TY - JOUR
T1 - A Perspective and a New Integrated Computational Strategy for Skin Sensitization Assessment
AU - Alves, Vinicius M.
AU - Capuzzi, Stephen J.
AU - Braga, Rodolpho C.
AU - Borba, Joyce V.B.
AU - Silva, Arthur C.
AU - Luechtefeld, Thomas
AU - Hartung, Thomas
AU - Andrade, Carolina Horta
AU - Muratov, Eugene N.
AU - Tropsha, Alexander
N1 - Funding Information:
This study was supported in part by NIH (Grant 1U01CA207160) and CNPq (Grant 400760/2014-2). J.V.B.B. and A.C.S. thank CAPES for Ph.D. scholarships. S.J.C. thanks the organizers of the 22nd Annual Green Chemistry & Engineering Conference.
Funding Information:
This study was supported in part by NIH (Grant 1U01CA207160) and CNPq (Grant 400760/2014-2). J.V.B.B. and A.C.S. thank CAPES for Ph.D. scholarships.
Funding Information:
Alexander Tropsha, PhD. is a K.H. Lee Distinguished Professor and associate dean for Pharmacoinformatics and Data Science at the UNC Eshelman School of Pharmacy, University of North Carolina−Chapel Hill. Prof. Tropsha obtained his Ph.D. in Chemical Enzymology in 1986 from Moscow State University, Russia, and came to University of North Carolina−Chapel Hill in 1989 as a postdoctoral fellow. He joined the School of Pharmacy in 1991 as an assistant professor and became full professor in 2002. His research interests are in the areas of computer-assisted drug design, computational toxicology, cheminformatics, (nano)materials informatics, and structural bioinformatics. He has authored or co-authored more than 200 peer-reviewed research papers, reviews, and book chapters, and co-edited two monographs. He is an associate editor of the ACS Journal of Chemical Information and Modeling. His research has been supported by multiple grants from the NIH, NSF, EPA, DOD, and private companies.
Publisher Copyright:
Copyright © 2018 American Chemical Society.
PY - 2018/3/5
Y1 - 2018/3/5
N2 - Traditionally, the skin sensitization potential of chemicals has been assessed using animal models. Due to growing ethical, political, and financial concerns, sustainable alternatives to animal testing need to be developed. As publicly available skin sensitization data continues to grow, computational approaches, such as alert-based systems, read-across, and QSAR models, are expected to reduce or replace animal testing for the prediction of human skin sensitization potential. Herein, we discuss current computational approaches to predicting skin sensitization and provide future perspectives of the field. As a proof-of-concept study, we have compiled the largest skin sensitization data set in the public domain and benchmarked several methods for building skin sensitization models. We propose a new comprehensive approach, which integrates multiple QSAR models developed with in vitro, in chemico, animal, and human data, and a Naive Bayes model for predicting human skin sensitization. Both the data sets and the KNIME implementation of the model allowing skin sensitization prediction for molecules of interest have been made freely available.
AB - Traditionally, the skin sensitization potential of chemicals has been assessed using animal models. Due to growing ethical, political, and financial concerns, sustainable alternatives to animal testing need to be developed. As publicly available skin sensitization data continues to grow, computational approaches, such as alert-based systems, read-across, and QSAR models, are expected to reduce or replace animal testing for the prediction of human skin sensitization potential. Herein, we discuss current computational approaches to predicting skin sensitization and provide future perspectives of the field. As a proof-of-concept study, we have compiled the largest skin sensitization data set in the public domain and benchmarked several methods for building skin sensitization models. We propose a new comprehensive approach, which integrates multiple QSAR models developed with in vitro, in chemico, animal, and human data, and a Naive Bayes model for predicting human skin sensitization. Both the data sets and the KNIME implementation of the model allowing skin sensitization prediction for molecules of interest have been made freely available.
KW - Alternative methods
KW - Naïve Bayes
KW - QSAR
KW - Skin sensitization
UR - http://www.scopus.com/inward/record.url?scp=85043249013&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85043249013&partnerID=8YFLogxK
U2 - 10.1021/acssuschemeng.7b04220
DO - 10.1021/acssuschemeng.7b04220
M3 - Review article
AN - SCOPUS:85043249013
SN - 2168-0485
VL - 6
SP - 2845
EP - 2859
JO - ACS Sustainable Chemistry and Engineering
JF - ACS Sustainable Chemistry and Engineering
IS - 3
ER -