202 / 2024-07-11 21:36:39

High-Content Image-based Regression Model for Drug Efficacy in Live Cell

High-content live cell imaging; Drug efficacy evaluation; FRET two-hybrid assay; Regression analysis; Precision medicine; Clinical drug screening

As precision medicine continues to evolve, the demand for quantitative drug efficacy evaluation is increasingly growing. This study aims to develop a regression model for drug efficacy evaluation based on high-content live cell imaging to provide an efficient and accurate quantitative analysis method for clinical drug screening. We first captured changes in cell morphology and function under positive drugs-treated using high-content live cell imaging, and then extracted key cellular feature parameters through image analysis software. Also, we used FRET two-hybrid assay technology to capture changes in drug targets and downstream signaling. Subsequently, we employed statistical methods such as multiple linear regression, ridge regression, and support vector regression, integrating indicators from both target and phenotype, to construct multiple drug efficacy evaluation models, which were then optimized and validated.

The results show that the established regression models can effectively predict drug efficacy and the correlation analysis indicates a high correlation between the model predictions and actual drug efficacy. Furthermore, we explored the applicability, advantages and disadvantages of different regression methods in drug efficacy evaluation, providing a theoretical basis and technical support for clinical drug screening. The proposed method not only improves the accuracy and efficiency of drug efficacy evaluation but also contributes to the development of personalized medicine, offering more precise treatment plans for patients.