SAVI (Synthetically Accessible Virtual Inventory) is a project of computationally generating a very large database of reliably and inexpensively synthesizable screening sample structures that have desirable properties for the drug development process. While most of the current similar approaches are based on machine learning methods learning from scratch, SAVI is designed as an expert system combining a generic knowledge of reactions and reasoning rules created by human experts, encoded in the LHASA project's transform description in CHMTRN and PATRAN. Since 2014, SAVI has grown to reach more than 2 billion compounds and has led to multiple insights and related projects to improve SAVI. The presentation will address how machine learning will enrich SAVI and illustrate it through different related projects.

How machine learning will enrich SAVI (Synthetically Accessible Virtual Inventory)

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.