Advancing Targeted Protein Degradation via Multiomics Profiling and Artificial Intelligence

Abstract

Only around 20% of the human proteome is considered to be druggable with small-molecule antagonists. This leaves some of the most compelling therapeutic targets outside the reach of ligand discovery. The concept of targeted protein degradation (TPD) promises to overcome some of these limitations. In brief, TPD is dependent on small molecules that induce the proximity between a protein of interest (POI) and an E3 ubiquitin ligase, causing ubiquitination and degradation of the POI. In this perspective, we want to reflect on current challenges in the field, and discuss how advances in multiomics profiling, artificial intelligence, and machine learning (AI/ML) will be vital in overcoming them. The presented roadmap is discussed in the context of small-molecule degraders but is equally applicable for other emerging proximity-inducing modalities.

AlphaFold-Multimer struggles in predicting PROTAC-mediated protein-protein interfaces

“…This new wealth of information could motivate the retraining of AF-Multimer, which should aim to include ligand contributions, or the development of a PROTAC-focused machine-learning model aiming at the accurate prediction of ternary complex structures. While some groups have developed tools for this purpose [32][33][34][35][36] , they are typically not general because they require that the PROTAC molecule be known a priori. Within our group we developed PROTACability 25 , which by-passes this constraint and achieves satisfactory accuracy but fails to produce high quality solutions.…”

Neutrophils of MDSCs in ovarian cancer are negatively related to Immunotherapy and prognosis: a multi-omics-based consensus clustering

“…As NGS techniques develop and multi-omics data expands, a myriad of cuttingedge tools and methods have been deployed for data integration and interpretation. For example, multi-omics profiling interfaces with AI/ML technologies enable advanced research in targeted protein degradation (TPD), pave the way toward efficient iden-tification and rational design of small-molecule degraders [40]. In addition, machine learning (ML) with two primary learning strategies (supervised and unsupervised) now has been conducted to multiomics data for a wide range of applications [41].…”

Function, mechanism and drug discovery of ubiquitin and ubiquitin-like modification with multiomics profiling for cancer therapy

“…Unfortunately, only approximately 20% of the human proteome is druggable for an inhibitor-centric development approach. To address the critical limitations of the inhibitor-centric approach, the development of E3-associated modulators has introduced the concept of target protein degradation (TPD) as a novel pharmacologic modality 285 . Notably, proteolysis-targeting chimeras (PROTACs) have expanded the application of PPIs and provided insights into the degradation pathways for drug discovery 286 , 287 , 288 , 289 .…”