Abstract: In this paper, molecular modelling (MM) with multiple linear regression (MLR) were employed for estimation and prediction of ¹³C NMR chemical shifts in alkanes from one or two through nine carbon atoms. Carbon atoms in alkanes were determined by 16 descriptors which correpond to the so-called embedding frequecies of rooted subtrees or subgraphs. These descriptors were equal to appearance numbers of smaller structural skeletons composed of one through six carbon atoms (C1~C6). It was demonstrated that the employed descriptors offered a quite useful formal technique for the proper and adequate description of environment of carbonatoms in alkanes.The results of MLR computation were compared with those of neural networks(NN) with modified backpropagation (MBP)calculations.Good results were obtained by using both techniques.

Key words: Molecular modelling in Spectroscopy, Chemical shifts of ¹³C NMR, Alkanes, Rooted subtrees and subgraphs, Modified backpropagation neural networks (MBPNN), Multiple linear regression (MLR)