TY - JOUR
T1 - Machine-learning based prediction models for assessing skin irritation and corrosion potential of liquid chemicals using physicochemical properties by XGBoost
AU - Kang, Yeonsoo
AU - Kim, Myeong Gyu
AU - Lim, Kyung Min
N1 - Funding Information:
This study was Cosmetic safety evaluation project carried out by the Korea Cosmetic Industry Institute (KCII) funded by the Ministry of Health and Welfare and the Korea Environment Industry and Technology Institute (KEITI) funded by Korea Ministry of Environment (MOE) (2021002970001, 1485017976).
Funding Information:
Funding was provided by Ministry of Environment (KR) (KEITI 2021002970001, 1485017976), and Ministry of Health and Welfare (KR) through the Korea Cosmetic Industry Institute (KCII).
Publisher Copyright:
© 2023, The Author(s) under exclusive licence to Korean Society of Toxicology.
PY - 2023/4
Y1 - 2023/4
N2 - Skin irritation test is an essential part of the safety assessment of chemicals. Recently, computational models to predict the skin irritation draw attention as alternatives to animal testing. We developed prediction models on skin irritation/corrosion of liquid chemicals using machine learning algorithms, with 34 physicochemical descriptors calculated from the structure. The training and test dataset of 545 liquid chemicals with reliable in vivo skin hazard classifications based on UN Globally Harmonized System [category 1 (corrosive, Cat 1), 2 (irritant, Cat 2), 3 (mild irritant, Cat 3), and no category (nonirritant, NC)] were collected from public databases. After the curation of input data through removal and correlation analysis, every model was constructed to predict skin hazard classification for liquid chemicals with 22 physicochemical descriptors. Seven machine learning algorithms [Logistic regression, Naïve Bayes, k-nearest neighbor, Support vector machine, Random Forest, Extreme gradient boosting (XGB), and Neural net] were applied to ternary and binary classification of skin hazard. XGB model demonstrated the highest accuracy (0.73–0.81), sensitivity (0.71–0.92), and positive predictive value (0.65–0.81). The contribution of physicochemical descriptors to the classification was analyzed using Shapley Additive exPlanations plot to provide an insight into the skin irritation of chemicals.
AB - Skin irritation test is an essential part of the safety assessment of chemicals. Recently, computational models to predict the skin irritation draw attention as alternatives to animal testing. We developed prediction models on skin irritation/corrosion of liquid chemicals using machine learning algorithms, with 34 physicochemical descriptors calculated from the structure. The training and test dataset of 545 liquid chemicals with reliable in vivo skin hazard classifications based on UN Globally Harmonized System [category 1 (corrosive, Cat 1), 2 (irritant, Cat 2), 3 (mild irritant, Cat 3), and no category (nonirritant, NC)] were collected from public databases. After the curation of input data through removal and correlation analysis, every model was constructed to predict skin hazard classification for liquid chemicals with 22 physicochemical descriptors. Seven machine learning algorithms [Logistic regression, Naïve Bayes, k-nearest neighbor, Support vector machine, Random Forest, Extreme gradient boosting (XGB), and Neural net] were applied to ternary and binary classification of skin hazard. XGB model demonstrated the highest accuracy (0.73–0.81), sensitivity (0.71–0.92), and positive predictive value (0.65–0.81). The contribution of physicochemical descriptors to the classification was analyzed using Shapley Additive exPlanations plot to provide an insight into the skin irritation of chemicals.
KW - Extreme gradient boosting (XGB)
KW - Machine learning
KW - Physicochemical descriptor
KW - Shapley Additive exPlanations (SHAP)
KW - Skin irritation/corrosion
UR - http://www.scopus.com/inward/record.url?scp=85146691200&partnerID=8YFLogxK
U2 - 10.1007/s43188-022-00168-8
DO - 10.1007/s43188-022-00168-8
M3 - Article
AN - SCOPUS:85146691200
SN - 1976-8257
VL - 39
SP - 295
EP - 305
JO - Toxicological Research
JF - Toxicological Research
IS - 2
ER -