Prescription opioids are among the most effective drugs to treat pain, which are ligands to the endogenous mu opioid receptor (MOR) and can exert agonistic, partially agonistic or antagonistic effects. When activated by agonists, MOR can mediate analgesic effects as well as modulate respiratory responses. However, lethal respiratory depression can occur when overdosed. To combat the opioid crisis, measures to reduce the prescription opioids supply alone will not be enough. It is therefore imperative to develop novel opioid analgesics with reduced overdose effects.
We have been working on identifying lead compounds for novel opioid analgesics with reduced overdose effects. To accelerate the discovery process and maximize subsequent success rates, we are developing an integrated AI-driven drug discovery pipeline, with the aims to: 1) establish a robust target product profile for novel opioid analgesics by mining RWD for the optimal properties underlying reduced overdose effects; 2) develop an efficient deep RL framework to generate molecules with multiple desired properties; and 3) validate the generated molecules with molecular docking analysis and molecular dynamics simulation.
The Integrated Artificial Intelligence Pipeline for Drug Discovery.