QSAR Machine learning in pharma and other chemical industries has become very popular and useful due to its direct application to discovery research. The significance of QSAR metrics in the understanding and selection of models in a basic and important way is extremely essential. It is very difficult for bench scientists and computational chemist experts to confidently choose one model over another, in a robust manner. We agree with previous researchers that it is essential to assess the performance of the holdout set (aka test set which are not used in the training nor building of the model) Several nuances of RMSE (root mean square error) and the Pearson correlation coefficient (R<sup>2</sup>) have been proposed and routinely used. We have recruited and developed few simple metrics to assess ~1000s of QSAR models. We have built QSAR models for INSR and applied them to a compilation of Marketed drugs

Useful AI/ML model metrics and an application of a QSAR model to repurpose some marketed drugs for therapeutic evaluation pertinent to INSR

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.