabolite discovery from marine microbial symbionts. Mar Drugs 2014; 12: 3416-3448
    CrossrefPubMedGoogle Scholar
  • 55 Eriksson L, Trygg J, Wold S. CV-ANOVA for significance testing of PLS and OPLS® models. J Chemom 2008; 22: 594-600
    CrossrefPubMedGoogle Scholar
  • 56 Tropsha A, Golbraikh A. Predictive QSAR modeling workflow, model applicability domains, and virtual screening. Curr Pharm Des 2007; 13: 3494-3504
    CrossrefPubMedGoogle Scholar
  • 57 Golbraikh A, Tropsha A. Beware of q2!. J Mol Graph Model 2002; 20: 269-276
    CrossrefPubMedGoogle Scholar
  • 58 Corley DG, Durley RC. Strategies for database dereplication of natural products. J Nat Prod 1994; 57: 1484-1490
    CrossrefPubMedGoogle Scholar
  • 59 García-Mediavilla V, Crespo I, Collado PS, Esteller A, Sánchez-Campos S, Tuñón MJ, Gonzállez-Gallego J. The anti-inflammatory flavones quercetin and kaempferol cause inhibition of inducible nitric oxide synthase, cyclooxygenase-2 and reactive C-protein, and down-regulation of the nuclear factor kappaB pathway in Chang Liver cells. Eur J Pharmacol 2007; 557: 221-229
    CrossrefPubMedGoogle Scholar
  • 60 Chagas-Paula DA, Oliveira RB, Rocha BA, Da Costa FB. Ethnobotany, chemistry, and biological activities of the genus Tithonia (Asteraceae). Chem Biodivers 2012; 9: 210-235
    CrossrefPubMedGoogle Scholar
  • 61 Sabir SM, Ahmad SD, Hamid A, Khan MQ, Athayde ML, Santos DB, Boligon AA, Rocha JBT. Antioxidant and hepatoprotective activity of ethanolic extract of leaves of Solidago microglossa containing polyphenolic compounds. Food Chem 2012; 131: 741-747
    CrossrefPubMedGoogle Scholar
  • 62 Heinrich M, Robles M, West JE, Ortiz de Montellano BR, Rodriguez E. Ethnopharmacology of Mexican Asteraceae (Compositae). Annu Rev Pharmacol Toxicol 1998; 38: 539-565
    CrossrefPubMedGoogle Scholar