Quantitative Structure-Activity Relationship of Fluorescent Probes and Their Intracellular Localizations

Abstract

The development of organelle-specific fluorescent probes has been impeded by the absence of a comprehensive understanding of the relationship between the physicochemical properties of fluorescent probes and their selectivity towards specific organelles. Although a few machine learning models have suggested several physicochemical parameters that control the target organelle of the probes and have attempted to predict the target organelles, they have been challenged by low accuracy and a limited range of applicable organelles. Herein, we report a multi-organelle prediction QSAR model that is capable of predicting the destination of probes among nine categories, including cytosol, endoplasmic reticulum, Golgi body, lipid droplet, lysosome, mitochondria, nucleus, plasma membrane, and no entry. The model is trained using the Random Forest algorithm with a dataset of 350 organelle-specific fluorescent probes and 786 descriptors, and it is able to predict the target organelles of fluorescent probes with an accuracy of 75%. The MDI analysis of the model identifies 38 key parameters that have a significant impact on the organelle selectivity of the probes, including LogD, pKa, hydrophilic-lipophilic balance (HLB), and topological polar surface area (TPSA). This prediction model may be useful in developing new organelle-specific fluorescent probes by providing crucial variables that determine the destination of the probes.

Keywords

• machine learning
• QSAR
• fluorescent probes
• organelle tracker