Pharmacophore-Based Machine Learning Model To Predict Ligand Selectivity for E3 Ligase Binders

Reagon Karki; Yojana Gadiya; Philip Gribbon; Andrea Zaliani

doi:10.1021/acsomega.3c02803

Pharmacophore-Based Machine Learning Model To Predict Ligand Selectivity for E3 Ligase Binders

ACS Omega. 2023 Aug 9;8(33):30177-30185. doi: 10.1021/acsomega.3c02803. eCollection 2023 Aug 22.

Authors

Reagon Karki^{1

2}, Yojana Gadiya^{1

2

3}, Philip Gribbon^{1

2}, Andrea Zaliani^{1

2}

Affiliations

¹ Fraunhofer Institute for Translational Medicine and Pharmacology (ITMP), Schnackenburgallee 114, 22525 Hamburg, Germany.
² Fraunhofer Cluster of Excellence for Immune-Mediated Diseases (CIMD), Theodor Stern Kai 7, 60590 Frankfurt, Germany.
³ Bonn-Aachen International Center for Information Technology (B-IT), University of Bonn, 53113 Bonn, Germany.

Abstract

E3 ligases are enzymes that play a critical role in ubiquitin-mediated protein degradation and are involved in various cellular processes. Pharmacophore analysis is a useful approach for predicting E3 ligase binding selectivity, which involves identifying key chemical features necessary for a ligand to interact with a specific protein target cavity. While pharmacophore analysis is not always sufficient to accurately predict ligand binding affinity, it can be a valuable tool for filtering and/or designing focused libraries for screening campaigns. In this study, we present a fast and an inexpensive approach using a pharmacophore fingerprinting scheme known as ErG, which is used in a multi-class machine learning classification model. This model can assign the correct E3 ligase binder to its known E3 ligase and predict the probability of each molecule to bind to different E3 ligases. Practical applications of this approach are demonstrated on commercial libraries such as Asinex for the rational design of E3 ligase binders. The scripts and data associated with this study can be found on GitHub at https://github.com/Fraunhofer-ITMP/E3_binder_Model.