AMPpred-EL: An effective antimicrobial peptide prediction model based on ensemble learning. (July 2022)

• Record Type: Journal Article
• Authors: Lv, Hongwu; Yan, Ke; Guo, Yichen; Zou, Quan; Hesham, Abd El-Latif; Liu, Bin
• Is Part Of: Computers in biology and medicine. Volume 146(2022)
• Publication Date: 2022-07
• Subjects: AMP prediction -- Ensemble learning -- LightGBM -- Logistic regression; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105577
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Antimicrobial peptides (AMPs) are important for the human immune system and are currently applied in clinical trials. AMPs have been received much attention for accurate recognition. Recently, several computational methods for identifying AMPs have been proposed. However, existing methods have difficulty in accurately predicting AMPs. In this paper, we propose a novel AMP prediction method called AMPpred-EL based on an ensemble learning strategy. AMPred-EL is constructed based on ensemble learning combined with LightGBM and logistic regression. Experimental results demonstrate that AMPpred-EL outperforms several state-of-the-art methods on the benchmark datasets and then improves the efficiency performance. Highlights: A novel AMP prediction method is proposed based on ensemble learning. The proposed method is efficient and has a good interpretability. The proposed method outperforms the state-of-the-art methods on the independent dataset.