Accurate prediction of kinase-substrate networks using
knowledge graphs

J 2020

Accurate prediction of kinase-substrate networks using knowledge graphs

NOVÁČEK, Vít, Gavin MCGAURAN, David MATALLANAS, Adrián Vallejo BLANCO, Piero CONCA et. al.

Základní údaje

Originální název

Accurate prediction of kinase-substrate networks using knowledge graphs

Autoři

NOVÁČEK, Vít (203 Česká republika, garant, domácí), Gavin MCGAURAN, David MATALLANAS, Adrián Vallejo BLANCO, Piero CONCA, Emir MUÑOZ, Luca COSTABELLO, Kamalesh KANAKARAJ, Zeeshan NAWAZ, Brian WALSH, Sameh K MOHAMED, Pierre-Yves VANDENBUSSCHE, Colm J RYAN, Walter KOLCH a Dirk FEY

Vydání

PLoS Computational Biology, Cambridge, PLoS, 2020, 1553-734X

Další údaje

Jazyk

angličtina

Typ výsledku

Článek v odborném periodiku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Velká Británie a Severní Irsko

Utajení

není předmětem státního či obchodního tajemství

Odkazy

URL URL

Impakt faktor

Impact factor: 4.475

Kód RIV

RIV/00216224:14330/20:00118443

Organizační jednotka

Fakulta informatiky

DOI

http://dx.doi.org/10.1371/journal.pcbi.1007578

UT WoS

000597151200003

Klíčová slova anglicky

knowledge graphs; kinase-substrate networks; phosphorylation prediction; relational machine learning

Štítky

kinase-substrate networks, knowledge graphs, phosphorylation prediction, relational machine learning

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 10. 5. 2021 06:22, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

Phosphorylation of specific substrates by protein kinases is a key control mechanism for vital cell-fate decisions and other cellular processes. However, discovering specific kinase-substrate relationships is time-consuming and often rather serendipitous. Computational predictions alleviate these challenges, but the current approaches suffer from limitations like restricted kinome coverage and inaccuracy. They also typically utilise only local features without reflecting broader interaction context. To address these limitations, we have developed an alternative predictive model. It uses statistical relational learning on top of phosphorylation networks interpreted as knowledge graphs, a simple yet robust model for representing networked knowledge. Compared to a representative selection of six existing systems, our model has the highest kinome coverage and produces biologically valid high-confidence predictions not possible with the other tools. Specifically, we have experimentally validated predictions of previously unknown phosphorylations by the LATS1, AKT1, PKA and MST2 kinases in human. Thus, our tool is useful for focusing phosphoproteomic experiments, and facilitates the discovery of new phosphorylation reactions. Our model can be accessed publicly via an easy-to-use web interface (LinkPhinder).

Přiložené soubory

journal.pcbi.1007578.pdf

Vyhledat podobné dokumenty

Citovat

NOVÁČEK, Vít, Gavin MCGAURAN, David MATALLANAS, Adrián Vallejo BLANCO, Piero CONCA, Emir MUÑOZ, Luca COSTABELLO, Kamalesh KANAKARAJ, Zeeshan NAWAZ, Brian WALSH, Sameh K MOHAMED, Pierre-Yves VANDENBUSSCHE, Colm J RYAN, Walter KOLCH a Dirk FEY. Accurate prediction of kinase-substrate networks using knowledge graphs. PLoS Computational Biology. Cambridge: PLoS, 2020, roč. 16, č. 12, s. 1-30. ISSN 1553-734X. Dostupné z: https://dx.doi.org/10.1371/journal.pcbi.1007578.

@article{1754803,
   author = {Nováček, Vít and McGauran, Gavin and Matallanas, David and Blanco, Adrián Vallejo and Conca, Piero and Muñoz, Emir and Costabello, Luca and Kanakaraj, Kamalesh and Nawaz, Zeeshan and Walsh, Brian and Mohamed, Sameh K and Vandenbussche, PierreandYves and Ryan, Colm J and Kolch, Walter and Fey, Dirk},
   article_location = {Cambridge},
   article_number = {12},
   doi = {http://dx.doi.org/10.1371/journal.pcbi.1007578},
   keywords = {knowledge graphs; kinase-substrate networks; phosphorylation prediction; relational machine learning},
   language = {eng},
   issn = {1553-734X},
   journal = {PLoS Computational Biology},
   title = {Accurate prediction of kinase-substrate networks using knowledge graphs},
   url = {https://figshare.com/projects/Accurate_Prediction_of_Kinase-Substrate_Networks_Using_Knowledge_Graphs/79254},
   volume = {16},
   year = {2020}
}

TY  - JOUR
ID  - 1754803
AU  - Nováček, Vít - McGauran, Gavin - Matallanas, David - Blanco, Adrián Vallejo - Conca, Piero - Muñoz, Emir - Costabello, Luca - Kanakaraj, Kamalesh - Nawaz, Zeeshan - Walsh, Brian - Mohamed, Sameh K - Vandenbussche, Pierre-Yves - Ryan, Colm J - Kolch, Walter - Fey, Dirk
PY  - 2020
TI  - Accurate prediction of kinase-substrate networks using knowledge graphs
JF  - PLoS Computational Biology
VL  - 16
IS  - 12
SP  - 1-30
EP  - 1-30
PB  - PLoS
SN  - 1553734X
KW  - knowledge graphs
KW  - kinase-substrate networks
KW  - phosphorylation prediction
KW  - relational machine learning
UR  - https://figshare.com/projects/Accurate_Prediction_of_Kinase-Substrate_Networks_Using_Knowledge_Graphs/79254
N2  - Phosphorylation of specific substrates by protein kinases is a key control mechanism for vital cell-fate decisions and other cellular processes. However, discovering specific kinase-substrate relationships is time-consuming and often rather serendipitous. Computational predictions alleviate these challenges, but the current approaches suffer from limitations like restricted kinome coverage and inaccuracy. They also typically utilise only local features without reflecting broader interaction context. To address these limitations, we have developed an alternative predictive model. It uses statistical relational learning on top of phosphorylation networks interpreted as knowledge graphs, a simple yet robust model for representing networked knowledge. Compared to a representative selection of six existing systems, our model has the highest kinome coverage and produces biologically valid high-confidence predictions not possible with the other tools. Specifically, we have experimentally validated predictions of previously unknown phosphorylations by the LATS1, AKT1, PKA and MST2 kinases in human. Thus, our tool is useful for focusing phosphoproteomic experiments, and facilitates the discovery of new phosphorylation reactions. Our model can be accessed publicly via an easy-to-use web interface (LinkPhinder).
ER  -

NOVÁČEK, Vít, Gavin MCGAURAN, David MATALLANAS, Adrián Vallejo BLANCO, Piero CONCA, Emir MUÑOZ, Luca COSTABELLO, Kamalesh KANAKARAJ, Zeeshan NAWAZ, Brian WALSH, Sameh K MOHAMED, Pierre-Yves VANDENBUSSCHE, Colm J RYAN, Walter KOLCH a Dirk FEY. Accurate prediction of kinase-substrate networks using knowledge graphs. \textit{PLoS Computational Biology}. Cambridge: PLoS, 2020, roč.~16, č.~12, s.~1-30. ISSN~1553-734X. Dostupné z: https://dx.doi.org/10.1371/journal.pcbi.1007578.

Podrobný výpis o publikaci