Recently, increasing importance has been given to neural tube defects (NTDs), considered a congenital disability that affects the brain and the spinal cord. NTD occurs because of genetic information passed from parents to children via genes that affect the brain region’s shape or function. Presently, minimum folate carrier (MFC A80G) gene polymorphism and maternal folic acid interactions are associated with NTD. Therefore, we designed and developed a grey wolf optimizer-assisted deep recurrent neural network to predict the association between gene polymorphism and folic acid interaction in NTD. The information of different control families and nuclear family information was collected to examine the process of polymorphism. Moreover, the homozygous mutant type (GG) genotype mothers and folic acid consumption levels were continuously analyzed to identify the link with and risk of NTD. The simulation analysis was performed to evaluate the statistical results in comparison with those obtained using conventional methods. Given the importance of interactions and associations, this research discusses the optimized deep recurrent neural network-based polymorphism process to identify the NTD risk factors with a lower error ratio of 0.015%. We found that MFC-GG genotype polymorphism and folic acid consumptions are essential and effective in lowering the prevalence of NTD among offspring with maximum accuracy rate of 99.5%.

最近，人们越来越重视神经管缺陷（NTD），人们认为神经管缺陷是一种影响大脑和脊髓的先天性残疾。发生NTD的原因是遗传信息通过影响大脑区域形状或功能的基因从父母传递给孩子。目前，最小叶酸载体（MFC A80G）基因多态性和母体叶酸相互作用与NTD相关。因此，我们设计和开发了灰狼优化器辅助的深度递归神经网络，以预测NTD中基因多态性与叶酸相互作用之间的关联。收集不同控制家族的信息和核心家族的信息，以检查多态性的过程。而且，对纯合突变型（GG）基因型母亲和叶酸消耗水平进行连续分析，以确定与NTD的联系和风险。与使用常规方法获得的统计结果相比，进行了模拟分析以评估统计结果。考虑到交互作用和关联的重要性，本研究讨论了基于优化的深度递归神经网络的多态性过程，以识别错误率低至0.015％的NTD危险因素。我们发现，MFC-GG基因型多态性和叶酸消耗量对于降低后代NTD患病率至关重要，且有效率最高，可达99.5％。与使用常规方法获得的统计结果相比，进行了模拟分析以评估统计结果。考虑到交互作用和关联的重要性，本研究讨论了基于优化的深度递归神经网络的多态性过程，以识别错误率低至0.015％的NTD危险因素。我们发现，MFC-GG基因型多态性和叶酸消耗量对于降低后代NTD患病率至关重要，且有效率最高，可达99.5％。与使用常规方法获得的统计结果相比，进行了模拟分析以评估统计结果。考虑到交互作用和关联的重要性，本研究讨论了基于优化的深度递归神经网络的多态性过程，以识别错误率低至0.015％的NTD危险因素。我们发现，MFC-GG基因型多态性和叶酸消耗量对于降低后代NTD患病率至关重要，且有效率最高，可达99.5％。