Discovery of plant anti-inflammatory biomarkers by machine learning algorithms and metabolomic studies

Daniela Chagas de Paula, T. B. Oliveria, Tong Zhang, Ruangelie Edrada-Ebel, Fernando B Da Costa

Research output: Contribution to journalConference Contribution

Abstract

NSAIDs are the most used anti-inflammatory (AI) drugs in the world. However, side effects still occur and some inflammatory pathologies lack efficient treatment. Cyclooxygenase (COX) and lipoxygenase (LOX) pathways are of utmost importance in inflammatory processes and therefore novel inhibitors for both of them are needed. Dual inhibitors on COX-1 and 5-LOX should be AI medicines with high efficacy and low side effects [1]. As AI activity of species from Asteraceae is well-known, we screened 55 leaf extracts (EtOH-H2O 7:3, v/v) against COX-1 and 5-LOX.

Among the tested extracts, 13 of them (26.6%, IC50 range from 0.03 – 36 µg/mL) displayed the desired inhibition. Each extract was further analysed by HPLC-HRFTMS. The data of all samples were processed employing a differential expression analysis software (MZmine 2.6) coupled to the Dictionary of Natural Products for dereplication studies. The 6,052 characteristic peaks in the extracts according to their respective AI properties were selected by genetic search (Weka 3) and 1,261 of them remained. An additional selection by decision trees J48 (Weka 3) was carried out and 11 substances were determined as biomarkers for the dual inhibition. Finally, a model to predict new biologically active extracts was built by multilayer perceptron using the biomarkers data (70% of active and non-active samples comprised the training group and 30% the test group).

In summary, we developed a new and robust model for prediction of the bioactivity of natural compounds, resulting in high percentage of correct predictions (90%), high precision (100%) for dual inhibition, and low error values (mean absolute error = 0.2) as also shown in the validation test. Thus, the biomarkers of the plant extracts were statistically correlated with their AI activities and therefore can be useful to predict new AI extracts as well as their AI compounds.

Fingerprint

Metabolomics
Biomarkers
Learning algorithms
Learning systems
Anti-Inflammatory Agents
Arachidonate 5-Lipoxygenase
Cyclooxygenase 1
Decision Trees
Asteraceae
Neural Networks (Computer)
Lipoxygenase
Plant Extracts
Non-Steroidal Anti-Inflammatory Agents
Pathology
Multilayer neural networks
Prostaglandin-Endoperoxide Synthases
Glossaries
Decision trees
Bioactivity
Machine Learning

Keywords

  • plant anti-inflammatory biomarkers
  • anti-inflammatory drugs
  • cyclooxygenase
  • lipoxygenase
  • COX
  • LOX
  • natural compounds
  • bioactivity

Cite this

Chagas de Paula, Daniela ; Oliveria, T. B. ; Zhang, Tong ; Edrada-Ebel, Ruangelie ; B Da Costa, Fernando. / Discovery of plant anti-inflammatory biomarkers by machine learning algorithms and metabolomic studies. In: Planta Medica. 2013 ; Vol. 79, No. 13.
@article{6e602682cc7b46718e15f72350c4720f,
title = "Discovery of plant anti-inflammatory biomarkers by machine learning algorithms and metabolomic studies",
abstract = "NSAIDs are the most used anti-inflammatory (AI) drugs in the world. However, side effects still occur and some inflammatory pathologies lack efficient treatment. Cyclooxygenase (COX) and lipoxygenase (LOX) pathways are of utmost importance in inflammatory processes and therefore novel inhibitors for both of them are needed. Dual inhibitors on COX-1 and 5-LOX should be AI medicines with high efficacy and low side effects [1]. As AI activity of species from Asteraceae is well-known, we screened 55 leaf extracts (EtOH-H2O 7:3, v/v) against COX-1 and 5-LOX.Among the tested extracts, 13 of them (26.6{\%}, IC50 range from 0.03 – 36 µg/mL) displayed the desired inhibition. Each extract was further analysed by HPLC-HRFTMS. The data of all samples were processed employing a differential expression analysis software (MZmine 2.6) coupled to the Dictionary of Natural Products for dereplication studies. The 6,052 characteristic peaks in the extracts according to their respective AI properties were selected by genetic search (Weka 3) and 1,261 of them remained. An additional selection by decision trees J48 (Weka 3) was carried out and 11 substances were determined as biomarkers for the dual inhibition. Finally, a model to predict new biologically active extracts was built by multilayer perceptron using the biomarkers data (70{\%} of active and non-active samples comprised the training group and 30{\%} the test group).In summary, we developed a new and robust model for prediction of the bioactivity of natural compounds, resulting in high percentage of correct predictions (90{\%}), high precision (100{\%}) for dual inhibition, and low error values (mean absolute error = 0.2) as also shown in the validation test. Thus, the biomarkers of the plant extracts were statistically correlated with their AI activities and therefore can be useful to predict new AI extracts as well as their AI compounds.",
keywords = "plant anti-inflammatory biomarkers, anti-inflammatory drugs, cyclooxygenase, lipoxygenase, COX, LOX, natural compounds, bioactivity",
author = "{Chagas de Paula}, Daniela and Oliveria, {T. B.} and Tong Zhang and Ruangelie Edrada-Ebel and {B Da Costa}, Fernando",
year = "2013",
month = "8",
doi = "10.1055/s-0033-1351853",
language = "English",
volume = "79",
journal = "Planta Medica",
issn = "0032-0943",
number = "13",

}

Discovery of plant anti-inflammatory biomarkers by machine learning algorithms and metabolomic studies. / Chagas de Paula, Daniela; Oliveria, T. B.; Zhang, Tong; Edrada-Ebel, Ruangelie; B Da Costa, Fernando.

In: Planta Medica, Vol. 79, No. 13, SL27, 08.2013.

Research output: Contribution to journalConference Contribution

TY - JOUR

T1 - Discovery of plant anti-inflammatory biomarkers by machine learning algorithms and metabolomic studies

AU - Chagas de Paula, Daniela

AU - Oliveria, T. B.

AU - Zhang, Tong

AU - Edrada-Ebel, Ruangelie

AU - B Da Costa, Fernando

PY - 2013/8

Y1 - 2013/8

N2 - NSAIDs are the most used anti-inflammatory (AI) drugs in the world. However, side effects still occur and some inflammatory pathologies lack efficient treatment. Cyclooxygenase (COX) and lipoxygenase (LOX) pathways are of utmost importance in inflammatory processes and therefore novel inhibitors for both of them are needed. Dual inhibitors on COX-1 and 5-LOX should be AI medicines with high efficacy and low side effects [1]. As AI activity of species from Asteraceae is well-known, we screened 55 leaf extracts (EtOH-H2O 7:3, v/v) against COX-1 and 5-LOX.Among the tested extracts, 13 of them (26.6%, IC50 range from 0.03 – 36 µg/mL) displayed the desired inhibition. Each extract was further analysed by HPLC-HRFTMS. The data of all samples were processed employing a differential expression analysis software (MZmine 2.6) coupled to the Dictionary of Natural Products for dereplication studies. The 6,052 characteristic peaks in the extracts according to their respective AI properties were selected by genetic search (Weka 3) and 1,261 of them remained. An additional selection by decision trees J48 (Weka 3) was carried out and 11 substances were determined as biomarkers for the dual inhibition. Finally, a model to predict new biologically active extracts was built by multilayer perceptron using the biomarkers data (70% of active and non-active samples comprised the training group and 30% the test group).In summary, we developed a new and robust model for prediction of the bioactivity of natural compounds, resulting in high percentage of correct predictions (90%), high precision (100%) for dual inhibition, and low error values (mean absolute error = 0.2) as also shown in the validation test. Thus, the biomarkers of the plant extracts were statistically correlated with their AI activities and therefore can be useful to predict new AI extracts as well as their AI compounds.

AB - NSAIDs are the most used anti-inflammatory (AI) drugs in the world. However, side effects still occur and some inflammatory pathologies lack efficient treatment. Cyclooxygenase (COX) and lipoxygenase (LOX) pathways are of utmost importance in inflammatory processes and therefore novel inhibitors for both of them are needed. Dual inhibitors on COX-1 and 5-LOX should be AI medicines with high efficacy and low side effects [1]. As AI activity of species from Asteraceae is well-known, we screened 55 leaf extracts (EtOH-H2O 7:3, v/v) against COX-1 and 5-LOX.Among the tested extracts, 13 of them (26.6%, IC50 range from 0.03 – 36 µg/mL) displayed the desired inhibition. Each extract was further analysed by HPLC-HRFTMS. The data of all samples were processed employing a differential expression analysis software (MZmine 2.6) coupled to the Dictionary of Natural Products for dereplication studies. The 6,052 characteristic peaks in the extracts according to their respective AI properties were selected by genetic search (Weka 3) and 1,261 of them remained. An additional selection by decision trees J48 (Weka 3) was carried out and 11 substances were determined as biomarkers for the dual inhibition. Finally, a model to predict new biologically active extracts was built by multilayer perceptron using the biomarkers data (70% of active and non-active samples comprised the training group and 30% the test group).In summary, we developed a new and robust model for prediction of the bioactivity of natural compounds, resulting in high percentage of correct predictions (90%), high precision (100%) for dual inhibition, and low error values (mean absolute error = 0.2) as also shown in the validation test. Thus, the biomarkers of the plant extracts were statistically correlated with their AI activities and therefore can be useful to predict new AI extracts as well as their AI compounds.

KW - plant anti-inflammatory biomarkers

KW - anti-inflammatory drugs

KW - cyclooxygenase

KW - lipoxygenase

KW - COX

KW - LOX

KW - natural compounds

KW - bioactivity

UR - http://www.thieme.com/

U2 - 10.1055/s-0033-1351853

DO - 10.1055/s-0033-1351853

M3 - Conference Contribution

VL - 79

JO - Planta Medica

T2 - Planta Medica

JF - Planta Medica

SN - 0032-0943

IS - 13

M1 - SL27

ER -