AUTHOR=Xie Xufen , Zhu Chuanchuan , Wu Di , Du Ming 

TITLE=Autoregressive Modeling and Prediction of the Activity of Antihypertensive Peptides

JOURNAL=Frontiers in Genetics

VOLUME=Volume 12 - 2021

YEAR=2022

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2021.801728

DOI=10.3389/fgene.2021.801728

ISSN=1664-8021

ABSTRACT=Naturally derived bioactive peptides with antihypertensive activities serve as promising alternatives to pharmaceutical drugs. There are few relevant reports on the mapping relationship between EC50 Value of antihypertensive peptides activity (AHTPA-EC50) and its corresponding amino acid sequence (AAS) at present. In this paper, we have constructed two group series based on sorting natural logarithm of AHTPA-EC50 or sorting its corresponding AAS encoding number. One group possesses two series, and we find that there must be a random number series in any group series. The random number series manifests fractal characteristics, and the constructed series of sorting natural logarithm of AHTPA-EC50 shows good autocorrelation characteristics. Therefore, two nonlinear autoregressive models with exogenous input (NARX) was established to describe the two series. A prediction method is further designed for AHTPA-EC50 prediction based on the proposed model. Two dynamic neural networks for NARX (NARXNN) are designed to verify the two series characteristics. Dipeptides and tripeptides are used to verify the proposed prediction method. The results show that the mean absolute error (MSE) of prediction is about 0.5589 for AHTPA-EC50 prediction when the classification of AAS is correct. The proposed method provides a solution for AHTPA-EC50 prediction.