Mapping the space of photoswitchable ligands and photodruggable proteins with computational modeling

TL;DR

This paper presents a computational approach combining docking and machine learning to efficiently identify and analyze photoswitchable ligands and photodruggable proteins, aiding the development of light-activated drugs.

Contribution

It introduces a novel procedure integrating ligand-protein docking with ML-based property prediction for large-scale virtual screening of photoactive compounds.

Findings

Most proteins prefer trans isomers over cis.

Binding affinities of active/inactive pairs are highly correlated.

Identified promising candidates for PARP1 inhibition with desirable properties.

Abstract

Light-activated drugs are a promising way to localize biological activity and minimize side effects. However, their development is complicated by the numerous photophysical and biological properties that must be simultaneously optimized. To accelerate the design of photoactive drugs, we describe a procedure that combines ligand-protein docking with chemical property prediction based on machine learning (ML). We apply this procedure to 58 proteins and 9,000 photo-drug candidates based on azobenzene cis-trans isomerism. We find that most proteins display a preference for trans isomers over cis, and that the binding affinities of nominally active/inactive pairs are in fact highly correlated. These findings have significant value for photopharmacology research, and reinforce the need for virtual screening to identify compounds with rare desirable properties. Further, we combine our procedure with quantum chemical validation to identify promising candidates for the photoactive inhibition of PARP1, an enzyme that is over-expressed in cancer cells. The top compounds are predicted to have long-lived active forms, differential bioactivity, and absorption in the near-infrared therapeutic window.