DeepNeuropePred: A robust and universal tool to predict cleavage sites from neuropeptide precursors by protein language model

• DOI: 10.1016/j.csbj.2023.12.004
• Publication Date: 2023-12-05T23:03:21Z
• Authors: Lei Wang; Zilu Zeng; Zhidong Xue; Yan Wang
• Keywords: Robustness; Cleavage (geology)

Neuropeptides play critical roles in many biological processes such as growth, learning, memory, metabolism, and neuronal differentiation. A few approaches have been reported for predicting neuropeptides that are cleaved from precursor protein sequences. However, these models cleavage site prediction of precursors were developed using a limited number neuropeptide datasets simple representation models. In addition, universal method sites can be applied to all species is still lacking. this paper, we proposed novel deep learning called DeepNeuropePred, combination pre-trained language model Convolutional Neural Networks feature extraction the precursors. To demonstrate model's effectiveness robustness, evaluated performance DeepNeuropePred four NeuroPred server independent dataset our achieved highest AUC score (0.916), which 6.9%, 7.8%, 8.8%, 10.9% higher than Mammalian (0.857), insects (0.850), Mollusc (0.842) Motif (0.826), respectively. For convenience researchers, provide web (http://isyslab.info/NeuroPepV2/deepNeuropePred.jsp).