The aim of this study is to provide the numerical outcomes of a nonlinear HIV infection system of latently infected CD4+ T cells exists in bioinformatics using Morlet wavelet (MW) artificial neural networks (ANNs) optimized initially with global search of genetic algorithms (GAs) hybridized for speedy local search of sequential quadratic programming (SQP), i.e., MW-ANN-GA-SQP. The design of an error function is presented by designing the MW-ANN models for the differential equations along with the initial conditions that represent the HIV infection system involving latently infected CD4+ T cells. The precision and persistence of the presented approach MW-ANN-GA-SQP are recognized through comparative studies from the results of the Runge-Kutta numerical scheme for solving the HIV infection spread system in case of single and multiple trails of the MW-ANN-GA-SQP. Statistical estimates with ‘Theil’s inequality coefficient’ and ‘root mean square error’ based indices further validate the sustainability and applicability of proposed MW-ANN-GA-SQP solver.

这项研究的目的是提供利用生物信息学中最初存在的Morlet小波（MW）人工神经网络（ANN）和遗传算法（GAs）的全局搜索进行最优化的生物信息学中存在的潜在感染CD4 + T细胞的非线性HIV感染系统的数值结果用于快速局部搜索顺序二次规划（SQP），即MW-ANN-GA-SQP。通过为微分方程设计MW-ANN模型以及代表包含潜在感染CD4 + T细胞的HIV感染系统的初始条件，来设计误差函数。通过比较研究从Runge-Kutta数值方案的结果中识别出了所提出方法MW-ANN-GA-SQP的准确性和持久性，以解决在MW-ANN-GA的单行或多行情况下解决HIV感染传播系统的问题。 GA-SQP。基于“ Theil的不平等系数”和“均方根误差”的指数进行的统计估计进一步验证了拟议的MW-ANN-GA-SQP求解器的可持续性和适用性。