Transformer decoder learns from a pretrained protein language model to generate ligands with high affinity

The drug discovery process can be significantly accelerated by using deep learn- ing methods to suggest molecules with drug-like features and, more importantly, that are good candidates to bind specific proteins of interest. We present a novel deep learning generative model, Prot2Drug, that learns to generate ligands binding specific targets leveraging i) the information carried by a pretrained protein language model and ii) the ability of transformers to capitalize the knowledge gathered from thousands of protein-ligand interactions. The embedding unveils the receipt to follow for de- signing molecules binding a given protein, and Prot2Drug translates such instructions by using the syntax of the molecular language generating novel compounds which are predicted to have favourable physicochemical properties and high affinity towards spe- cific targets. Moreover, Prot2Drug reproduced numerous known interactions between compounds and proteins used for generating them and suggested novel protein targets for known compounds indicating potential drug repurposing strategies. Remarkably, Prot2Drug allows the designing of promising ligands also in the case of protein targets with limited and/or no information about ligands and 3D structure.