My group has recently used machine learning tools to address two key challenges in virtual screening / designing new protein-ligand interactions. First, we take advantage of protein flexibility by using a biased sampling approach to identify low-energy pocket-containing conformations of the protein target. Potentially druggable conformations of the protein are then analyzed using a random forest model that quantitative evaluates druggability by predicting the maximal achievable potency of (hitherto unknown) ligands addressing a given pocket. Thus, this strategy allows identification of the most promising protein conformation(s) ahead of any virtual screening. Second, after carrying out virtual screening to search for ligands that complement these pockets, we re-rank the resulting complexes using a new random forest model that identifies those compounds most likely to show activity. By carefully training the model against very compelling decoys, the model proves effective at discriminating active complexes from typical virtual screening outputs. Thus, this model allows prioritization of complexes for subsequent characterization, either via further simulations or through wetlab assays. Both approaches will be described in the context of specific case studies in which we have applied them, and results will be discussed in the context of free energies of protein re-arrangement and free energies of ligand binding.<br/>

Enhancing structure-based drug design through data science

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.