Building predictive models for various ADMET end-points e.g., solubility, intrinsic clearance, or hERG toxicity, requires the inclusion of diverse chemotypes to ensure their applicability to a wide range of chemical structures. Building an ensemble of models tends to yield better results when there is significant diversity amongst the models. In this presentation, the performance of different ensemble methods will be compared. We used different ensemble algorithms, e.g, Random Forest, and XGBoost as well as our proprietary Artificial Neural Network and Support Vector Machine ensemble methods to build models from the same training compounds and descriptor pools. These methods were used to build regression and classification models of different end-points, pertaining to drug discovery. The strengths and limitations of these methods will be discussed along with their performance.

Comparison of ensemble learning methodologies in drug discovery

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.