A novel model for prediction of stability constants of the thiosemicarbazone ligands with different types of toxic heavy metal ions using structural parameters and multivariate linear regression method

Design, virtual screening and in silico QSPR modeling for the development of new thiosemicarbazone‐based complexes

“…(approximation of 15%). [16] The architecture of the neural network is I(6)-HL(m)-O(1), in which six neurons of the input layer I(6) are dipole, 5 C, 4 N, fw, xc3, and ka1; the output layer with one neuron the log12 values. The number of neurons of the hidden layer (m) was surveyed, and the initial values of the m neurons are indicated in table 4.…”

“…Besides, these derivatives have been synthesized in practice and have high biological activity, like thiosemicarbazone and their complexes, to orient further future studies. Six variables of the models, including dipole, 5 C, 4 N, fw, xc3, and ka1, were selected to discover the new thiosemicarbazone-based complexes.…”

“…Up to now, there are a few QSPR studies on the M:L complex of a thiosemicarbazone ligand (L) with a metal ion (M) in an aqueous solution. [ 4,5 ] Meanwhile, the difference between these studies is that the models are developed with different data sets and different methods. Besides, in the QSAR/QSPR research, popular methods such as multivariate linear regression (MLR), support vector regression (SVR), and artificial neural network (ANN) are often used or can be combined with other intelligent algorithms.…”

“…Besides, in the QSAR/QSPR research, popular methods such as multivariate linear regression (MLR), support vector regression (SVR), and artificial neural network (ANN) are often used or can be combined with other intelligent algorithms. [4,5] However, the studies on the M:2L complex of two thiosemicarbazone ligands (L) with a metal ion (M) in an aqueous solution are still very limited and these studies also came from our works. [6] Furthermore, it should be noted that in QSAR/QSPR studies the data space is so large that it is difficult to have a model that represents the entire structure of the derivative.…”