A Quantitative Structure-activity Relationships Model Based on Hybrid Artificial Intelligence Methods and its Application

• DOI: 10.20944/preprints201805.0475.v1
• Publication Date: 2018-06-05T09:40:51Z
• Authors: Mengshan Li; Huaijin Zhang; Liang Liu; Bingsheng Chen; Lixin Guan; Yan Wu
• Keywords: Molecular descriptor; Backpropagation; Mean absolute error

Quantitative structure-activity relationship (QSAR) model is adopted to study the between chemical and physical properties of various substances structure. Through QSAR studies, internal invisible structure activity can be obtained. In this paper, a novel chaos-enhanced accelerate particle swarm algorithm (CAPSO) proposed, which used molecular descriptors screening optimization weights back propagation artificial neural network (BP ANN). Then, based on CAPSO BP ANN put forward, hereinafter referred as model. The prediction experiment showed that reliable method for five obtained by could well characterize each compound in pKa prediction. experimental results also has good performance predicting values compounds, absolute mean relative error, root square correlation coefficient are respectively 0.5364, 0.0632, 0.9438, indicating higher accuracy correlation. proposed hybrid intelligent applied all kinds engineering design, calculation.