Predicting Anti-inflammatory Peptides by Ensemble Machine Learning and Deep Learning

• DOI: 10.1021/acs.jcim.3c01602
• Publication Date: 2023-12-06T15:24:41Z
• Authors: Jiahui Guan; Lantian Yao; Chia-Ru Chung; Peilin Xie; Yilun Zhang; Junyang Deng; Ying-Chih Chiang; Tzong-Yi Lee
• Keywords: Feature (linguistics); Inflammatory response

Inflammation is a biological response to harmful stimuli, aiding in the maintenance of tissue homeostasis. However, excessive or persistent inflammation can precipitate myriad pathological conditions. Although current treatments such as NSAIDs, corticosteroids, and immunosuppressants are effective, they have side effects resistance issues. In this backdrop, anti-inflammatory peptides (AIPs) emerged promising therapeutic approach against inflammation. Leveraging machine learning methods, we opportunity accelerate discovery investigation these AIPs more effectively. study, proposed an advanced framework by ensemble deep for AIP prediction. Initially, constructed three individual models with extremely randomized trees (ET), gated recurrent unit (GRU), convolutional neural networks (CNNs) attention mechanism then used stacking architecture build final predictor. By utilizing various sequence encodings combining strengths different algorithms, our predictor demonstrated exemplary performance. On independent test set, model achieved accuracy, MCC, F1-score 0.757, 0.500, 0.707, respectively, clearly outperforming other contemporary prediction methods. Additionally, offers profound insights into feature interpretation AIPs, establishing valuable knowledge foundation design development future strategies.