scholarly journals Prediction Model of Clearance by a Novel Quantitative Structure–Activity Relationship Approach, Combination DeepSnap-Deep Learning and Conventional Machine Learning

ACS Omega ◽  
2021 ◽  
Vol 6 (36) ◽  
pp. 23570-23577
Author(s):  
Hideaki Mamada ◽  
Yukihiro Nomura ◽  
Yoshihiro Uesawa
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Prediction Model ◽  
Quantitative Structure Activity Relationship ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Quantitative Structure ◽  
Structure Activity ◽  
Conventional Machine

scholarly journals A Novel Approach for a Toxicity Prediction Model of Environmental Pollutants by Using a Quantitative Structure-Activity Relationship Method Based on Toxicogenomics

2011 ◽  
Vol 2011 ◽  
pp. 1-9 ◽  
Author(s):  
Junichi Hosoya ◽  
Kumiko Tamura ◽  
Naomi Muraki ◽  
Hiroki Okumura ◽  
Tsuyoshi Ito ◽  
...  
Keyword(s):  
Gene Expression ◽  
Prediction Model ◽  
Environmental Pollutants ◽  
Quantitative Structure Activity Relationship ◽  
Structure Activity Relationship ◽  
Activity Relationship ◽  
Quantitative Structure ◽  
Toxicity Prediction ◽  
Human Lung Cells ◽  
Structure Activity

The development of automobile emission reduction technologies has decreased dramatically the particle concentration in emissions; however, there is a possibility that unexpected harmful chemicals are formed in emissions due to new technologies and fuels. Therefore, we attempted to develop new and efficient toxicity prediction models for the myriad environmental pollutants including those in automobile emissions. We chose 54 compounds related to engine exhaust and, by use of the DNA microarray, examined their effect on gene expression in human lung cells. We focused on IL-8 as a proinflammatory cytokine and developed a prediction model with quantitative structure-activity relationship (QSAR) for the IL-8 gene expression by using an in silico system. Our results demonstrate that this model showed high accuracy in predicting upregulation of the IL-8 gene. These results suggest that the prediction model with QSAR based on the gene expression from toxicogenomics may have great potential in predictive toxicology of environmental pollutants.

Sign in / Sign up

Export Citation Format

Share Document