A deep learning model for anti-inflammatory peptides identification based on deep variational autoencoder and contrastive learning.
Anti-inflammatory peptides
Contrastive learning
Deep variational autoencoder
Multi-hot
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
08 Aug 2024
08 Aug 2024
Historique:
received:
24
05
2024
accepted:
05
08
2024
medline:
9
8
2024
pubmed:
9
8
2024
entrez:
8
8
2024
Statut:
epublish
Résumé
As a class of biologically active molecules with significant immunomodulatory and anti-inflammatory effects, anti-inflammatory peptides have important application value in the medical and biotechnology fields due to their unique biological functions. Research on the identification of anti-inflammatory peptides provides important theoretical foundations and practical value for a deeper understanding of the biological mechanisms of inflammation and immune regulation, as well as for the development of new drugs and biotechnological applications. Therefore, it is necessary to develop more advanced computational models for identifying anti-inflammatory peptides. In this study, we propose a deep learning model named DAC-AIPs based on variational autoencoder and contrastive learning for accurate identification of anti-inflammatory peptides. In the sequence encoding part, the incorporation of multi-hot encoding helps capture richer sequence information. The autoencoder, composed of convolutional layers and linear layers, can learn latent features and reconstruct features, with variational inference enhancing the representation capability of latent features. Additionally, the introduction of contrastive learning aims to improve the model's classification ability. Through cross-validation and independent dataset testing experiments, DAC-AIPs achieves superior performance compared to existing state-of-the-art models. In cross-validation, the classification accuracy of DAC-AIPs reached around 88%, which is 7% higher than previous models. Furthermore, various ablation experiments and interpretability experiments validate the effectiveness of DAC-AIPs. Finally, a user-friendly online predictor is designed to enhance the practicality of the model, and the server is freely accessible at http://dac-aips.online .
Identifiants
pubmed: 39117712
doi: 10.1038/s41598-024-69419-y
pii: 10.1038/s41598-024-69419-y
doi:
Substances chimiques
Anti-Inflammatory Agents
0
Peptides
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
18451Subventions
Organisme : Natural Science Basic Research Program of Shaanxi
ID : 2024JC-YBMS-004
Organisme : Xidian University Specially Funded Project for Interdisciplinary Exploration
ID : TZJH2024028
Organisme : National Natural Science Foundation of China
ID : 12101480
Informations de copyright
© 2024. The Author(s).
Références
Dadar, M. et al. Antiinflammatory peptides: Current knowledge and promising prospects. Inflamm. Res. 68, 125–145 (2019).
pubmed: 30560372
doi: 10.1007/s00011-018-1208-x
La Manna, S., Di Natale, C., Florio, D. & Marasco, D. Peptides as therapeutic agents for inflammatory-related diseases. Int. J. Mol. Sci. 19, 2714 (2018).
pubmed: 30208640
pmcid: 6163503
doi: 10.3390/ijms19092714
Zhao, L., Wang, X., Zhang, X. L. & Xie, Q. F. Purification and identification of anti-inflammatory peptides derived from simulated gastrointestinal digests of velvet antler protein (Cervus elaphus Linnaeus). J. Food Drug Anal. 24, 376–384 (2016).
pubmed: 28911592
pmcid: 9339547
doi: 10.1016/j.jfda.2015.10.003
Marie, C., Pitton, C., Fitting, C. & Cavaillon, J. M. Regulation by anti-inflammatory cytokines (IL-4, IL-10, IL-13, TGFbeta) of interleukin-8 production by LPS- and/or TNFalpha-activated human polymorphonuclear cells. Mediators Inflamm. 5, 334–340 (1996).
pubmed: 18475727
pmcid: 2365804
doi: 10.1155/S0962935196000488
Delgado, M., Abad, C., Martinez, C., Leceta, J. & Gomariz, R. P. Vasoactive intestinal peptide prevents experimental arthritis by downregulating both autoimmune and inflammatory components of the disease. Nat. Med. 7, 563–568 (2001).
pubmed: 11329057
doi: 10.1038/87887
Majumder, K., Mine, Y. & Wu, J. The potential of food proteinderived anti-inflammatory peptides against various chronic inflammatory diseases. J. Sci. Food Agric. 96, 2303–2311 (2015).
doi: 10.1002/jsfa.7600
Gokhale, A. S. & Satyanarayanajois, S. Peptides and peptidomimetics as immunomodulators. Immunotherapy. 6, 755–774 (2014).
pubmed: 25186605
doi: 10.2217/imt.14.37
Muntjewerff, E. M. et al. The anti-inflammatory peptide Catestatin blocks chemotaxis. J. Leukoc. Biol. 112, 273–278 (2022).
pubmed: 34939227
doi: 10.1002/JLB.3CRA1220-790RR
Vidal, C. et al. Licofelone, a balanced inhibitor of cyclooxygenase and 5-lipoxygenase, reduces inflammation in a rabbit model of atherosclerosis. J. Pharmacol. Exp. Ther. 320, 108–116 (2007).
pubmed: 17015640
doi: 10.1124/jpet.106.110361
Delgado, M. & Ganea, D. Anti-inflammatory neuropeptides: A new class of endogenous immunoregulatory agents. Brain Behav. Immun. 22, 1146–1151 (2008).
pubmed: 18598752
pmcid: 2784101
doi: 10.1016/j.bbi.2008.06.001
Downer, E. J. et al. A synthetic NCAM-derived mimetic peptide, FGL, exerts anti-inflammatory properties via IGF-1 and interferon-gamma modulation. J. Neurochem. 109, 1516–1525 (2009).
pubmed: 19457161
doi: 10.1111/j.1471-4159.2009.06076.x
Mookherjee, N. & Hancock, R. E. Cationic host defence peptides: innate immune regulatory peptides as a novel approach for treating infections. Cell Mol. Life Sci. 64, 922–933 (2007).
pubmed: 17310278
pmcid: 11136131
doi: 10.1007/s00018-007-6475-6
Khan, S. et al. Optimized feature learning for anti-inflammatory peptide prediction using parallel distributed computing. Appl. Sci. 13, 7059 (2023).
doi: 10.3390/app13127059
Kumar, N. & Yin, C. The anti-inflammatory peptide Ac-SDKP: Synthesis, role in ACE inhibition, and its therapeutic potential in hypertension and cardiovascular diseases. Pharmacol. Res. 134, 268–279 (2018).
pubmed: 29990624
doi: 10.1016/j.phrs.2018.07.006
Rivera-Jiménez, J. et al. Peptides and protein hydrolysates exhibiting anti-inflammatory activity: Sources, structural features and modulation mechanisms. Food Funct. 13, 12510–12540 (2022).
pubmed: 36420754
doi: 10.1039/D2FO02223K
Cicero, A. F. G., Fogacci, F. & Colletti, A. Potential role of bioactive peptides in prevention and treatment of chronic diseases: A narrative review. Br. J. Pharmacol. 174, 1378–1394 (2017).
pubmed: 27572703
doi: 10.1111/bph.13608
Gupta, S., Sharma, A. K., Shastri, V., Madhu, M. K. & Sharma, V. K. Prediction of anti-inflammatory proteins/peptides: An insilico approach. J. Transl. Med. 15, 7 (2017).
pubmed: 28057002
pmcid: 5216551
doi: 10.1186/s12967-016-1103-6
Manavalan, B., Shin, T. H., Kim, M. O. & Lee, G. AIPpred: sequence-based prediction of anti-inflammatory peptides using random forest. Front. Pharmacol. 9, 276 (2018).
pubmed: 29636690
pmcid: 5881105
doi: 10.3389/fphar.2018.00276
Khatun, M. S., Hasan, M. M. & Kurata, H. PreAIP: Computational prediction of anti-inflammatory peptides by integrating multiple complementary features. Front. Genet. 10, 129 (2019).
pubmed: 30891059
pmcid: 6411759
doi: 10.3389/fgene.2019.00129
Zhang, J., Zhang, Z., Pu, L., Tang, J. & Guo, F. AIEpred: An ensemble predictive model of classifier chain to identify anti-inflammatory peptides. IEEE/ACM Trans. Comput. Biol. Bioinform. 18, 1831–1840 (2021).
pubmed: 31985437
doi: 10.1109/TCBB.2020.2968419
Leyi, W., Chen, Z., Ran, S. & Quan, Z. PEPred-Suite: Improved and robust prediction of therapeutic peptides using adaptive feature representation learning. Bioinformatics. 35, 4272–4280 (2019).
doi: 10.1093/bioinformatics/btz246
Zhang, Y. P. & Zou, Q. PPTPP: A novel therapeutic peptide prediction method using physicochemical property encoding and adaptive feature representation learning. Bioinformatics. 36, 3982–3987 (2020).
pubmed: 32348463
doi: 10.1093/bioinformatics/btaa275
Yichen, G., Ke, Y., Hongwu, L. V. & Bin, L. PreTP-EL: prediction of therapeutic peptides based on ensemble learning. Brief. Bioinform. 22, bbab358 (2021).
doi: 10.1093/bib/bbab358
Ke, Y. et al. PreTP-Stack: Prediction of therapeutic peptide based on the stacked ensemble learning. IEEE/ACM Trans. Comput. Biol. Bioinform. 20, 1337–1344 (2022).
Zhao, D., Teng, Z., Li, Y. & Chen, D. iAIPs: Identifying anti-inflammatory peptides using random forest. Front. Genet. 12, 773202 (2021).
pubmed: 34917130
pmcid: 8669811
doi: 10.3389/fgene.2021.773202
Wang, R. et al. DeepBIO: an automated and interpretable deep-learning platform for high-throughput biological sequence prediction, functional annotation and visualization analysis. Nucleic Acids Res. 51, 3017–3029 (2023).
pubmed: 36796796
pmcid: 10123094
doi: 10.1093/nar/gkad055
Shi, H. Y., Zhang, S. L. & Li, X. J. R5hmCFDV: Computational identification of RNA 5-hydroxymethylcytosine based on deep feature fusion and deep voting. Brief. Bioinform. 23, bbac341 (2022).
pubmed: 35945157
doi: 10.1093/bib/bbac341
Zhang, S. L., Zhao, Y. & Liang, Y. Y. AMP-EF: An ensemble framework of extreme gradient boosting and bidirectional long short-term memory network for identifying antimicrobial peptides. Match-Commun. Math. Comput. Chem. 91, 109–131 (2023).
doi: 10.46793/match.91-1.109Z
Zhang S. L., Jing Y. Y. & Liang Y. Y. EACVP: An ESM-2 LM framework combined CNN and CBAM attention to predict anti-coronavirus Peptides. Curr. Med. Chem. (2024) (Epub ahead of print).
Mui-zzud-din, et al. Predicting skin cancer melanoma using stacked convolutional neural networks model. Multimed. Tools Appl. 83, 9503–9522 (2024).
doi: 10.1007/s11042-023-15488-6
Yanbu, G., Dongming, Z., Pu, L., Chaoyang, L. & Jinde, C. Context-aware poly(A) signal prediction model via deep spatial-temporal neural networks. IEEE Trans. Neural Netw. Learn. Syst. 35, 8241–8253 (2024).
doi: 10.1109/TNNLS.2022.3226301
Weihua, L., Yanbu, G., Bingyi, W. & Bei, Y. cLearning spatiotemporal embedding with gated convolutional recurrent networks for translation initiation site prediction. Pattern Recogn. 136, 0031–3203 (2023).
Shaoliang, Y., Dongming, Z., Jinde, C. & Yanbu, G. LightingNet: An integrated learning method for low-light image enhancement. IEEE Trans. Comput. Imaging. 9, 29–42 (2023).
doi: 10.1109/TCI.2023.3240087
Raza, A. et al. AIPs-SnTCN: Predicting anti-inflammatory peptides using fasttext and transformer encoder-based hybrid word embedding with self-normalized temporal convolutional networks. J. Chem. Inf. Model. 63, 6537–6554 (2023).
pubmed: 37905969
doi: 10.1021/acs.jcim.3c01563
Guan, J. et al. Predicting anti-inflammatory peptides by ensemble machine learning and deep learning. J. Chem. Inf. Model. 63, 7886–7898 (2023).
pubmed: 38054927
doi: 10.1021/acs.jcim.3c01602
Gaffar, S., Hassan, M. T., Tayara, H. & Chong, K. T. IF-AIP: A machine learning method for the identification of anti-inflammatory peptides using multi-feature fusion strategy. Comput. Biol. Med. 168, 107724 (2024).
pubmed: 37989075
doi: 10.1016/j.compbiomed.2023.107724
Fu, L., Niu, B., Zhu, Z., Wu, S. & Li, W. CD-HIT: Accelerated for clustering the next-generation sequencing data. Bioinformatics. 28, 3150–3152 (2012).
pubmed: 23060610
pmcid: 3516142
doi: 10.1093/bioinformatics/bts565
Al-Shehari, T. & Alsowail, R. A. An insider data leakage detection using one-hot encoding, synthetic minority oversampling and machine learning techniques. Entropy 23, 1258 (2021).
pubmed: 34681982
pmcid: 8535057
doi: 10.3390/e23101258
Okada, S., Ohzeki, M. & Taguchi, S. Efficient partition of integer optimization problems with one-hot encoding. Sci. Rep. 9, 13036 (2019).
pubmed: 31506502
pmcid: 6737027
doi: 10.1038/s41598-019-49539-6
Zhao, J. et al. CNNArginineMe: A CNN structure for training models for predicting arginine methylation sites based on the One-Hot encoding of peptide sequence. Front. Genet. 13, 1036862 (2022).
pubmed: 36324513
pmcid: 9618650
doi: 10.3389/fgene.2022.1036862
Li, P., Yan, P. & Li, J. A comprehensive survey on design and application of autoencoder in deep learning. Appl. Soft Comput. 138, 110176 (2023).
doi: 10.1016/j.asoc.2023.110176
Zhai J., Zhang S., Chen J. & He Q. Autoencoder and its various variants. In IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan. Vol. 2018, 415–419 (2018).
Kingma D. P., Welling M. Auto-encoding variational bayes. arXiv preprint. arXiv:1312.6114 (2013).
Doersch C. Tutorial on variational autoencoders. arXiv preprint. arXiv:1606.05908 (2016).
Oord A., Li Y., Vinyals O. Representation learning with contrastive predictive coding. arXiv preprint. arXiv:1807.03748 (2018).
Zhang S. L., Xu Y. J., Jing Y. Y., Liang Y. Y. TNFIPs-Net: A deep learning model based on multi-feature fusion for prediction of TNF-α inducing epitopes. In 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Istanbul, Turkiye. Vol. 2023, 978–983 (2023).
Zhang, S. L., Xu, Y. J. & Liang, Y. Y. TMSC-m7G: A transformer architecture based on multi-sense-scaled embedding features and convolutional neural network to identify RNA N7-methylguanosine sites. Comput. Struct. Biotechnol. J. 23, 129–139 (2024).
pubmed: 38089465
doi: 10.1016/j.csbj.2023.11.052
Zhang, S. L. & Jing, Y. Y. PreVFs-RG: A deep hybrid model for identifying virulence factors based on residual block and gated recurrent unit. IEEE/ACM Trans. Comput. Biol. Bioinform. 20, 1926–1934 (2023).
pubmed: 36399585
doi: 10.1109/TCBB.2022.3223038
Li, X. J., Zhang, S. L. & Shi, H. Y. An improved residual network using deep fusion for identifying RNA 5-methylcytosine sites. Bioinformatics. 38, 4271–4277 (2022).
pubmed: 35866985
doi: 10.1093/bioinformatics/btac532
Fang, Y. et al. AFP-MFL: Accurate identification of antifungal peptides using multi-view feature learning. Brief. Bioinform. 24, 606 (2023).
doi: 10.1093/bib/bbac606
Akiba T., Sano S., Yanase T., Ohta T. & Koyama M. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Vol. 2019, 2623–2631 (2019).
Alberguez M. & Wong Y. P. The tree-structured parzen estimator. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI-10). 1607–1612 (2010).
Mcinnes, L. & Healy, J. UMAP: Uniform manifold approximation and projection for dimension reduction. J. Open Source Softw. 3, 861 (2018).
doi: 10.21105/joss.00861
Li, Z. et al. ExamPle: explainable deep learning framework for the prediction of plant small secreted peptides. Bioinformatics. 39, btad108 (2023).
pubmed: 36897030
pmcid: 10027287
doi: 10.1093/bioinformatics/btad108
Wu, X. & Bartel, D. P. kpLogo: Positional k-mer analysis reveals hidden specificity in biological sequences. Nucleic Acids Res. 45, W534-538 (2017).
pubmed: 28460012
pmcid: 5570168
doi: 10.1093/nar/gkx323