Comprehensive and Automated Linear Interaction Energy Based Binding-Affinity Prediction for Multifarious Cytochrome P450 Aromatase Inhibitors

Marc van Dijk, Antonius M Ter Laak, Jörg D Wichard, Luigi Capoferri, Nico P E Vermeulen, Daan P Geerke

Research output: Contribution to JournalArticleAcademicpeer-review

Abstract

Cytochrome P450 aromatase (CYP19A1) plays a key role in the development of estrogen dependent breast cancer, and aromatase inhibitors have been at the front line of treatment for the past three decades. The development of potent, selective and safer inhibitors is ongoing with in silico screening methods playing a more prominent role in the search for promising lead compounds in bioactivity-relevant chemical space. Here we present a set of comprehensive binding affinity prediction models for CYP19A1 using our automated Linear Interaction Energy (LIE) based workflow on a set of 132 putative and structurally diverse aromatase inhibitors obtained from a typical industrial screening study. We extended the workflow with machine learning methods to automatically cluster training and test compounds in order to maximize the number of explained compounds in one or more predictive LIE models. The method uses protein-ligand interaction profiles obtained from Molecular Dynamics (MD) trajectories to help model search and define the applicability domain of the resolved models. Our method was successful in accounting for 86% of the data set in 3 robust models that show high correlation between calculated and observed values for ligand-binding free energies (RMSE < 2.5 kJ mol(-1)), with good cross-validation statistics.

LanguageEnglish
Pages2294-2308
Number of pages15
JournalJournal of Chemical Information and Modeling
Volume57
Issue number9
DOIs
StatePublished - 25 Sep 2017

Fingerprint

Aromatase Inhibitors
Cytochrome P-450 Enzyme System
energy
interaction
workflow
Screening
Ligands
Lead compounds
Aromatase
learning method
Bioactivity
Free energy
Learning systems
Molecular dynamics
Estrogens
cancer
statistics
Trajectories
Statistics
Proteins

Keywords

  • Aromatase
  • Aromatase Inhibitors
  • Automation
  • Computational Biology
  • Ligands
  • Linear Models
  • Molecular Dynamics Simulation
  • Protein Binding
  • Protein Conformation
  • Thermodynamics
  • Journal Article

Cite this

@article{9214af7dd3104848a1e0281b9c65a70e,
title = "Comprehensive and Automated Linear Interaction Energy Based Binding-Affinity Prediction for Multifarious Cytochrome P450 Aromatase Inhibitors",
abstract = "Cytochrome P450 aromatase (CYP19A1) plays a key role in the development of estrogen dependent breast cancer, and aromatase inhibitors have been at the front line of treatment for the past three decades. The development of potent, selective and safer inhibitors is ongoing with in silico screening methods playing a more prominent role in the search for promising lead compounds in bioactivity-relevant chemical space. Here we present a set of comprehensive binding affinity prediction models for CYP19A1 using our automated Linear Interaction Energy (LIE) based workflow on a set of 132 putative and structurally diverse aromatase inhibitors obtained from a typical industrial screening study. We extended the workflow with machine learning methods to automatically cluster training and test compounds in order to maximize the number of explained compounds in one or more predictive LIE models. The method uses protein-ligand interaction profiles obtained from Molecular Dynamics (MD) trajectories to help model search and define the applicability domain of the resolved models. Our method was successful in accounting for 86{\%} of the data set in 3 robust models that show high correlation between calculated and observed values for ligand-binding free energies (RMSE < 2.5 kJ mol(-1)), with good cross-validation statistics.",
keywords = "Aromatase, Aromatase Inhibitors, Automation, Computational Biology, Ligands, Linear Models, Molecular Dynamics Simulation, Protein Binding, Protein Conformation, Thermodynamics, Journal Article",
author = "{van Dijk}, Marc and {Ter Laak}, {Antonius M} and Wichard, {J{\"o}rg D} and Luigi Capoferri and Vermeulen, {Nico P E} and Geerke, {Daan P}",
year = "2017",
month = "9",
day = "25",
doi = "10.1021/acs.jcim.7b00222",
language = "English",
volume = "57",
pages = "2294--2308",
journal = "Journal of Chemical Information and Modeling",
issn = "1549-9596",
publisher = "American Chemical Society",
number = "9",

}

Comprehensive and Automated Linear Interaction Energy Based Binding-Affinity Prediction for Multifarious Cytochrome P450 Aromatase Inhibitors. / van Dijk, Marc; Ter Laak, Antonius M; Wichard, Jörg D; Capoferri, Luigi; Vermeulen, Nico P E; Geerke, Daan P.

In: Journal of Chemical Information and Modeling, Vol. 57, No. 9, 25.09.2017, p. 2294-2308.

Research output: Contribution to JournalArticleAcademicpeer-review

TY - JOUR

T1 - Comprehensive and Automated Linear Interaction Energy Based Binding-Affinity Prediction for Multifarious Cytochrome P450 Aromatase Inhibitors

AU - van Dijk,Marc

AU - Ter Laak,Antonius M

AU - Wichard,Jörg D

AU - Capoferri,Luigi

AU - Vermeulen,Nico P E

AU - Geerke,Daan P

PY - 2017/9/25

Y1 - 2017/9/25

N2 - Cytochrome P450 aromatase (CYP19A1) plays a key role in the development of estrogen dependent breast cancer, and aromatase inhibitors have been at the front line of treatment for the past three decades. The development of potent, selective and safer inhibitors is ongoing with in silico screening methods playing a more prominent role in the search for promising lead compounds in bioactivity-relevant chemical space. Here we present a set of comprehensive binding affinity prediction models for CYP19A1 using our automated Linear Interaction Energy (LIE) based workflow on a set of 132 putative and structurally diverse aromatase inhibitors obtained from a typical industrial screening study. We extended the workflow with machine learning methods to automatically cluster training and test compounds in order to maximize the number of explained compounds in one or more predictive LIE models. The method uses protein-ligand interaction profiles obtained from Molecular Dynamics (MD) trajectories to help model search and define the applicability domain of the resolved models. Our method was successful in accounting for 86% of the data set in 3 robust models that show high correlation between calculated and observed values for ligand-binding free energies (RMSE < 2.5 kJ mol(-1)), with good cross-validation statistics.

AB - Cytochrome P450 aromatase (CYP19A1) plays a key role in the development of estrogen dependent breast cancer, and aromatase inhibitors have been at the front line of treatment for the past three decades. The development of potent, selective and safer inhibitors is ongoing with in silico screening methods playing a more prominent role in the search for promising lead compounds in bioactivity-relevant chemical space. Here we present a set of comprehensive binding affinity prediction models for CYP19A1 using our automated Linear Interaction Energy (LIE) based workflow on a set of 132 putative and structurally diverse aromatase inhibitors obtained from a typical industrial screening study. We extended the workflow with machine learning methods to automatically cluster training and test compounds in order to maximize the number of explained compounds in one or more predictive LIE models. The method uses protein-ligand interaction profiles obtained from Molecular Dynamics (MD) trajectories to help model search and define the applicability domain of the resolved models. Our method was successful in accounting for 86% of the data set in 3 robust models that show high correlation between calculated and observed values for ligand-binding free energies (RMSE < 2.5 kJ mol(-1)), with good cross-validation statistics.

KW - Aromatase

KW - Aromatase Inhibitors

KW - Automation

KW - Computational Biology

KW - Ligands

KW - Linear Models

KW - Molecular Dynamics Simulation

KW - Protein Binding

KW - Protein Conformation

KW - Thermodynamics

KW - Journal Article

U2 - 10.1021/acs.jcim.7b00222

DO - 10.1021/acs.jcim.7b00222

M3 - Article

VL - 57

SP - 2294

EP - 2308

JO - Journal of Chemical Information and Modeling

T2 - Journal of Chemical Information and Modeling

JF - Journal of Chemical Information and Modeling

SN - 1549-9596

IS - 9

ER -