Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors

Tutkimustuotos: Lehtiartikkelivertaisarvioitu

Standard

Computational-experimental approach to drug-target interaction mapping : A case study on kinase inhibitors. / Cichonska, Anna; Ravikumar, Balaguru; Parri, Elina; Timonen, Sanna; Pahikkala, Tapio; Airola, Antti; Wennerberg, Krister; Rousu, Juho; Aittokallio, Tero.

julkaisussa: PLoS computational biology, Vuosikerta 13, Nro 8, e1005678, 01.08.2017, s. 1-28.

Tutkimustuotos: Lehtiartikkelivertaisarvioitu

Harvard

Cichonska, A, Ravikumar, B, Parri, E, Timonen, S, Pahikkala, T, Airola, A, Wennerberg, K, Rousu, J & Aittokallio, T 2017, 'Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors', PLoS computational biology, Vuosikerta. 13, Nro 8, e1005678, Sivut 1-28. https://doi.org/10.1371/journal.pcbi.1005678

APA

Vancouver

Author

Cichonska, Anna ; Ravikumar, Balaguru ; Parri, Elina ; Timonen, Sanna ; Pahikkala, Tapio ; Airola, Antti ; Wennerberg, Krister ; Rousu, Juho ; Aittokallio, Tero. / Computational-experimental approach to drug-target interaction mapping : A case study on kinase inhibitors. Julkaisussa: PLoS computational biology. 2017 ; Vuosikerta 13, Nro 8. Sivut 1-28.

Bibtex - Lataa

@article{48e3270044994179845da0cc87b2b821,
title = "Computational-experimental approach to drug-target interaction mapping: A case study on kinase inhibitors",
abstract = "Due to relatively high costs and labor required for experimental profiling of the full target space of chemical compounds, various machine learning models have been proposed as cost-effective means to advance this process in terms of predicting the most potent compound-target interactions for subsequent verification. However, most of the model predictions lack direct experimental validation in the laboratory, making their practical benefits for drug discovery or repurposing applications largely unknown. Here, we therefore introduce and carefully test a systematic computational-experimental framework for the prediction and pre-clinical verification of drug-target interactions using a well-established kernel-based regression algorithm as the prediction model. To evaluate its performance, we first predicted unmeasured binding affinities in a large-scale kinase inhibitor profiling study, and then experimentally tested 100 compound-kinase pairs. The relatively high correlation of 0.77 (p < 0.0001) between the predicted and measured bioactivities supports the potential of the model for filling the experimental gaps in existing compound-target interaction maps. Further, we subjected the model to a more challenging task of predicting target interactions for such a new candidate drug compound that lacks prior binding profile information. As a specific case study, we used tivozanib, an investigational VEGF receptor inhibitor with currently unknown off-target profile. Among 7 kinases with high predicted affinity, we experimentally validated 4 new off-targets of tivozanib, namely the Src-family kinases FRK and FYN A, the non-receptor tyrosine kinase ABL1, and the serine/threonine kinase SLK. Our sub-sequent experimental validation protocol effectively avoids any possible information leakage between the training and validation data, and therefore enables rigorous model validation for practical applications. These results demonstrate that the kernel-based modeling approach offers practical benefits for probing novel insights into the mode of action of investigational compounds, and for the identification of new target selectivities for drug repurposing applications.",
author = "Anna Cichonska and Balaguru Ravikumar and Elina Parri and Sanna Timonen and Tapio Pahikkala and Antti Airola and Krister Wennerberg and Juho Rousu and Tero Aittokallio",
year = "2017",
month = "8",
day = "1",
doi = "10.1371/journal.pcbi.1005678",
language = "English",
volume = "13",
pages = "1--28",
journal = "PLoS computational biology",
issn = "1553-734X",
publisher = "Public Library of Science",
number = "8",

}

RIS - Lataa

TY - JOUR

T1 - Computational-experimental approach to drug-target interaction mapping

T2 - A case study on kinase inhibitors

AU - Cichonska, Anna

AU - Ravikumar, Balaguru

AU - Parri, Elina

AU - Timonen, Sanna

AU - Pahikkala, Tapio

AU - Airola, Antti

AU - Wennerberg, Krister

AU - Rousu, Juho

AU - Aittokallio, Tero

PY - 2017/8/1

Y1 - 2017/8/1

N2 - Due to relatively high costs and labor required for experimental profiling of the full target space of chemical compounds, various machine learning models have been proposed as cost-effective means to advance this process in terms of predicting the most potent compound-target interactions for subsequent verification. However, most of the model predictions lack direct experimental validation in the laboratory, making their practical benefits for drug discovery or repurposing applications largely unknown. Here, we therefore introduce and carefully test a systematic computational-experimental framework for the prediction and pre-clinical verification of drug-target interactions using a well-established kernel-based regression algorithm as the prediction model. To evaluate its performance, we first predicted unmeasured binding affinities in a large-scale kinase inhibitor profiling study, and then experimentally tested 100 compound-kinase pairs. The relatively high correlation of 0.77 (p < 0.0001) between the predicted and measured bioactivities supports the potential of the model for filling the experimental gaps in existing compound-target interaction maps. Further, we subjected the model to a more challenging task of predicting target interactions for such a new candidate drug compound that lacks prior binding profile information. As a specific case study, we used tivozanib, an investigational VEGF receptor inhibitor with currently unknown off-target profile. Among 7 kinases with high predicted affinity, we experimentally validated 4 new off-targets of tivozanib, namely the Src-family kinases FRK and FYN A, the non-receptor tyrosine kinase ABL1, and the serine/threonine kinase SLK. Our sub-sequent experimental validation protocol effectively avoids any possible information leakage between the training and validation data, and therefore enables rigorous model validation for practical applications. These results demonstrate that the kernel-based modeling approach offers practical benefits for probing novel insights into the mode of action of investigational compounds, and for the identification of new target selectivities for drug repurposing applications.

AB - Due to relatively high costs and labor required for experimental profiling of the full target space of chemical compounds, various machine learning models have been proposed as cost-effective means to advance this process in terms of predicting the most potent compound-target interactions for subsequent verification. However, most of the model predictions lack direct experimental validation in the laboratory, making their practical benefits for drug discovery or repurposing applications largely unknown. Here, we therefore introduce and carefully test a systematic computational-experimental framework for the prediction and pre-clinical verification of drug-target interactions using a well-established kernel-based regression algorithm as the prediction model. To evaluate its performance, we first predicted unmeasured binding affinities in a large-scale kinase inhibitor profiling study, and then experimentally tested 100 compound-kinase pairs. The relatively high correlation of 0.77 (p < 0.0001) between the predicted and measured bioactivities supports the potential of the model for filling the experimental gaps in existing compound-target interaction maps. Further, we subjected the model to a more challenging task of predicting target interactions for such a new candidate drug compound that lacks prior binding profile information. As a specific case study, we used tivozanib, an investigational VEGF receptor inhibitor with currently unknown off-target profile. Among 7 kinases with high predicted affinity, we experimentally validated 4 new off-targets of tivozanib, namely the Src-family kinases FRK and FYN A, the non-receptor tyrosine kinase ABL1, and the serine/threonine kinase SLK. Our sub-sequent experimental validation protocol effectively avoids any possible information leakage between the training and validation data, and therefore enables rigorous model validation for practical applications. These results demonstrate that the kernel-based modeling approach offers practical benefits for probing novel insights into the mode of action of investigational compounds, and for the identification of new target selectivities for drug repurposing applications.

UR - http://www.scopus.com/inward/record.url?scp=85030618091&partnerID=8YFLogxK

U2 - 10.1371/journal.pcbi.1005678

DO - 10.1371/journal.pcbi.1005678

M3 - Article

VL - 13

SP - 1

EP - 28

JO - PLoS computational biology

JF - PLoS computational biology

SN - 1553-734X

IS - 8

M1 - e1005678

ER -

ID: 15875261