DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation

Carcinogenicity testing plays an essential role in identifying carcinogens in environmental chemistry and drug development. However, it is a time-consuming and label-intensive process to evaluate the carcinogenic potency with conventional 2-years rodent animal studies. Thus, there is an urgent need...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ting Li, Weida Tong, Ruth Roberts, Zhichao Liu, Shraddha Thakkar
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	carcinogenicity deep learning QSAR non-animal models NCTRlcdb Electronic computers. Computer science QA75.5-76.95
Acceso en línea:	https://doaj.org/article/a33432a4df954daaa489eac9d7c120ba
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:a33432a4df954daaa489eac9d7c120ba
record_format	dspace
spelling	oai:doaj.org-article:a33432a4df954daaa489eac9d7c120ba2021-11-18T06:52:46ZDeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation2624-821210.3389/frai.2021.757780https://doaj.org/article/a33432a4df954daaa489eac9d7c120ba2021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/frai.2021.757780/fullhttps://doaj.org/toc/2624-8212Carcinogenicity testing plays an essential role in identifying carcinogens in environmental chemistry and drug development. However, it is a time-consuming and label-intensive process to evaluate the carcinogenic potency with conventional 2-years rodent animal studies. Thus, there is an urgent need for alternative approaches to providing reliable and robust assessments on carcinogenicity. In this study, we proposed a DeepCarc model to predict carcinogenicity for small molecules using deep learning-based model-level representations. The DeepCarc Model was developed using a data set of 692 compounds and evaluated on a test set containing 171 compounds in the National Center for Toxicological Research liver cancer database (NCTRlcdb). As a result, the proposed DeepCarc model yielded a Matthews correlation coefficient (MCC) of 0.432 for the test set, outperforming four advanced deep learning (DL) powered quantitative structure-activity relationship (QSAR) models with an average improvement rate of 37%. Furthermore, the DeepCarc model was also employed to screen the carcinogenicity potential of the compounds from both DrugBank and Tox21. Altogether, the proposed DeepCarc model could serve as an early detection tool (https://github.com/TingLi2016/DeepCarc) for carcinogenicity assessment.Ting LiTing LiWeida TongRuth RobertsRuth RobertsZhichao LiuShraddha ThakkarFrontiers Media S.A.articlecarcinogenicitydeep learningQSARnon-animal modelsNCTRlcdbElectronic computers. Computer scienceQA75.5-76.95ENFrontiers in Artificial Intelligence, Vol 4 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	carcinogenicity deep learning QSAR non-animal models NCTRlcdb Electronic computers. Computer science QA75.5-76.95
spellingShingle	carcinogenicity deep learning QSAR non-animal models NCTRlcdb Electronic computers. Computer science QA75.5-76.95 Ting Li Ting Li Weida Tong Ruth Roberts Ruth Roberts Zhichao Liu Shraddha Thakkar DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation
description	Carcinogenicity testing plays an essential role in identifying carcinogens in environmental chemistry and drug development. However, it is a time-consuming and label-intensive process to evaluate the carcinogenic potency with conventional 2-years rodent animal studies. Thus, there is an urgent need for alternative approaches to providing reliable and robust assessments on carcinogenicity. In this study, we proposed a DeepCarc model to predict carcinogenicity for small molecules using deep learning-based model-level representations. The DeepCarc Model was developed using a data set of 692 compounds and evaluated on a test set containing 171 compounds in the National Center for Toxicological Research liver cancer database (NCTRlcdb). As a result, the proposed DeepCarc model yielded a Matthews correlation coefficient (MCC) of 0.432 for the test set, outperforming four advanced deep learning (DL) powered quantitative structure-activity relationship (QSAR) models with an average improvement rate of 37%. Furthermore, the DeepCarc model was also employed to screen the carcinogenicity potential of the compounds from both DrugBank and Tox21. Altogether, the proposed DeepCarc model could serve as an early detection tool (https://github.com/TingLi2016/DeepCarc) for carcinogenicity assessment.
format	article
author	Ting Li Ting Li Weida Tong Ruth Roberts Ruth Roberts Zhichao Liu Shraddha Thakkar
author_facet	Ting Li Ting Li Weida Tong Ruth Roberts Ruth Roberts Zhichao Liu Shraddha Thakkar
author_sort	Ting Li
title	DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation
title_short	DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation
title_full	DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation
title_fullStr	DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation
title_full_unstemmed	DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation
title_sort	deepcarc: deep learning-powered carcinogenicity prediction using model-level representation
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/a33432a4df954daaa489eac9d7c120ba
work_keys_str_mv	AT tingli deepcarcdeeplearningpoweredcarcinogenicitypredictionusingmodellevelrepresentation AT tingli deepcarcdeeplearningpoweredcarcinogenicitypredictionusingmodellevelrepresentation AT weidatong deepcarcdeeplearningpoweredcarcinogenicitypredictionusingmodellevelrepresentation AT ruthroberts deepcarcdeeplearningpoweredcarcinogenicitypredictionusingmodellevelrepresentation AT ruthroberts deepcarcdeeplearningpoweredcarcinogenicitypredictionusingmodellevelrepresentation AT zhichaoliu deepcarcdeeplearningpoweredcarcinogenicitypredictionusingmodellevelrepresentation AT shraddhathakkar deepcarcdeeplearningpoweredcarcinogenicitypredictionusingmodellevelrepresentation
_version_	1718424244870709248

DeepCarc: Deep Learning-Powered Carcinogenicity Prediction Using Model-Level Representation

Ejemplares similares