RASAR - accurate in silico toxicology assessment
2018
Johns Hopkins University, Baltimore, USA
The study describes a read-across structure-activity relationships (RASAR) in silico method capable of analyzing large chemical databases. Based on structural similarities and known properties of chemical substances, RASAR groups multiple chemicals together and predicts putative toxic effects with an accuracy of 80-95%, which is significantly higher than the standard toxicological animal experiments.
Machine Learning of Toxicological Big Data Enables Read-Across Structure Activity Relationships (RASAR) Outperforming Animal Test Reproducibility
Thomas Hartung
Added on: 09-01-2020
[1] https://academic.oup.com/toxsci/article/165/1/198/5043469
