Assessing Endocrine Disruption Potential in Consumer Product Ingredients
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 product chemicals.
-
2
Expanded the estrogen receptor assessment
Following publication of an EPA paper, built additional estrogen receptor models and used them to make further predictions.
-
3
Assessed androgen receptor and aromatase activity
Conducted similar assessments for the androgen receptor and aromatase receptors.