Assessing Endocrine Disruption Potential of Consumer Product Ingredients
Case Study 09
A progressive series of machine-learning assessments evaluated consumer product ingredients across estrogen, androgen, and aromatase receptor targets; the resulting work was published in separate papers.
Challenge
The client asked CPI to assess the chemicals used in its products for potential endocrine disruption, beginning with estrogen receptor models.
What We Did
-
1
Built and validated estrogen receptor models
Curated data to build an array of machine learning models and performed extensive validation before evaluating the chemical of interest from the client products.
-
2
Expanded the estrogen receptor assessment
Following publication of a paper from the EPA, CPI built additional estrogen receptor models and used them to make further predictions.
-
3
Assessed androgen receptor and aromatase activity
CPI conducted similar assessments for the androgen receptor and aromatase receptors building and validating machine learning models.