Using a combination of theoretical descriptors and a neural network to predict the activity of a set of N-alkyl-n-acyl- -aminoamide derivatives

A back -propagation artificial neural net has been trained to estimate the activity values of a set of 18 N-alkyl-N-acyl- -aminoamide derivatives from the results of molecular mechanics and RHF/PM3/SCF MO semi-empirical calculations. The input descriptors include molecular properties such as the partition coefficient P, 3d structure dependent parameters, charge dependent parameters, and topological descriptors.
Nội dung trích xuất từ tài liệu:
Using a combination of theoretical descriptors and a neural network to predict the activity of a set of N-alkyl-n-acyl- -aminoamide derivativesJournal of Chemistry, Vol. 38, No.3, P. 91 - 96, 2000 Using a combination of theoretical descriptors and a neural network to predict the activity of a set of N-alkyl-n-acyl- -aminoamide derivatives Received 21-02-2000 Pham Van Tat, Pham Nu Ngoc Han Department of Chemistry, University of Dalat Summary A back -propagation artificial neural net has been trained to estimate the activity values of a set of 18 N-alkyl-N-acyl- -aminoamide derivatives from the results of molecular mechanics and RHF/PM3/SCF MO semi-empirical calculations. The input descriptors include molecular properties such as the partition coefficient P, 3d structure dependent parameters, charge dependent parameters, and topological descriptors. I - Introduction In general, the skeleton of N-alkyl-N-acyl- -aminoamide derivatives is given in figure 1 Quantitative structure-activity relationship [1].(QSAR) has been used extensively incorrelation molecular structure features of O R2 Hcompounds to their biological, chemical, andphysical properties. The preferability of QSAR N R N R3is that there is quantitative connection between 1the microscopic (molecular structure) and the 8 O R Hmacroscopic (empirical) properties (particularly R4 O 2 13biological activity) of a molecule. Furthermore, 3 (A) 9 11 N 4 7this connection can be used to predict empirical 2 N 10 R3properties of a compound with its molecular 15 1 16 5 Ostructure given. COOH 14 6 R4 12 The N-alkyl-N-acyl- -aminoamides weresynthesized and screened against several protein (B)tyrosine phosphatases (PTPase), and severalclasses of potent and the selective inhibitors ofvarious PTPase. The compounds of generalformula in figure 1 bearing a cinnamate groupwere shown to exhibit low micromolar Figure 1: The skeleton of N-alkyl-N-acyl- -inhibitory activity against HePTP which is a aminoamidephosphatase specific to hematopoeitic cells and A) general structure, B) the R1 group isimplicated in acute leukemia. replaced by a cinnamic group 91 The electrostatic interaction, and bulk or are used here shown in table 1 and thesteric effect, and transfer property (trans- numeration needed for indicating net charge isferability) of the molecules are considered as given in figure 1.microscopic properties. Theoretical descriptors Table 1: Theoretical descriptors are used in calculations [4] 3d structure dependent parameters Volume Van der Waals volume Mol. Weight Molecular weight of a molecular Polar Molecular polarizability Sp. Polar Specific polarizability of a molecule LogP The logarithm of the partition coefficient P Charge dependent parameters Dipole Dipole moment of the molecule MaxQpos Largest positive charge over the atoms MarQneg Largest negative charge over the atoms ABSQ Sum of absolute values of the charges on each atom ABSQon Sum of absolute values of the charges on the nitrogen and oxygen in molecule Net charge of the atoms C1 Net charge of 1 atom C7 Net charge of 7 atom N13 Net charge of 13 atom C2 Net charge of 2 atom O8 Net charge of 8 atom C14 Net charge of 14 atom C3 Net charge of 3 atom N9 Net charge of 9 atom C15 Net charge of 15 atom C4 Net charge of 4 atom C10 Net charge of 10 atom C16 Net charge of 16 atom C5 Net charge of 5 atom C11 Net c ...