QSAR modeling of PET imaging agents for the diagnosis of Parkinson’s disease targeting dopamine receptor

Abstract

Dopamine (D2) receptor has emerged as a potent drug target for the diagnosis and treatment of Parkinson’s disease (PD). Radiolabelled imaging such as positron emission tomography (PET) has been recognized as an important tool in medicinal chemistry useful for the early diagnosis of PD. The present study explores quantitative structure—activity relationship analysis of 34 PET imaging agents targeted toward dopamine D2 receptor. The dataset division into training and test sets was done using Euclidean distance division method, while the feature selection was done by double cross-validation-genetic algorithm method. Finally, a five-descriptor partial least squares regression model was derived after carrying out the best subset selection applied on the significant descriptors. The developed model showed robustness in terms of statistical parameters. Finally, the structural information derived from the model descriptors gives an insight for the development of new candidate D2-PET imaging for the use in PD.