Prediction EC50 some compounds by Multi linear regression (MLR) and partial linear regression (PLS)

Quantitative structure–activity relationship (QSAR) analysis has been directed to a series of substituted aromatic compounds. Modeling of the 50% effective inhibition concentration (48 h – EC50) as a function of the theoretically derived descriptors was established by multiple linear regression (MLR) and partial least squares (PLS) regression. Appropriate models with low standard errors and high correlation was used. A comparison of the two regression methods used showed that MLR has a better prediction ability than PLS.