MsaACPpred: Prediction of Anticancer Peptides Based on Multi-Scale Attention Convolutional Network
DOI:
https://doi.org/10.54097/y2ewqf29Keywords:
Anticancer Peptides, CNN, Attention Mechanism, BiLSTMAbstract
Anticancer peptides (ACPs) constitute a family of biologically active peptides with significant anti-tumor activity. These peptides are composed of 5 to 50 amino acid residues and are generally cationic in nature. Through electrostatic interactions, ACPs are able to target and bind to negatively charged cell membranes on the surface of cancer cells, thereby destroying their structure and inducing apoptosis. Given that the process of recognizing ACPs in the laboratory is highly restricted, which is not only costly but also time-consuming and lengthy, this study proposes a computational method for predicting ACPs based on sequence information. The method is designed with three core modules: feature encoding of peptide sequences, deep learning module layers, and a classification prediction layer. Among them, the deep learning module integrates convolutional neural network (CNN), attention mechanism and bidirectional long short-term memory network (BiLSTM), which enhances the learning and analyzing ability of the model. Ultimately, our model achieves 73.1% accuracy while maintaining 77.8% sensitivity and 69.6% specificity.
Downloads
References
[1] Cheng L, Zhao H, Wang P, et al. Computational Methods for Identifying Similar Diseases[J]. Mol Ther Nucleic Acids, 2019,18:590–604.
[2] Ge R, Feng G, Jing X, et al. EnACP: An Ensemble Learning Model for Identification of Anticancer Peptides[J]. Frontiers in Genetics,2020,11:760.
[3] Hajisharifi Z, Piryaiee M, Beigi MM, et al. Predicting anticancer peptides with chou’s pseudo amino acid composition and investigating their mutagenicity via Ames test [J]. J Theor Biol,2014,341:34–40.
[4] Saravanan Vijayakumar, Lakshmi PTV.ACPP: A Web Server for Prediction and Design of Anti-cancer Peptides[J]. International Journal of Peptide Research &Therapeutics, 2015, 21 (1):99–106.
[5] Rao B, Zhou C, Zhang G, et al. ACPred-Fuse: fusing multi-view information improves the prediction of anticancer peptides [J]. Briefings in Bioinformatics, 2020, 21(5): 1846–1855.
[6] Yu L, Jing R, Liu F, et al. DeepACP: A Novel Computational Approach for Accurate Identification of Anticancer Peptides by Deep Learning Algorithm[J]. Mol Ther Nucleic Acids,2020,22: 862–870.
[7] Sajid Ahmed, Rafsanjani Muhammod, Zahid Hossain Khan, et al. ACP-MHCNN: an accurate multi-headed deep-convolutional neural network to predict anticancer peptides[J]. Scientific Reports,2021,11(1): 1–15.
[8] Cao R, Wang M, Bin Y, et al. DLFF-ACP: prediction of ACPs based on deep learning and multi-view features fusion[J]. PeerJ, 2021,9: e11906.
[9] Chen X, Zhang W, Yang X, et al. ACP-DA: Improving the Prediction of Anticancer Peptides Using Data Augmentation[J]. Frontiers in Genetics, 2021,12: 1-9.
[10] Rao B, Zhang L, Zhang G. ACP-GCN: The Identification of Anticancer Peptides Based on Graph Convolution Networks[J]. IEEE Access, 2020, 8: 176005–176011.
[11] Lv Z, Cui F, Zou Q, et al. Anticancer peptides prediction with deep representation learning features[J]. Briefings in Bioinformatics, 2021,22(5): bbab008.
[12] Yuan Q, Chen K, Yu Y, et al. Prediction of anticancer peptides based on an ensemble model of deep learning and machine learning using ordinal positional encoding[J]. Briefings in Bioinformatics, 2023, 24(1):1–10.
[13] Agrawal P, Bhagat D, Mahalwal M, et al. AntiCP 2.0: an updated model for predicting anticancer peptides[J]. Briefings in Bioinformatics, 2020,22(3): bbaa153.
[14] Pande A, Patiyal S, Lathwal A, et al. Computing wide range of protein/peptide features from their sequence and structure[J]. bioRxiv, 2019.DOI:10.1101/599126.
[15] Pfahringer B , Reutemann P , Witten I H ,et al.The WEKA data mining software: an update[J].Acm Sigkdd Explorations Newsletter, 2009, 11(1):10-18.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Frontiers in Computing and Intelligent Systems
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
