Probabilistic Approach to Predicting Substrate Specificity of Methyltransferases

Teresa Szczepińska, Jan Kutner, Michał Kopczyński, Krzysztof Pawłowski, Andrzej Dziembowski, Andrzej Kudlicki, Krzysztof Ginalski, Malgorzata Rowicka-Kudlicka

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

We present a general probabilistic framework for predicting the substrate specificity of enzymes. We designed this approach to be easily applicable to different organisms and enzymes. Therefore, our predictive models do not rely on species-specific properties and use mostly sequence-derived data. Maximum Likelihood optimization is used to fine-tune model parameters and the Akaike Information Criterion is employed to overcome the issue of correlated variables. As a proof-of-principle, we apply our approach to predicting general substrate specificity of yeast methyltransferases (MTases). As input, we use several physico-chemical and biological properties of MTases: structural fold, isoelectric point, expression pattern and cellular localization. Our method accurately predicts whether a yeast MTase methylates a protein, RNA or another molecule. Among our experimentally tested predictions, 89% were confirmed, including the surprising prediction that YOR021C is the first known MTase with a SPOUT fold that methylates a substrate other than RNA (protein). Our approach not only allows for highly accurate prediction of functional specificity of MTases, but also provides insight into general rules governing MTase substrate specificity.

Original languageEnglish (US)
Article numbere1003514
JournalPLoS Computational Biology
Volume10
Issue number3
DOIs
StatePublished - 2014

Fingerprint

Probabilistic Approach
methyltransferases
Methyltransferases
substrate specificity
Substrate Specificity
Specificity
Substrate
substrate
prediction
Substrates
Yeasts
RNA
Yeast
yeasts
yeast
Prediction
Enzymes
Fold
Isoelectric Point
isoelectric point

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Modeling and Simulation
  • Ecology, Evolution, Behavior and Systematics
  • Genetics
  • Molecular Biology
  • Ecology
  • Cellular and Molecular Neuroscience

Cite this

Szczepińska, T., Kutner, J., Kopczyński, M., Pawłowski, K., Dziembowski, A., Kudlicki, A., ... Rowicka-Kudlicka, M. (2014). Probabilistic Approach to Predicting Substrate Specificity of Methyltransferases. PLoS Computational Biology, 10(3), [e1003514]. https://doi.org/10.1371/journal.pcbi.1003514

Probabilistic Approach to Predicting Substrate Specificity of Methyltransferases. / Szczepińska, Teresa; Kutner, Jan; Kopczyński, Michał; Pawłowski, Krzysztof; Dziembowski, Andrzej; Kudlicki, Andrzej; Ginalski, Krzysztof; Rowicka-Kudlicka, Malgorzata.

In: PLoS Computational Biology, Vol. 10, No. 3, e1003514, 2014.

Research output: Contribution to journalArticle

Szczepińska, T, Kutner, J, Kopczyński, M, Pawłowski, K, Dziembowski, A, Kudlicki, A, Ginalski, K & Rowicka-Kudlicka, M 2014, 'Probabilistic Approach to Predicting Substrate Specificity of Methyltransferases', PLoS Computational Biology, vol. 10, no. 3, e1003514. https://doi.org/10.1371/journal.pcbi.1003514
Szczepińska T, Kutner J, Kopczyński M, Pawłowski K, Dziembowski A, Kudlicki A et al. Probabilistic Approach to Predicting Substrate Specificity of Methyltransferases. PLoS Computational Biology. 2014;10(3). e1003514. https://doi.org/10.1371/journal.pcbi.1003514
Szczepińska, Teresa ; Kutner, Jan ; Kopczyński, Michał ; Pawłowski, Krzysztof ; Dziembowski, Andrzej ; Kudlicki, Andrzej ; Ginalski, Krzysztof ; Rowicka-Kudlicka, Malgorzata. / Probabilistic Approach to Predicting Substrate Specificity of Methyltransferases. In: PLoS Computational Biology. 2014 ; Vol. 10, No. 3.
@article{c902c7fa752943efb75a402b0bc894bb,
title = "Probabilistic Approach to Predicting Substrate Specificity of Methyltransferases",
abstract = "We present a general probabilistic framework for predicting the substrate specificity of enzymes. We designed this approach to be easily applicable to different organisms and enzymes. Therefore, our predictive models do not rely on species-specific properties and use mostly sequence-derived data. Maximum Likelihood optimization is used to fine-tune model parameters and the Akaike Information Criterion is employed to overcome the issue of correlated variables. As a proof-of-principle, we apply our approach to predicting general substrate specificity of yeast methyltransferases (MTases). As input, we use several physico-chemical and biological properties of MTases: structural fold, isoelectric point, expression pattern and cellular localization. Our method accurately predicts whether a yeast MTase methylates a protein, RNA or another molecule. Among our experimentally tested predictions, 89{\%} were confirmed, including the surprising prediction that YOR021C is the first known MTase with a SPOUT fold that methylates a substrate other than RNA (protein). Our approach not only allows for highly accurate prediction of functional specificity of MTases, but also provides insight into general rules governing MTase substrate specificity.",
author = "Teresa Szczepińska and Jan Kutner and Michał Kopczyński and Krzysztof Pawłowski and Andrzej Dziembowski and Andrzej Kudlicki and Krzysztof Ginalski and Malgorzata Rowicka-Kudlicka",
year = "2014",
doi = "10.1371/journal.pcbi.1003514",
language = "English (US)",
volume = "10",
journal = "PLoS Computational Biology",
issn = "1553-734X",
publisher = "Public Library of Science",
number = "3",

}

TY - JOUR

T1 - Probabilistic Approach to Predicting Substrate Specificity of Methyltransferases

AU - Szczepińska, Teresa

AU - Kutner, Jan

AU - Kopczyński, Michał

AU - Pawłowski, Krzysztof

AU - Dziembowski, Andrzej

AU - Kudlicki, Andrzej

AU - Ginalski, Krzysztof

AU - Rowicka-Kudlicka, Malgorzata

PY - 2014

Y1 - 2014

N2 - We present a general probabilistic framework for predicting the substrate specificity of enzymes. We designed this approach to be easily applicable to different organisms and enzymes. Therefore, our predictive models do not rely on species-specific properties and use mostly sequence-derived data. Maximum Likelihood optimization is used to fine-tune model parameters and the Akaike Information Criterion is employed to overcome the issue of correlated variables. As a proof-of-principle, we apply our approach to predicting general substrate specificity of yeast methyltransferases (MTases). As input, we use several physico-chemical and biological properties of MTases: structural fold, isoelectric point, expression pattern and cellular localization. Our method accurately predicts whether a yeast MTase methylates a protein, RNA or another molecule. Among our experimentally tested predictions, 89% were confirmed, including the surprising prediction that YOR021C is the first known MTase with a SPOUT fold that methylates a substrate other than RNA (protein). Our approach not only allows for highly accurate prediction of functional specificity of MTases, but also provides insight into general rules governing MTase substrate specificity.

AB - We present a general probabilistic framework for predicting the substrate specificity of enzymes. We designed this approach to be easily applicable to different organisms and enzymes. Therefore, our predictive models do not rely on species-specific properties and use mostly sequence-derived data. Maximum Likelihood optimization is used to fine-tune model parameters and the Akaike Information Criterion is employed to overcome the issue of correlated variables. As a proof-of-principle, we apply our approach to predicting general substrate specificity of yeast methyltransferases (MTases). As input, we use several physico-chemical and biological properties of MTases: structural fold, isoelectric point, expression pattern and cellular localization. Our method accurately predicts whether a yeast MTase methylates a protein, RNA or another molecule. Among our experimentally tested predictions, 89% were confirmed, including the surprising prediction that YOR021C is the first known MTase with a SPOUT fold that methylates a substrate other than RNA (protein). Our approach not only allows for highly accurate prediction of functional specificity of MTases, but also provides insight into general rules governing MTase substrate specificity.

UR - http://www.scopus.com/inward/record.url?scp=84897447639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897447639&partnerID=8YFLogxK

U2 - 10.1371/journal.pcbi.1003514

DO - 10.1371/journal.pcbi.1003514

M3 - Article

VL - 10

JO - PLoS Computational Biology

JF - PLoS Computational Biology

SN - 1553-734X

IS - 3

M1 - e1003514

ER -