eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates
Abstract Background The efficiency of drug development defined as a number of successfully launched new pharmaceuticals normalized by financial investments has significantly declined. Nonetheless, recent advances in high-throughput experimental techniques and computational modeling promise reduction...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2019-01-01
|
Series: | BMC Pharmacology and Toxicology |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s40360-018-0282-6 |
id |
doaj-0bb75d97851c4fcd9b6f9ba5dde95ad3 |
---|---|
record_format |
Article |
spelling |
doaj-0bb75d97851c4fcd9b6f9ba5dde95ad32020-11-25T02:04:01ZengBMCBMC Pharmacology and Toxicology2050-65112019-01-0120111510.1186/s40360-018-0282-6eToxPred: a machine learning-based approach to estimate the toxicity of drug candidatesLimeng Pu0Misagh Naderi1Tairan Liu2Hsiao-Chun Wu3Supratik Mukhopadhyay4Michal Brylinski5Division of Electrical & Computer Engineering, Louisiana State UniversityDepartment of Biological Sciences, Louisiana State UniversityDepartment of Mechanical Engineering, Louisiana State UniversityDivision of Electrical & Computer Engineering, Louisiana State UniversityDepartment of Computer Science, Louisiana State UniversityDepartment of Biological Sciences, Louisiana State UniversityAbstract Background The efficiency of drug development defined as a number of successfully launched new pharmaceuticals normalized by financial investments has significantly declined. Nonetheless, recent advances in high-throughput experimental techniques and computational modeling promise reductions in the costs and development times required to bring new drugs to market. The prediction of toxicity of drug candidates is one of the important components of modern drug discovery. Results In this work, we describe eToxPred, a new approach to reliably estimate the toxicity and synthetic accessibility of small organic compounds. eToxPred employs machine learning algorithms trained on molecular fingerprints to evaluate drug candidates. The performance is assessed against multiple datasets containing known drugs, potentially hazardous chemicals, natural products, and synthetic bioactive compounds. Encouragingly, eToxPred predicts the synthetic accessibility with the mean square error of only 4% and the toxicity with the accuracy of as high as 72%. Conclusions eToxPred can be incorporated into protocols to construct custom libraries for virtual screening in order to filter out those drug candidates that are potentially toxic or would be difficult to synthesize. It is freely available as a stand-alone software at https://github.com/pulimeng/etoxpred.http://link.springer.com/article/10.1186/s40360-018-0282-6Virtual screeningSynthetic accessibilityToxicityMachine learningDeep belief networkExtremely randomized trees |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Limeng Pu Misagh Naderi Tairan Liu Hsiao-Chun Wu Supratik Mukhopadhyay Michal Brylinski |
spellingShingle |
Limeng Pu Misagh Naderi Tairan Liu Hsiao-Chun Wu Supratik Mukhopadhyay Michal Brylinski eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates BMC Pharmacology and Toxicology Virtual screening Synthetic accessibility Toxicity Machine learning Deep belief network Extremely randomized trees |
author_facet |
Limeng Pu Misagh Naderi Tairan Liu Hsiao-Chun Wu Supratik Mukhopadhyay Michal Brylinski |
author_sort |
Limeng Pu |
title |
eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates |
title_short |
eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates |
title_full |
eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates |
title_fullStr |
eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates |
title_full_unstemmed |
eToxPred: a machine learning-based approach to estimate the toxicity of drug candidates |
title_sort |
etoxpred: a machine learning-based approach to estimate the toxicity of drug candidates |
publisher |
BMC |
series |
BMC Pharmacology and Toxicology |
issn |
2050-6511 |
publishDate |
2019-01-01 |
description |
Abstract Background The efficiency of drug development defined as a number of successfully launched new pharmaceuticals normalized by financial investments has significantly declined. Nonetheless, recent advances in high-throughput experimental techniques and computational modeling promise reductions in the costs and development times required to bring new drugs to market. The prediction of toxicity of drug candidates is one of the important components of modern drug discovery. Results In this work, we describe eToxPred, a new approach to reliably estimate the toxicity and synthetic accessibility of small organic compounds. eToxPred employs machine learning algorithms trained on molecular fingerprints to evaluate drug candidates. The performance is assessed against multiple datasets containing known drugs, potentially hazardous chemicals, natural products, and synthetic bioactive compounds. Encouragingly, eToxPred predicts the synthetic accessibility with the mean square error of only 4% and the toxicity with the accuracy of as high as 72%. Conclusions eToxPred can be incorporated into protocols to construct custom libraries for virtual screening in order to filter out those drug candidates that are potentially toxic or would be difficult to synthesize. It is freely available as a stand-alone software at https://github.com/pulimeng/etoxpred. |
topic |
Virtual screening Synthetic accessibility Toxicity Machine learning Deep belief network Extremely randomized trees |
url |
http://link.springer.com/article/10.1186/s40360-018-0282-6 |
work_keys_str_mv |
AT limengpu etoxpredamachinelearningbasedapproachtoestimatethetoxicityofdrugcandidates AT misaghnaderi etoxpredamachinelearningbasedapproachtoestimatethetoxicityofdrugcandidates AT tairanliu etoxpredamachinelearningbasedapproachtoestimatethetoxicityofdrugcandidates AT hsiaochunwu etoxpredamachinelearningbasedapproachtoestimatethetoxicityofdrugcandidates AT supratikmukhopadhyay etoxpredamachinelearningbasedapproachtoestimatethetoxicityofdrugcandidates AT michalbrylinski etoxpredamachinelearningbasedapproachtoestimatethetoxicityofdrugcandidates |
_version_ |
1724945099535679488 |