Quantitative Structure Property Relationship Models for the Prediction of Heat Capacity of Amino Acid Derivatives Using Topological Indices

The present work represents a quantitative structure–property relationship (QSPR) study for predicting ofheat capacity (Cv) of 35 amino acids derivatives based on the Randic (1X), Balaban (J), Szeged (Sz), Harary (H),Wiener (W), Hyper Wiener (WW) and Wiener Polarity (WP) topological indices. The calculation was performed by theab-initio method at HF/6-31G (d) level of theory. The correlation coefficients (R) between experimental and predictedheat capacity (Cv) for the prediction set by multiple linear regressions (MLR) and partial least square (PLS) methodsare 0.9263 and 0.998, respectively. The results demonstrated that the calculated Cv values by PLS were in goodagreement with the experimental ones, and the performance of the PLS model was superior to MLR approach.

کلیدواژه ها:

quantitative structure–property relationship ، Amino Acid Derivatives ، PLS