@article{Samigulina_Massimkanova_2018, title={Construction of an optimal immune network model based on the modified swarm algorithm}, volume={98}, url={https://bm.kaznu.kz/index.php/kaznu/article/view/402}, DOI={10.26577/jmmcs-2018-2-402}, abstractNote={<p>the approach of artificial immune systems, for the computer molecular design of new drugs and<br>prediction the "structure-property/activity"relationship (QSAR) of chemical compounds is an<br>actual problem. The article is devoted to the solution of the task of QSAR on the construction of<br>immune network model based on the choice of optimal set of descriptors to facilitate the selection of<br>new chemical compounds for candidate drugs with predefined properties. According to the concept<br>of multialgorithmic approach development of optimal immune network model and allocation of<br>informative descriptors is carried out on the basis of swarm intelligence algorithms. In this work<br>comparison of standard particle swarm optimization algorithm (PSO) and modified inertia weight<br>particle swarm optimization (IWPSO) is described for selection of informative descriptors on the<br>example of drug compounds of the sulfanilamide group with various pharmacological activities. The<br>choice of the parameters (fitness functions, population size, the number of iterations, etc.), which<br>define performance of the offered algorithms for creation of optimal set of descriptors is analysed.<br>The results of modeling of dependence of fitness function values on the number of iterations in<br>software products WEKA and Yarpiz (PSO) are given.</p>}, number={2}, journal={Journal of Mathematics, Mechanics and Computer Science}, author={Samigulina, G. A. and Massimkanova, Zh. A.}, year={2018}, month={Aug.}, pages={77–87} }