Combined Ensemble Docking and Machine Learning in Identification of Therapeutic Agents with Potential Inhibitory Effect on Human CES1

Eliane Briand; Ragnar Thomsen; Kristian Linnet; Henrik Berg Rasmussen; Søren Brunak; Olivier Taboureau

doi:10.3390/molecules24152747

Combined Ensemble Docking and Machine Learning in Identification of Therapeutic Agents with Potential Inhibitory Effect on Human CES1

Eliane Briand, Ragnar Thomsen, Kristian Linnet, Henrik Berg Rasmussen, Søren Brunak, Olivier Taboureau^*

^*Corresponding author af dette arbejde

1 Citationer (Scopus)

26 Downloads (Pure)

Abstract

The human carboxylesterase 1 (CES1), responsible for the biotransformation of many diverse therapeutic agents, may contribute to the occurrence of adverse drug reactions and therapeutic failure through drug interactions. The present study is designed to address the issue of potential drug interactions resulting from the inhibition of CES1. Based on an ensemble of 10 crystal structures complexed with different ligands and a set of 294 known CES1 ligands, we used docking (Autodock Vina) and machine learning methodologies (LDA, QDA and multilayer perceptron), considering the different energy terms from the scoring function to assess the best combination to enable the identification of CES1 inhibitors. The protocol was then applied on a library of 1114 FDA-approved drugs and eight drugs were selected for in vitro CES1 inhibition. An inhibition effect was observed for diltiazem (IC50 = 13.9 µM). Three others drugs (benztropine, iloprost and treprostinil), exhibited a weak CES1 inhibitory effects with IC50 values of 298.2 µM, 366.8 µM and 391.6 µM respectively. In conclusion, the binding site of CES1 is relatively flexible and can adapt its conformation to different types of ligands. Combining ensemble docking and machine learning approaches improves the prediction of CES1 inhibitors compared to a docking study using only one crystal structure.

Originalsprog	Engelsk
Tidsskrift	Molecules
Vol/bind	24
Udgave nummer	15
Antal sider	17
ISSN	1420-3049
DOI	https://doi.org/10.3390/molecules24152747
Status	Udgivet - 29 jul. 2019

Adgang til dokumentet

10.3390/molecules24152747

Combined Ensemble Docking and Machine Learning in Identification of Therapeutic Agents with Potential Inhibitory Effect on Human CES1 Forlagets udgivne version, 5,35 MB

Citationsformater

@article{7122027457254b9ab8ed6a96768c7cf2,

title = "Combined Ensemble Docking and Machine Learning in Identification of Therapeutic Agents with Potential Inhibitory Effect on Human CES1",

abstract = "The human carboxylesterase 1 (CES1), responsible for the biotransformation of many diverse therapeutic agents, may contribute to the occurrence of adverse drug reactions and therapeutic failure through drug interactions. The present study is designed to address the issue of potential drug interactions resulting from the inhibition of CES1. Based on an ensemble of 10 crystal structures complexed with different ligands and a set of 294 known CES1 ligands, we used docking (Autodock Vina) and machine learning methodologies (LDA, QDA and multilayer perceptron), considering the different energy terms from the scoring function to assess the best combination to enable the identification of CES1 inhibitors. The protocol was then applied on a library of 1114 FDA-approved drugs and eight drugs were selected for in vitro CES1 inhibition. An inhibition effect was observed for diltiazem (IC50 = 13.9 µM). Three others drugs (benztropine, iloprost and treprostinil), exhibited a weak CES1 inhibitory effects with IC50 values of 298.2 µM, 366.8 µM and 391.6 µM respectively. In conclusion, the binding site of CES1 is relatively flexible and can adapt its conformation to different types of ligands. Combining ensemble docking and machine learning approaches improves the prediction of CES1 inhibitors compared to a docking study using only one crystal structure.",

author = "Eliane Briand and Ragnar Thomsen and Kristian Linnet and Rasmussen, {Henrik Berg} and S{\o}ren Brunak and Olivier Taboureau",

year = "2019",

month = jul,

day = "29",

doi = "10.3390/molecules24152747",

language = "English",

volume = "24",

journal = "Molecules",

issn = "1420-3049",

publisher = "M D P I AG",

number = "15",

}

TY - JOUR

T1 - Combined Ensemble Docking and Machine Learning in Identification of Therapeutic Agents with Potential Inhibitory Effect on Human CES1

AU - Briand, Eliane

AU - Thomsen, Ragnar

AU - Linnet, Kristian

AU - Rasmussen, Henrik Berg

AU - Brunak, Søren

AU - Taboureau, Olivier

PY - 2019/7/29

Y1 - 2019/7/29

N2 - The human carboxylesterase 1 (CES1), responsible for the biotransformation of many diverse therapeutic agents, may contribute to the occurrence of adverse drug reactions and therapeutic failure through drug interactions. The present study is designed to address the issue of potential drug interactions resulting from the inhibition of CES1. Based on an ensemble of 10 crystal structures complexed with different ligands and a set of 294 known CES1 ligands, we used docking (Autodock Vina) and machine learning methodologies (LDA, QDA and multilayer perceptron), considering the different energy terms from the scoring function to assess the best combination to enable the identification of CES1 inhibitors. The protocol was then applied on a library of 1114 FDA-approved drugs and eight drugs were selected for in vitro CES1 inhibition. An inhibition effect was observed for diltiazem (IC50 = 13.9 µM). Three others drugs (benztropine, iloprost and treprostinil), exhibited a weak CES1 inhibitory effects with IC50 values of 298.2 µM, 366.8 µM and 391.6 µM respectively. In conclusion, the binding site of CES1 is relatively flexible and can adapt its conformation to different types of ligands. Combining ensemble docking and machine learning approaches improves the prediction of CES1 inhibitors compared to a docking study using only one crystal structure.

AB - The human carboxylesterase 1 (CES1), responsible for the biotransformation of many diverse therapeutic agents, may contribute to the occurrence of adverse drug reactions and therapeutic failure through drug interactions. The present study is designed to address the issue of potential drug interactions resulting from the inhibition of CES1. Based on an ensemble of 10 crystal structures complexed with different ligands and a set of 294 known CES1 ligands, we used docking (Autodock Vina) and machine learning methodologies (LDA, QDA and multilayer perceptron), considering the different energy terms from the scoring function to assess the best combination to enable the identification of CES1 inhibitors. The protocol was then applied on a library of 1114 FDA-approved drugs and eight drugs were selected for in vitro CES1 inhibition. An inhibition effect was observed for diltiazem (IC50 = 13.9 µM). Three others drugs (benztropine, iloprost and treprostinil), exhibited a weak CES1 inhibitory effects with IC50 values of 298.2 µM, 366.8 µM and 391.6 µM respectively. In conclusion, the binding site of CES1 is relatively flexible and can adapt its conformation to different types of ligands. Combining ensemble docking and machine learning approaches improves the prediction of CES1 inhibitors compared to a docking study using only one crystal structure.

U2 - 10.3390/molecules24152747

DO - 10.3390/molecules24152747

M3 - Journal article

C2 - 31362390

SN - 1420-3049

VL - 24

JO - Molecules

JF - Molecules

IS - 15

ER -

Combined Ensemble Docking and Machine Learning in Identification of Therapeutic Agents with Potential Inhibitory Effect on Human CES1

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater