Drug design and repurposing with a sequence-to-drug paradigm

Abstract

Drug development based on target proteins has been a successful approach in recent decades. A conventional structure-based drug design pipeline is a complex, human-engineered pipeline with multiple independently optimized steps. Advances in end-to-end differentiable learning suggest the potential benefits of similarly reformulating drug design. Here, we proposed a new sequence-to-drug paradigm that discovers drug-like small-molecule modulators directly from protein sequences and validated this concept for the first time in three stages. First, we designed TransformerCPI2.0 as a core tool for the sequence-to-drug paradigm, which exhibited competitive performance with conventional structure-based drug design approaches. Second, we validated the binding knowledge that TransformerCPI2.0 has learned. Third, we applied a sequence-to-drug paradigm to discover new hits for E3 ubiquitin-protein ligases: speckle-type POZ protein (SPOP) and ring finger protein 130 (RNF130) which does not have a 3D structure. This first proof of concept shows that the sequence-to-drug paradigm is a promising direction for drug development.

Deep generative model for drug design from protein target sequence

“…Given a specific protein (also called target, such as a protein representing a human or virus), two standard methods could be reemployed to discover a ligand: virtual screening and de novo design. Virtual screening [ 3 ] is carried out in two manners: (1) by studying the interaction patterns between target proteins and small molecules and (2) by comparing the structures and pharmacophores of known small molecules to select from many molecules that are reasonable for subsequent testing. De novo design towards target protein directly generates molecules by exploring the explicit rules of known data, in contrast to virtual screening, which is cumbersome and not straightforward.…”