Current BioinformaticsCurrent BioinformaticsCurrent Bioinformatics1574-89362212-392XBentham Science64377510.2174/0115748936299044240202100019Life SciencesResearch ArticleCFCN: An HLA-peptide Prediction Model based on Taylor Extension Theory and Multi-view LearningRaoBinginfo@benthamscience.netHanBinginfo@benthamscience.netWeiLeyiinfo@benthamscience.netZhangZeyuinfo@benthamscience.netJiangXinboinfo@benthamscience.netManavalanBalachandraninfo@benthamscience.netSchool of Information and Electrical Engineering, Hangzhou City University, Beidahuang Industry Group General HospitalFaculty of Applied Sciences,, Macao Polytechnic UniversitySoftware Engineering, Shandong UniversitySchool of Qilu Transportation, Shandong University, Shandong UniversityDepartment of Integrative Biotechnology, College of Biotechnology and Bioengineering, Sungkyunkwan University01102024191097799007012025Copyright ©; 2024, Bentham Science Publishers2024Bentham Science Publishershttps://journals.eco-vector.com/1574-8936/article/view/643775

Background:With the increasing development of biotechnology, many cancer solutions have been proposed nowadays. In recent years, Neo-peptides-based methods have made significant contributions, with an essential prerequisite of bindings between peptides and HLA molecules. However, the binding is hard to predict, and the accuracy is expected to improve further.

Methods:Therefore, we propose the Crossed Feature Correction Network (CFCN) with deep learning method, which can automatically extract and adaptively learn the discriminative features in HLA-peptide binding, in order to make more accurate predictions on HLA-peptide binding tasks. With the fancy structure of encoding and feature extracting process for peptides, as well as the feature fusion process between fine-grained and coarse-grained level, it shows many advantages on given tasks.

Results:The experiment illustrates that CFCN achieves better performances overall, compared with other fancy models in many aspects.

Conclusion:In addition, we also consider to use multi-view learning methods for the feature fusion process, in order to find out further relations among binding features. Eventually, we encapsulate our model as a useful tool for further research on binding tasks.

HLA moleculesHLA-peptideleukocytetaylor extension theorymulti-view learningbiotechnology.Luo H, Ye H, Ng HW, Sakkiah S, Mendrick DL, Hong H. sNebula, a network-based algorithm to predict binding between human leukocyte antigens and peptides. Sci Rep 2016; 6(1): 32115. doi: 10.1038/srep32115 PMID: 27558848Cao C, Wang J, Kwok D, et al. webTWAS: A resource for disease candidate susceptibility genes identified by transcriptome-wide association study. Nucleic Acids Res 2022; 50(D1): D1123-30. doi: 10.1093/nar/gkab957 PMID: 34669946Nilsson JB, Kaabinejadian S, Yari H, et al. Accurate prediction of HLA class II antigen presentation across all loci using tailored data acquisition and refined machine learning. Sci Adv 2023; 9(47): eadj6367. doi: 10.1126/sciadv.adj6367 PMID: 38000035Mei S, Li F, Xiang D, et al. Anthem: A user customised tool for fast and accurate prediction of binding between peptides and HLA class I molecules. Brief Bioinform 2021; 22(5): bbaa415. doi: 10.1093/bib/bbaa415 PMID: 33454737Lundegaard C, Lund O, Buus S, Nielsen M. Major histocompatibility complex class I binding predictions as a tool in epitope discovery. Immunology 2010; 130(3): 309-18. doi: 10.1111/j.1365-2567.2010.03300.x PMID: 20518827Purcell AW, Ramarathinam SH, Ternette N. Mass spectrometry–based identification of MHC-bound peptides for immunopeptidomics. Nat Protoc 2019; 14(6): 1687-707. doi: 10.1038/s41596-019-0133-y PMID: 31092913Yu L, Yang K, He X, Li M, Gao L, Zha Y. Repositioning linifanib as a potent anti-necroptosis agent for sepsis. Cell Death Discov 2023; 9(1): 57. doi: 10.1038/s41420-023-01351-y PMID: 36765040Purcell AW, McCluskey J, Rossjohn J. More than one reason to rethink the use of peptides in vaccine design. Nat Rev Drug Discov 2007; 6(5): 404-14. doi: 10.1038/nrd2224 PMID: 17473845Cheng H, Rao B, Liu L, et al. PepFormer: End-to-End transformer-based siamese network to predict and enhance peptide detectability based on sequence only. Anal Chem 2021; 93(16): 6481-90. doi: 10.1021/acs.analchem.1c00354 PMID: 33843206Mei S, Li F, Leier A, et al. A comprehensive review and performance evaluation of bioinformatics tools for HLA class I peptide-binding prediction. Brief Bioinform 2020; 21(4): 1119-35. doi: 10.1093/bib/bbz051 PMID: 31204427Gupta S, Nerli S, Kutti Kandy S, Mersky GL, Sgourakis NG. HLA3DB: Comprehensive annotation of peptide/HLA complexes enables blind structure prediction of T cell epitopes. Nat Commun 2023; 14(1): 6349. doi: 10.1038/s41467-023-42163-z PMID: 37816745Wang R, Jiang Y, Jin J, et al. DeepBIO: An automated and interpretable deep-learning platform for high-throughput biological sequence prediction, functional annotation and visualization analysis. Nucleic Acids Res 2023; 51(7): 3017-29. doi: 10.1093/nar/gkad055 PMID: 36796796Jin J, Yu Y, Wang R, et al. iDNA-ABF: Multi-scale deep biological language learning model for the interpretable prediction of DNA methylations. Genome Biol 2022; 23(1): 219. doi: 10.1186/s13059-022-02780-1 PMID: 36253864Zeng X, Wang F, Luo Y, et al. Deep generative molecular design reshapes drug discovery. Cell Rep Med 2022; 3(12): 100794. doi: 10.1016/j.xcrm.2022.100794 PMID: 36306797Xu J. Graph embedding and Gaussian mixture variational autoencoder network for end-to-end analysis of single-cell RNA sequencing data. Cell Rep Methods 2023; 3(1): 100382.Li HL, Pang YH, Liu B. BioSeq-BLM: A platform for analyzing DNA, RNA and protein sequences based on biological language models. Nucleic Acids Res 2021; 49(22): e129. doi: 10.1093/nar/gkab829 PMID: 34581805Tang YJ, Pang YH, Liu B. IDP-Seq2Seq: Identification of intrinsically disordered regions based on sequence to sequence learning. Bioinformatics 2021; 36(21): 5177-86. doi: 10.1093/bioinformatics/btaa667 PMID: 32702119Chen L, Yu L, Gao L. Potent antibiotic design via guided search from antibacterial activity evaluations. Bioinformatics 2023; 39(2): btad059. doi: 10.1093/bioinformatics/btad059 PMID: 367079902023 Alzheimer’s disease facts and figures. Alzheimers Dement 2023; 19(4): 1598-695. doi: 10.1002/alz.13016 PMID: 36918389Hu Y, Sun J, Zhang Y, et al. rs1990622 variant associates with Alzheimer’s disease and regulates TMEM106B expression in human brain tissues. BMC Med 2021; 19(1): 11. doi: 10.1186/s12916-020-01883-5 PMID: 33461566Hu Y, Zhang H, Liu B, et al. rs34331204 regulates TSPAN13 expression and contributes to Alzheimer’s disease with sex differences. Brain 2020; 143(11): e95. doi: 10.1093/brain/awaa302 PMID: 33175954Hu Y, Zhang Y, Zhang H, et al. Mendelian randomization highlights causal association between genetically increased C‐reactive protein levels and reduced Alzheimer’s disease risk. Alzheimers Dement 2022; 18(10): 2003-6. doi: 10.1002/alz.12687 PMID: 35598332Hu Y, Zhang Y, Zhang H, et al. Cognitive performance protects against Alzheimer’s disease independently of educational attainment and intelligence. Mol Psychiatry 2022; 27(10): 4297-306. doi: 10.1038/s41380-022-01695-4 PMID: 35840796Liu G, Li D, Li Z, et al. PSSMHCpan: A novel PSSM-based software for predicting class I peptide-HLA binding affinity. Gigascience 2017; 6(5): 1-11. doi: 10.1093/gigascience/gix017 PMID: 28327987Bassani-Sternberg M, Chong C, Guillaume P, et al. Deciphering HLA-I motifs across HLA peptidomes improves neo-antigen predictions and identifies allostery regulating HLA specificity. PLOS Comput Biol 2017; 13(8): e1005725. doi: 10.1371/journal.pcbi.1005725 PMID: 28832583Rammensee HG, Bachmann J, Emmerich NPN, Bachor OA, Stevanović S. SYFPEITHI: database for MHC ligands and peptide motifs. Immunogenetics 1999; 50(3-4): 213-9. doi: 10.1007/s002510050595 PMID: 10602881Reche PA, Glutting JP, Reinherz EL. Prediction of MHC class I binding peptides using profile motifs. Hum Immunol 2002; 63(9): 701-9. doi: 10.1016/S0198-8859(02)00432-9 PMID: 12175724Zhang H, Lund O, Nielsen M. The PickPocket method for predicting binding specificities for receptors based on receptor pocket similarities: Application to MHC-peptide binding. Bioinformatics 2009; 25(10): 1293-9. doi: 10.1093/bioinformatics/btp137 PMID: 19297351Andreatta M, Nielsen M. Gapped sequence alignment using artificial neural networks: Application to the MHC class I system. Bioinformatics 2016; 32(4): 511-7. doi: 10.1093/bioinformatics/btv639 PMID: 26515819Wu J, Wang W, Zhang J, et al. DeepHLApan: A deep learning approach for neoantigen prediction considering both HLA-peptide binding and immunogenicity. Front Immunol 2019; 10: 2559. doi: 10.3389/fimmu.2019.02559 PMID: 31736974Chen J, Zou Q, Li J. DeepM6ASeq-EL: Prediction of human N6-methyladenosine (m6A) sites with LSTM and ensemble learning. Front Comput Sci 2022; 16(2): 162302. doi: 10.1007/s11704-020-0180-0Ye Y, Wang J, Xu Y, et al. MATHLA: A robust framework for HLA-peptide binding prediction integrating bidirectional LSTM and multiple head attention mechanism. BMC Bioinformatics 2021; 22(1): 7. doi: 10.1186/s12859-020-03946-z PMID: 33407098Liu Z, Cui Y, Xiong Z, Nasiri A, Zhang A, Hu J. DeepSeqPan, a novel deep convolutional neural network model for pan-specific class I HLA-peptide binding affinity prediction. Sci Rep 2019; 9(1): 794. doi: 10.1038/s41598-018-37214-1 PMID: 30692623Rasmussen M, Fenoy E, Harndahl M, et al. Pan-specific prediction of peptide–MHC class I complex stability, a correlate of T cell immunogenicity. J Immunol 2016; 197(4): 1517-24. doi: 10.4049/jimmunol.1600582 PMID: 27402703Bhattacharya R. Prediction of peptide binding to MHC Class I proteins in the age of deep learning. BioRxiv 2017; 154757.O'Donnell TJ. MHCflurry: Open-source class I MHC binding affinity prediction. Cell systems 2018; 7(1): 129-32. e4 doi: 10.1016/j.cels.2018.05.014Han Y, Kim D. Deep convolutional neural networks for pan-specific peptide-MHC class I binding prediction. BMC Bioinformatics 2017; 18(1): 585. doi: 10.1186/s12859-017-1997-x PMID: 29281985Vang YS, Xie X. HLA class I binding prediction via convolutional neural networks. Bioinformatics 2017; 33(17): 2658-65. doi: 10.1093/bioinformatics/btx264 PMID: 28444127Luo X, Chi W, Deng M. Deepprune: Learning efficient and interpretable convolutional networks through weight pruning for predicting dna-protein binding. Front Genet 2019; 10: 1145. doi: 10.3389/fgene.2019.01145 PMID: 31824562Luo X, Tu X, Ding Y, Gao G, Deng M. Expectation pooling: An effective and interpretable pooling method for predicting DNA–protein binding. Bioinformatics 2020; 36(5): 1405-12. doi: 10.1093/bioinformatics/btz768 PMID: 31598637Karosiene E, Lundegaard C, Lund O, Nielsen M. NetMHCcons: A consensus method for the major histocompatibility complex class I predictions. Immunogenetics 2012; 64(3): 177-86. doi: 10.1007/s00251-011-0579-8 PMID: 22009319Zhang C, Liu Y, Fu H. Ae2-nets: Autoencoder in autoencoder networks. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 15-20 June 2019; Long Beach, CA, USA. 2019.Dhanda SK, Mahajan S, Paul S, et al. IEDB-AR: Immune epitope database—analysis resource in 2019. Nucleic Acids Res 2019; 47(W1): W502-6. doi: 10.1093/nar/gkz452 PMID: 31114900Neefjes J, Jongsma MLM, Paul P, Bakke O. Towards a systems understanding of MHC class I and MHC class II antigen presentation. Nat Rev Immunol 2011; 11(12): 823-36. doi: 10.1038/nri3084 PMID: 22076556Thomas G, Finney R. Calculus and Analytic Geometry. Reading, MA: Addison-Wesley Publishing 1996.Kline M. Calculus: an intuitive and physical approach. Courier Corporation 1998.Zhang C, Cui Y, Han Z, Zhou JT, Fu H, Hu Q. Deep partial multi-view learning. IEEE Trans Pattern Anal Mach Intell 2020; 44(3): 2402-15. doi: 10.1109/TPAMI.2020.3037734 PMID: 33180720Wang Y, Pang C, Wang Y, et al. Retrosynthesis prediction with an interpretable deep-learning framework based on molecular assembly tasks. Nat Commun 2023; 14(1): 6155. doi: 10.1038/s41467-023-41698-5 PMID: 37788995Li H, Liu B. BioSeq-Diabolo: Biological sequence similarity analysis using Diabolo. PLOS Comput Biol 2023; 19(6): e1011214. doi: 10.1371/journal.pcbi.1011214 PMID: 37339155Xu C, Tao D, Xu C. A survey on multi-view learning. ar Xiv:13045634 2013.Dao FY, Liu ML, Su W, et al. AcrPred: A hybrid optimization with enumerated machine learning algorithm to predict Anti-CRISPR proteins. Int J Biol Macromol 2023; 228: 706-14. doi: 10.1016/j.ijbiomac.2022.12.250 PMID: 36584777Dao FY, Lv H, Fullwood MJ, Lin H. Accurate identification of DNA replication origin by fusing epigenomics and chromatin interaction information. Research 2022; 2022: 2022/9780293. doi: 10.34133/2022/9780293 PMID: 36405252Ao C, Ye X, Sakurai T, Zou Q, Yu L. m5U-SVM: Identification of RNA 5-methyluridine modification sites based on multi-view features of physicochemical features and distributed representation. BMC Biol 2023; 21(1): 93. doi: 10.1186/s12915-023-01596-0 PMID: 37095510Wang Y, Zhai Y, Ding Y, Zou Q. SBSM-Pro: Support bio-sequence machine for proteins. arXiv:230810275 2023.Qian Y, Ding Y, Zou Q, Guo F. Multi-view kernel sparse representation for identification of membrane protein types. IEEE/ACM Trans Comput Biol Bioinformatics 2023; 20(2): 1234-45. doi: 10.1109/TCBB.2022.3191325 PMID: 35857734Liu X, Yang H, Ai C, Ding Y, Guo F, Tang J. MVML-MPI: Multi-view multi-label learning for metabolic pathway inference. Brief Bioinform 2023; 24(6): bbad393. PMID: 37930024Liang C, Wang L, Liu L, Zhang H, Guo F. Multi-view unsupervised feature selection with tensor robust principal component analysis and consensus graph learning. Pattern Recognit 2023; 141: 109632. doi: 10.1016/j.patcog.2023.109632Liu J. Multi-view clustering via joint nonnegative matrix factorization. Proceedings of the 2013 SIAM international conference on data mining 252-60. doi: 10.1137/1.9781611972832.28Kumar A, Rai P, Daume H. Co-regularized multi-view spectral clustering. Adv Neural Inf Process Syst 2011; 24: 1413-21.Zeng X, Xiang H, Yu L, et al. Accurate prediction of molecular properties and drug targets using a self-supervised image representation learning framework. Nat Mach Intell 2022; 4(11): 1004-16. doi: 10.1038/s42256-022-00557-6Hotelling H. Relations between two sets of variates Breakthroughs in statistics. Springer 1992; pp. 162-90. doi: 10.1007/978-1-4612-4380-9_14Akaho S. A kernel method for canonical correlation analysis. arXiv preprint cs/0609071 2006.Andrew G, Raman A, Jeff B, Karen LP. Deep canonical correlation analysis Proceedings of the 30th International Conference on Machine Learning, PMLR. 1247-55.Song J, Li F, Leier A, et al. PROSPERous: High-throughput prediction of substrate cleavage sites for 90 proteases with improved accuracy. Bioinformatics 2018; 34(4): 684-7. doi: 10.1093/bioinformatics/btx670 PMID: 29069280Agarap AF. Deep learning using rectified linear units (relu). ar Xiv:180308375 2018.He S, Ye X, Sakurai T, Zou Q. MRMD3.0: A Python tool and webserver for dimensionality reduction and data visualization via an ensemble strategy. J Mol Biol 2023; 435(14): 168116. doi: 10.1016/j.jmb.2023.168116 PMID: 37356901Bradley AP. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit 1997; 30(7): 1145-59. doi: 10.1016/S0031-3203(96)00142-2Yan K, Lv H, Guo Y, Peng W, Liu B. sAMPpred-GAT: prediction of antimicrobial peptide by graph attention network and predicted peptide structure. Bioinformatics 2023; 39(1): btac715. doi: 10.1093/bioinformatics/btac715 PMID: 36342186Jin Huang, Ling CX. Using AUC and accuracy in evaluating learning algorithms. IEEE Trans Knowl Data Eng 2005; 17(3): 299-310. doi: 10.1109/TKDE.2005.50Matthews BW. Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta Protein Struct 1975; 405(2): 442-51. doi: 10.1016/0005-2795(75)90109-9 PMID: 1180967Zou X, Ren L, Cai P, et al. Accurately identifying hemagglutinin using sequence information and machine learning methods. Front Med 2023; 10: 1281880. doi: 10.3389/fmed.2023.1281880 PMID: 38020152Zhu W, Yuan SS, Li J, Huang CB, Lin H, Liao B. A first computational frame for recognizing heparin-binding protein. Diagnostics 2023; 13(14): 2465. doi: 10.3390/diagnostics13142465 PMID: 37510209Liu B, Gao X, Zhang H. BioSeq-Analysis2.0: An updated platform for analyzing DNA, RNA and protein sequences at sequence level and residue level based on machine learning approaches. Nucleic Acids Res 2019; 47(20): e127. doi: 10.1093/nar/gkz740 PMID: 31504851