3D Based Generative PROTAC Linker Design with Reinforcement Learning

Proteolysis targeting chimeras (PROTACs), have emerged as an effective therapeutic modality by harnessing the ubiquitin-proteasome system to selectively induce targeted protein degradation, with the potential to modulate traditional undruggable targets. Due to its hetero-bifunctional characteristics, in which a linker joins warhead binding to a protein of interest, conferring specificity, and E3-ligand binding to an E3 ubiquitin ligase, a PROTAC molecule can form a PROTAC ternary structure for bring the protein of interest to the vicinity of the E3 ligase. The rational PROTAC linker design is challenging due to its relatively large molecular weight and the complexity of maintaining the binding mode of warhead and E3-ligand in the binding pockets of counterpart. Conventional linker generation method can only generate linkers in either 1D SMILES or 2D graph, without taking into account the information of ternary structures. Here we propose a novel 3D linker generative model PROTAC-INVENT which can not only generate SMILES of PROTAC but also its 3D putative binding conformation coupled with the target protein and the E3 ligase. The model is trained jointly with the RL approach to bias the generation of PROTAC structures toward pre-defined 2D and 3D based properties. Examples were provided to demonstrate the utility of the model for generating reasonable 3D conformation of PROTACs. On the other hand, our results show that the associated workflow for 3D PROTAC conformation generation can also be used as an efficient docking protocol for PROTACs.