Providing an efficient model to predict antimicrobial peptides using artificial intelligence algorithms

Document Type : Research Paper

Authors

1 Department of Animal Science, Faculty of Agriculture, Ferdowsi Mashhad University, Mashhad, Iran

2 Department of Animal Science, Faculty of Agriculture, Ferdowsi Mashhad University, Mashhad, Iran.

3 Assistant Professor, Department of Animal Science, Faculty of Agriculture, Ferdowsi Mashhad University, Mashhad, Iran.

Abstract

Objective
The aim of this study was to propose an efficient algorithm to predict antimicrobial peptides using artificial intelligence algorithms.
Materials and methods
In this study, an updated AMP and non-AMP data set including physico-chemical characteristics at the level of amino acids and protein sequence in three animal species and humans was extracted. After data exploration and data pre-processing steps, four methods Supervised learning including Decision Tree, Random Forest, Naive Bayes and SVM on the AMP dataset with 10-fold cross-validation to build models and predict the AMP label using the evaluation criteria of specificity, sensitivity, rate Accuracy, precision, recall, F1 score and area under the rock curve (AUC) were evaluated.
Results
In this study, using an up-to-date dataset, a machine learning model has been successfully trained to predict antimicrobial peptides. A comprehensive set of features has been subjected to feature selection to identify key features of antimicrobial peptides. After selecting the feature, among the different generated models, the model based on the RF model classifier showed the best performance with Accuracy (95 percent), Precision (96 percent), Recall (95 percent), F1 Score (95 percent). the four classification of algorithms, Random Forest algorithm and SVM are the most accurate. The Decision Tree classification algorithm had the least accuracy.
Conclusions
According to the obtained results, the proposed RF model has a better performance than other models for AMP prediction. This model predicted some peptides as peptides with antimicrobial properties. This predictive approach can be useful in extracting AMPs with antimicrobial properties from AMP libraries in useful clinical applications before moving on to experimental studies. On the other hand, several features in the final selection properties indicate that these features are critical determinants of peptide properties and should be considered in the development of models to predict peptide activity. The executable code is available in the attached file.

Keywords

References

Aburomman AA, Reaz MBI (2017) A survey of intrusion detection systems based on ensemble and hybrid classifiers. J Comput Secur 65, 135-152.
Aronica PG, Reid LM, Desai N, et al. (2021) Computational methods and tools in antimicrobial peptide research. J Chem Inf Model 61, 3172-3196.
Bhadra P, Yan J, Li J, et al. (2018) AmPEP: Sequence-based prediction of antimicrobial peptides using distribution patterns of amino acid properties and random forest. J Sci Rep 8, 1697
Bradley AP (1997) The use of the area under the ROC curve in the evaluation of machine learning algorithms. J Pattern Recognit 30, 1145-1159
Breiman L (2001) Random forests. J Mach Learn 45, 5-32
Cao DS, Xu QS, Liang YZ (2013) propy: a tool to generate various modes of Chou’s PseAAC. J Bioinform 29(7), 960–962
Chaudhary K, Kumar R, Singh S, et al. (2016) A web server and mobile app for computing hemolytic potency of peptides.J Sci Rep 6, 22843
Cherkasov A, Hilpert K, Jenssen H, et al. (2009) Use of artificial intelligence in the design of small peptide antibiotics effective against a broad spectrum of highly antibiotic-resistant superbugs.J ACS Chem Biol 4, 65-74
Cutler A, Cutler DR, Stevens JR (2012) Random Forests. In: Zhang, C., Ma, Y. (eds) Ensemble Machine Learning. Springer, New York, NY. https://doi.org/10.1007/978-1-4419-9326-7_5.
Dubos RJ (1939) Studies on a bactericidal agent extracted from a soil bacillus: I. Preparation of the agent. Its activity in vitro. J Exp Med 70, 1-10.
Feng Y, Xu J, Shi M, et al. (2022) COX7A1 enhances the sensitivity of human NSCLC cells to cystine deprivation-induced ferroptosis via regulating mitochondrial metabolism. J Cell Death Dis 13, e988
Gasteiger E, Hoogland C, Gattiker A, et al. (2005) Protein identification and analysis tools on the ExPASy server. J Springer https://doi.org/10.1385/1-59259-890-0:571.
Ghotbaldini H, Mohammadabadi MR, Nezamabadi-pour H, et al. (2019) Predicting breeding value of body weight at 6-month age using Artificial Neural Networks in Kermani sheep breed. Acta Scientiarum Anim Sci 41, e45282.  
Groves M, Peterson R, Kiddy C (1965) Polymorphism in the Red Protein isolated from Milk of Individual Cows. J Nature 207, 1007-1008.
Hirsch JG (1956) Phagocytin: a bactericidal substance from polymorphonuclear leucocytes. J Exp Med 103, 589.
Jafari A,Babajani A,Sarrami Forooshani R, et al. (2022) Clinical applications and anticancer effects of antimicrobial peptides: from bench to bedside. J Front Oncol 12, 819563.
Jamali AA, Ferdousi R, Razzaghi S, et al. (2016) DrugMiner: comparative analysis of machine learning algorithms for prediction of potential druggable proteins. J Drug Discov Today Technol 21, 718-724.
Khorshidi M, Mohammadabadi MR, Esmailizadeh AK, et al. (2019) Comparison of artificial neural network and regression models for prediction of body weight in Raini Cashmere goat. Iran J Appl Anim Sci 9 (3), 453-461.
Khosravian M, Kazemi Faramarzi F, Mohammad Beigi M, et al. (2013) Predicting antibacterial peptides by the concept of Chou's pseudo-amino acid composition and machine learning methods. J  Protein Pept Lett  20, 180-186
Khourdifi Y, Bahaj M (2018) Applying best machine learning algorithms for breast cancer prediction and classification. In: International conference on electronics, control, optimization and computer science.J ICECOCS. IEEE. pp. 1-5
Kiss G, Michl H (1962) Uber das Giftsekret der Gelbbauchunke, Bombina variegata L. J Toxicon 1, 33-34.
Kohavi R (1995) A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection. J IJCAI, Montreal, Canada. pp. 1137-1145.
Kumar K, Bhatnagar V (2021) Machine Learning Algorithms Performance Evaluation for Intrusion Detection. J Inf Technol Manag 13, 42-61.
Lee EY, Fulan BM, Wong GC, Ferguson AL (2016) Mapping membrane activity in undiscovered peptide sequence space using machine learning. J Proc Natl Acad Sci 113, 13588-13593.
Lin W, Xu D (2016) Imbalanced multi-label learning for identifying antimicrobial peptides and their functional types. J Bioinform 32, 3745-3752.
Marne S, Churi S, Marne M (2020) Predicting breast cancer using effective classification with decision tree and k means clustering technique. International Conference on Emerging Smart Computing and Informatics (ESCI). IEEE. pp. 39-42.
Meher PK, Sahu TK, Saini V, Rao AR (2017) Predicting antimicrobial peptides with improved accuracy by incorporating the compositional, physico-chemical and structural features into Chou’s general PseAAC. J Sci Rep 7, 42362.
Mohammadabadi M, Kheyrodin H, Afanasenko V, Babenko O, Klopenko N, Kalashnyk O, Ievstafiieva Y, Buchkovska V (2024) The role of artificial intelligence in genomics. Agricultural Biotechnology Journal 16 (2), 195-279) In Persian(.
Nguyen LT, Haney EF, Vogel HJ (2011) The expanding scope of antimicrobial peptide structures and their modes of action. J Trends Biotechnol 29, 464-472.
Pour Hamidi S, Mohammadabadi MR, Asadi Foozi M, Nezamabadi-pour H (2017) Prediction of breeding values for the milk production trait in Iranian Holstein cows applying artificial neural networks. J Livestock Sci Technol 5 (2), 53-61.
Safavian SR, Landgrebe D (1991) A survey of decision tree classifier methodology. J IEEE Trans Syst Man Cybern 21, 660-674
Schneider P, Müller AT, Gabernet G, et al. (2017) Hybrid network model for “deep learning” of chemical data: application to antimicrobial peptides. J Mol Inform 36, e1600011.
Söylemez UG, Yousef M, et al. (2023) Prediction of Antimicrobial Peptides Using Deep Neural Networks. In Proceedings of the 16th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2023) - Volume 3: BIOINFORMATICS, pages 188-194.
Su X, Xu J, Yin Y, et al. (2019) Antimicrobial peptide identification using multi-scale convolutional network. J BMC Bioinform 20, 1-10.
Wang G, Mishra B (2012) The importance of amino acid composition in natural AMPs: an evolutional, structural, and functional perspective. J Front Immunol 3, e31946
Wang P, Hu L, Liu G, et al. (2011) Prediction of antimicrobial peptides based on sequence alignment and feature selection methods. J PloS one 6, e18476
Yeaman MR, Yount NY (2003) Mechanisms of antimicrobial peptide action and resistance. J  Pharmacol Rev 55, 27-55.
Yin C, Zhu Y, Fei J, He X (2017) A deep learning approach for intrusion detection using recurrent neural networks. J IEEE Access 5, 21954-21961
Zare M, Mohabatkar H, Faramarzi FK, et al. (2015) Using Chou’s Pseudo Amino Acid Composition and Machine Learning Method to Predict the Antiviral Peptides. J Open Bioinform 9, 13-19.
Agricultural Biotechnology Journal
Volume 16, Issue 3
September 2024
Pages 89-110

Files

Share

How to cite

Statistics