1. Advancing chemical carcinogenicity prediction modeling: opportunities and challenges.
- Author
-
Mittal, Aayushi and Ahuja, Gaurav
- Subjects
- *
MACHINE learning , *CARCINOGENICITY , *ARTIFICIAL intelligence , *PREDICTION models , *CARCINOGENS , *HUMAN fingerprints - Abstract
First-generation chemical carcinogenicity prediction models leveraged classical chemistry-based fingerprints or descriptors; however, these do not provide the underlying mechanistic insights associated with predictions. The paucity of experimentally validated (non)carcinogens pose challenges to machine learning models in capturing the bewildering complexity of the chemical space. Newly emerging multifaceted chemical representations have overtaken the classical descriptors and are continually revolutionizing the performance and generalizability of carcinogen predictors. The validation and adoption of the next-generation carcinogen predictors will also be contingent on their capability to explain the biological underpinnings of the predictions. Carcinogenicity assessment of any compound is a laborious and expensive exercise with several associated ethical and practical concerns. While artificial intelligence (AI) offers promising solutions, unfortunately, it is contingent on several challenges concerning the inadequacy of available experimentally validated (non)carcinogen datasets and variabilities within bioassays, which contribute to the compromised model training. Existing AI solutions that leverage classical chemistry-driven descriptors do not provide adequate biological interpretability involved in imparting carcinogenicity. This highlights the urgency to devise alternative AI strategies. We propose multiple strategies, including implementing data-driven (integrated databases) and known carcinogen-characteristic-derived features to overcome these apparent shortcomings. In summary, these next-generation approaches will continue facilitating robust chemical carcinogenicity prediction, concomitant with deeper mechanistic insights. [ABSTRACT FROM AUTHOR]
- Published
- 2023
- Full Text
- View/download PDF