Reaction graph kernels predict EC numbers of unknown enzymatic reactions in plant secondary metabolism

Hiroto Saigo, Masahiro Hattori, Hisashi Kashima, Koji Tsuda

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Background: Understanding of secondary metabolic pathway in plant is essential for finding druggable candidate enzymes. However, there are many enzymes whose functions are not yet discovered in organism-specific metabolic pathways. Towards identifying the functions of those enzymes, assignment of EC numbers to the enzymatic reactions they catalyze plays a key role, since EC numbers represent the categorization of enzymes on one hand, and the categorization of enzymatic reactions on the other hand.Results: We propose reaction graph kernels for automatically assigning EC numbers to unknown enzymatic reactions in a metabolic network. Reaction graph kernels compute similarity between two chemical reactions considering the similarity of chemical compounds in reaction and their relationships. In computational experiments based on the KEGG/REACTION database, our method successfully predicted the first three digits of the EC number with 83% accuracy. We also exhaustively predicted missing EC numbers in plant's secondary metabolism pathway. The prediction results of reaction graph kernels on 36 unknown enzymatic reactions are compared with an expert's knowledge. Using the same data for evaluation, we compared our method with E-zyme, and showed its ability to assign more number of accurate EC numbers.Conclusion: Reaction graph kernels are a new metric for comparing enzymatic reactions.

Original languageEnglish
Article numberS31
JournalBMC bioinformatics
Volume11
Issue numberSUPPLL.1
DOIs
Publication statusPublished - Jan 18 2010

Fingerprint

Secondary Metabolism
Metabolism
Enzymes
Metabolic Networks and Pathways
kernel
Predict
Unknown
Graph in graph theory
Chemical compounds
Pathway
Chemical reactions
Categorization
Databases
Metabolic Network
Digit
Chemical Reaction
Computational Experiments
Experiments
Assign
Assignment

All Science Journal Classification (ASJC) codes

  • Structural Biology
  • Biochemistry
  • Molecular Biology
  • Computer Science Applications
  • Applied Mathematics

Cite this

Reaction graph kernels predict EC numbers of unknown enzymatic reactions in plant secondary metabolism. / Saigo, Hiroto; Hattori, Masahiro; Kashima, Hisashi; Tsuda, Koji.

In: BMC bioinformatics, Vol. 11, No. SUPPLL.1, S31, 18.01.2010.

Research output: Contribution to journalArticle

Saigo, Hiroto ; Hattori, Masahiro ; Kashima, Hisashi ; Tsuda, Koji. / Reaction graph kernels predict EC numbers of unknown enzymatic reactions in plant secondary metabolism. In: BMC bioinformatics. 2010 ; Vol. 11, No. SUPPLL.1.
@article{a2fef2d73eda4de1aa290bdffd7812b5,
title = "Reaction graph kernels predict EC numbers of unknown enzymatic reactions in plant secondary metabolism",
abstract = "Background: Understanding of secondary metabolic pathway in plant is essential for finding druggable candidate enzymes. However, there are many enzymes whose functions are not yet discovered in organism-specific metabolic pathways. Towards identifying the functions of those enzymes, assignment of EC numbers to the enzymatic reactions they catalyze plays a key role, since EC numbers represent the categorization of enzymes on one hand, and the categorization of enzymatic reactions on the other hand.Results: We propose reaction graph kernels for automatically assigning EC numbers to unknown enzymatic reactions in a metabolic network. Reaction graph kernels compute similarity between two chemical reactions considering the similarity of chemical compounds in reaction and their relationships. In computational experiments based on the KEGG/REACTION database, our method successfully predicted the first three digits of the EC number with 83{\%} accuracy. We also exhaustively predicted missing EC numbers in plant's secondary metabolism pathway. The prediction results of reaction graph kernels on 36 unknown enzymatic reactions are compared with an expert's knowledge. Using the same data for evaluation, we compared our method with E-zyme, and showed its ability to assign more number of accurate EC numbers.Conclusion: Reaction graph kernels are a new metric for comparing enzymatic reactions.",
author = "Hiroto Saigo and Masahiro Hattori and Hisashi Kashima and Koji Tsuda",
year = "2010",
month = "1",
day = "18",
doi = "10.1186/1471-2105-11-S1-S31",
language = "English",
volume = "11",
journal = "BMC Bioinformatics",
issn = "1471-2105",
publisher = "BioMed Central",
number = "SUPPLL.1",

}

TY - JOUR

T1 - Reaction graph kernels predict EC numbers of unknown enzymatic reactions in plant secondary metabolism

AU - Saigo, Hiroto

AU - Hattori, Masahiro

AU - Kashima, Hisashi

AU - Tsuda, Koji

PY - 2010/1/18

Y1 - 2010/1/18

N2 - Background: Understanding of secondary metabolic pathway in plant is essential for finding druggable candidate enzymes. However, there are many enzymes whose functions are not yet discovered in organism-specific metabolic pathways. Towards identifying the functions of those enzymes, assignment of EC numbers to the enzymatic reactions they catalyze plays a key role, since EC numbers represent the categorization of enzymes on one hand, and the categorization of enzymatic reactions on the other hand.Results: We propose reaction graph kernels for automatically assigning EC numbers to unknown enzymatic reactions in a metabolic network. Reaction graph kernels compute similarity between two chemical reactions considering the similarity of chemical compounds in reaction and their relationships. In computational experiments based on the KEGG/REACTION database, our method successfully predicted the first three digits of the EC number with 83% accuracy. We also exhaustively predicted missing EC numbers in plant's secondary metabolism pathway. The prediction results of reaction graph kernels on 36 unknown enzymatic reactions are compared with an expert's knowledge. Using the same data for evaluation, we compared our method with E-zyme, and showed its ability to assign more number of accurate EC numbers.Conclusion: Reaction graph kernels are a new metric for comparing enzymatic reactions.

AB - Background: Understanding of secondary metabolic pathway in plant is essential for finding druggable candidate enzymes. However, there are many enzymes whose functions are not yet discovered in organism-specific metabolic pathways. Towards identifying the functions of those enzymes, assignment of EC numbers to the enzymatic reactions they catalyze plays a key role, since EC numbers represent the categorization of enzymes on one hand, and the categorization of enzymatic reactions on the other hand.Results: We propose reaction graph kernels for automatically assigning EC numbers to unknown enzymatic reactions in a metabolic network. Reaction graph kernels compute similarity between two chemical reactions considering the similarity of chemical compounds in reaction and their relationships. In computational experiments based on the KEGG/REACTION database, our method successfully predicted the first three digits of the EC number with 83% accuracy. We also exhaustively predicted missing EC numbers in plant's secondary metabolism pathway. The prediction results of reaction graph kernels on 36 unknown enzymatic reactions are compared with an expert's knowledge. Using the same data for evaluation, we compared our method with E-zyme, and showed its ability to assign more number of accurate EC numbers.Conclusion: Reaction graph kernels are a new metric for comparing enzymatic reactions.

UR - http://www.scopus.com/inward/record.url?scp=75149133815&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=75149133815&partnerID=8YFLogxK

U2 - 10.1186/1471-2105-11-S1-S31

DO - 10.1186/1471-2105-11-S1-S31

M3 - Article

C2 - 20122204

AN - SCOPUS:75149133815

VL - 11

JO - BMC Bioinformatics

JF - BMC Bioinformatics

SN - 1471-2105

IS - SUPPLL.1

M1 - S31

ER -