Chemoinformatics profiling of ionic liquids: automatic and chemically interpretable cytotoxicity profiling, virtual screening and cytotoxicophore identification

Maykel C Monteagudo, Evys Ancede-Gallardo, Miguel Jorge, M. Natalia D. S. Cordeiro

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Ionic liquids (ILs) possess a unique physicochemical profile providing a wide range of applications. Their almost limitless structural possibilities allow the design of task-specific ILs. However, their “greenness,” specifically their claimed relative nontoxicity has been frequently questioned, hindering their REACH registration processes and, so, their final application. Because the vast majority of ILs is yet to be synthesized, the development of chemoinformatics tools efficiently profiling their hazardous potential becomes essential. In this work, we introduce a reliable, predictive, simple, and chemically interpretable Classification and Regression Trees (CART) classifier, enabling the prioritization of ILs with a favorable cytotoxicity profile. Besides a good predictive capability (81% or 75% or 83% of accuracy or sensitivity or specificity in an external evaluation set), the other salient feature of the proposed cytotoxicity CART classifier is their simplicity and transparent chemical interpretation based on structural molecular fragments. The essentials of the current structure-cytotoxicity relationships of ILs are faithfully reproduced by this model, supporting its biophysical relevance and the reliability of the resultant predictions. By inspecting the structure of the CART, several moieties that can be regarded as “cytotoxicophores” were identified and used to establish a set of SAR trends specifically aimed to prioritize low-cytotoxicity ILs. Finally, we demonstrated the suitability of the joint use of the CART classifier and a group fusion similarity search as a virtual screening strategy for the automatic prioritization of safe ILs disperse in a data set of ILs of moderate to very high cytotoxicity.
LanguageEnglish
Pages548-565
Number of pages18
JournalToxicological Sciences
Volume136
Issue number2
Early online date25 Sep 2013
DOIs
Publication statusPublished - 2013

Fingerprint

Ionic Liquids
Cytotoxicity
Screening
Classifiers
Fusion reactions
Joints
Sensitivity and Specificity

Keywords

  • chemoinformatics
  • cytotoxicophores
  • Ionic liquids
  • IPC-81 cytotoxicity
  • structure-cytotoxicity relationships
  • virtual screening

Cite this

@article{f0b3888891f444f09137b78eb42e96e2,
title = "Chemoinformatics profiling of ionic liquids: automatic and chemically interpretable cytotoxicity profiling, virtual screening and cytotoxicophore identification",
abstract = "Ionic liquids (ILs) possess a unique physicochemical profile providing a wide range of applications. Their almost limitless structural possibilities allow the design of task-specific ILs. However, their “greenness,” specifically their claimed relative nontoxicity has been frequently questioned, hindering their REACH registration processes and, so, their final application. Because the vast majority of ILs is yet to be synthesized, the development of chemoinformatics tools efficiently profiling their hazardous potential becomes essential. In this work, we introduce a reliable, predictive, simple, and chemically interpretable Classification and Regression Trees (CART) classifier, enabling the prioritization of ILs with a favorable cytotoxicity profile. Besides a good predictive capability (81{\%} or 75{\%} or 83{\%} of accuracy or sensitivity or specificity in an external evaluation set), the other salient feature of the proposed cytotoxicity CART classifier is their simplicity and transparent chemical interpretation based on structural molecular fragments. The essentials of the current structure-cytotoxicity relationships of ILs are faithfully reproduced by this model, supporting its biophysical relevance and the reliability of the resultant predictions. By inspecting the structure of the CART, several moieties that can be regarded as “cytotoxicophores” were identified and used to establish a set of SAR trends specifically aimed to prioritize low-cytotoxicity ILs. Finally, we demonstrated the suitability of the joint use of the CART classifier and a group fusion similarity search as a virtual screening strategy for the automatic prioritization of safe ILs disperse in a data set of ILs of moderate to very high cytotoxicity.",
keywords = "chemoinformatics, cytotoxicophores , Ionic liquids, IPC-81 cytotoxicity, structure-cytotoxicity relationships, virtual screening",
author = "Monteagudo, {Maykel C} and Evys Ancede-Gallardo and Miguel Jorge and {D. S. Cordeiro}, {M. Natalia}",
year = "2013",
doi = "10.1093/toxsci/kft209",
language = "English",
volume = "136",
pages = "548--565",
journal = "Toxicological Sciences",
issn = "1096-6080",
number = "2",

}

Chemoinformatics profiling of ionic liquids : automatic and chemically interpretable cytotoxicity profiling, virtual screening and cytotoxicophore identification. / Monteagudo, Maykel C; Ancede-Gallardo, Evys; Jorge, Miguel; D. S. Cordeiro, M. Natalia.

In: Toxicological Sciences, Vol. 136, No. 2, 2013, p. 548-565.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Chemoinformatics profiling of ionic liquids

T2 - Toxicological Sciences

AU - Monteagudo, Maykel C

AU - Ancede-Gallardo, Evys

AU - Jorge, Miguel

AU - D. S. Cordeiro, M. Natalia

PY - 2013

Y1 - 2013

N2 - Ionic liquids (ILs) possess a unique physicochemical profile providing a wide range of applications. Their almost limitless structural possibilities allow the design of task-specific ILs. However, their “greenness,” specifically their claimed relative nontoxicity has been frequently questioned, hindering their REACH registration processes and, so, their final application. Because the vast majority of ILs is yet to be synthesized, the development of chemoinformatics tools efficiently profiling their hazardous potential becomes essential. In this work, we introduce a reliable, predictive, simple, and chemically interpretable Classification and Regression Trees (CART) classifier, enabling the prioritization of ILs with a favorable cytotoxicity profile. Besides a good predictive capability (81% or 75% or 83% of accuracy or sensitivity or specificity in an external evaluation set), the other salient feature of the proposed cytotoxicity CART classifier is their simplicity and transparent chemical interpretation based on structural molecular fragments. The essentials of the current structure-cytotoxicity relationships of ILs are faithfully reproduced by this model, supporting its biophysical relevance and the reliability of the resultant predictions. By inspecting the structure of the CART, several moieties that can be regarded as “cytotoxicophores” were identified and used to establish a set of SAR trends specifically aimed to prioritize low-cytotoxicity ILs. Finally, we demonstrated the suitability of the joint use of the CART classifier and a group fusion similarity search as a virtual screening strategy for the automatic prioritization of safe ILs disperse in a data set of ILs of moderate to very high cytotoxicity.

AB - Ionic liquids (ILs) possess a unique physicochemical profile providing a wide range of applications. Their almost limitless structural possibilities allow the design of task-specific ILs. However, their “greenness,” specifically their claimed relative nontoxicity has been frequently questioned, hindering their REACH registration processes and, so, their final application. Because the vast majority of ILs is yet to be synthesized, the development of chemoinformatics tools efficiently profiling their hazardous potential becomes essential. In this work, we introduce a reliable, predictive, simple, and chemically interpretable Classification and Regression Trees (CART) classifier, enabling the prioritization of ILs with a favorable cytotoxicity profile. Besides a good predictive capability (81% or 75% or 83% of accuracy or sensitivity or specificity in an external evaluation set), the other salient feature of the proposed cytotoxicity CART classifier is their simplicity and transparent chemical interpretation based on structural molecular fragments. The essentials of the current structure-cytotoxicity relationships of ILs are faithfully reproduced by this model, supporting its biophysical relevance and the reliability of the resultant predictions. By inspecting the structure of the CART, several moieties that can be regarded as “cytotoxicophores” were identified and used to establish a set of SAR trends specifically aimed to prioritize low-cytotoxicity ILs. Finally, we demonstrated the suitability of the joint use of the CART classifier and a group fusion similarity search as a virtual screening strategy for the automatic prioritization of safe ILs disperse in a data set of ILs of moderate to very high cytotoxicity.

KW - chemoinformatics

KW - cytotoxicophores

KW - Ionic liquids

KW - IPC-81 cytotoxicity

KW - structure-cytotoxicity relationships

KW - virtual screening

UR - http://toxsci.oxfordjournals.org/

U2 - 10.1093/toxsci/kft209

DO - 10.1093/toxsci/kft209

M3 - Article

VL - 136

SP - 548

EP - 565

JO - Toxicological Sciences

JF - Toxicological Sciences

SN - 1096-6080

IS - 2

ER -