Key result
ML-driven QSAR models identify structural elements to optimize atypical DAT inhibitors with reduced hERG affinity.
Why the study?
When developing atypical DAT inhibitors for psychostimulant use disorders, avoiding off-target hERG potassium channel blockade is necessary to prevent potentially lethal ventricular tachycardia.
Population
Validation set of DAT inhibitors
Design
In silico machine learning QSAR modeling, experimental validation, and molecular simulations
Authors
Loading...
May inform preclinical DAT inhibitor optimization to limit hERG risk; leaves open clinical translation.
A combined machine learning and molecular modeling approach successfully established a counter-screening platform to optimize atypical DAT inhibitors while minimizing hERG-related cardiotoxicity.
Lee et al. (2021) studied Psychostimulant use disorders. Machine learning and molecular modeling was evaluated on DAT and hERG binding affinities. A combined machine learning and molecular modeling approach established robust QSAR models to identify structural elements for optimizing atypical DAT inhibitors with reduced hERG affinity.