HemoFuse: Multi-feature Fusion Based on Multi-head Cross-attention for Identification of Hemolytic Peptides

Overview

Journal Sci Rep

Specialty Science

Date 2024 Sep 28

PMID 39342017

Authors

Ya Zhao

Shengli Zhang

Yunyun Liang

Affiliations

Soon will be listed here.

Abstract

Hemolytic peptides are therapeutic peptides that damage red blood cells. However, therapeutic peptides used in medical treatment must exhibit low toxicity to red blood cells to achieve the desired therapeutic effect. Therefore, accurate prediction of the hemolytic activity of therapeutic peptides is essential for the development of peptide therapies. In this study, a multi-feature cross-fusion model, HemoFuse, for hemolytic peptide identification is proposed. The feature vectors of peptide sequences are transformed by word embedding technique and four hand-crafted feature extraction methods. We apply multi-head cross-attention mechanism to hemolytic peptide identification for the first time. It captures the interaction between word embedding features and hand-crafted features by calculating the attention of all positions in them, so that multiple features can be deeply fused. Moreover, we visualize the features obtained by this module to enhance its interpretability. On the comprehensive integrated dataset, HemoFuse achieves ideal results, with ACC, SP, SN, MCC, F1, AUC, and AP of 0.7575, 0.8814, 0.5793, 0.4909, 0.6620, 0.8387, and 0.7118, respectively. Compared with HemoDL proposed by Yang et al., it is 3.32%, 3.89%, 5.93%, 10.6%, 8.17%, 5.88%, and 2.72% higher. Other ablation experiments also prove that our model is reasonable and efficient. The codes and datasets are accessible at https://github.com/z11code/Hemo .

References

Bhasin M, Raghava G . ESLpred: SVM-based method for subcellular localization of eukaryotic proteins using dipeptide composition and PSI-BLAST. Nucleic Acids Res. 2004; 32(Web Server issue):W414-9. PMC: 441488. DOI: 10.1093/nar/gkh350. View

Shi H, Zhang S . Accurate Prediction of Anti-hypertensive Peptides Based on Convolutional Neural Network and Gated Recurrent unit. Interdiscip Sci. 2022; 14(4):879-894. DOI: 10.1007/s12539-022-00521-3. View

Zhu Y, Liu Z, Liu Y, Ji Z, Yu D . ULDNA: integrating unsupervised multi-source language models with LSTM-attention network for high-accuracy protein-DNA binding site prediction. Brief Bioinform. 2024; 25(2). PMC: 10939370. DOI: 10.1093/bib/bbae040. View

Hasan M, Schaduangrat N, Basith S, Lee G, Shoombuatong W, Manavalan B . HLPpred-Fuse: improved and robust prediction of hemolytic peptide and its activity by fusing multiple feature representation. Bioinformatics. 2020; 36(11):3350-3356. DOI: 10.1093/bioinformatics/btaa160. View

Pham N, Rakkiyapan R, Park J, Malik A, Manavalan B . H2Opred: a robust and efficient hybrid deep learning model for predicting 2'-O-methylation sites in human RNA. Brief Bioinform. 2024; 25(1). PMC: 10768780. DOI: 10.1093/bib/bbad476. View

Li Z, Fang J, Wang S, Zhang L, Chen Y, Pian C . Adapt-Kcr: a novel deep learning framework for accurate prediction of lysine crotonylation sites based on learning embedding features and attention architecture. Brief Bioinform. 2022; 23(2). DOI: 10.1093/bib/bbac037. View

Win T, Malik A, Prachayasittikul V, Wikberg J, Nantasenamat C, Shoombuatong W . HemoPred: a web server for predicting the hemolytic activity of peptides. Future Med Chem. 2017; 9(3):275-291. DOI: 10.4155/fmc-2016-0188. View

Du Z, Xu Y, Liu C, Li Y . pLM4Alg: Protein Language Model-Based Predictors for Allergenic Proteins and Peptides. J Agric Food Chem. 2023; 72(1):752-760. DOI: 10.1021/acs.jafc.3c07143. View

Li W, Godzik A . Cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics. 2006; 22(13):1658-9. DOI: 10.1093/bioinformatics/btl158. View

10.

Pirtskhalava M, Amstrong A, Grigolava M, Chubinidze M, Alimbarashvili E, Vishnepolsky B . DBAASP v3: database of antimicrobial/cytotoxic activity and structure of peptides as a resource for development of new therapeutics. Nucleic Acids Res. 2020; 49(D1):D288-D297. PMC: 7778994. DOI: 10.1093/nar/gkaa991. View

11.

Wang R, Feng Y, Sun M, Jiang Y, Li Z, Cui L . MVIL6: Accurate identification of IL-6-induced peptides using multi-view feature learning. Int J Biol Macromol. 2023; 246:125412. DOI: 10.1016/j.ijbiomac.2023.125412. View

12.

Yang S, Xu P . HemoDL: Hemolytic peptides prediction by double ensemble engines from Rich sequence-derived and transformer-enhanced information. Anal Biochem. 2024; 690:115523. DOI: 10.1016/j.ab.2024.115523. View

13.

Li A, Wang L, Shi Y, Wang M, Jiang Z, Feng H . Phosphorylation site prediction with a modified k-nearest neighbor algorithm and BLOSUM62 matrix. Conf Proc IEEE Eng Med Biol Soc. 2007; 2005:6075-8. DOI: 10.1109/IEMBS.2005.1615878. View

14.

Xing W, Zhang J, Li C, Huo Y, Dong G . iAMP-Attenpred: a novel antimicrobial peptide predictor based on BERT feature extraction method and CNN-BiLSTM-Attention combination model. Brief Bioinform. 2023; 25(1). PMC: 10699745. DOI: 10.1093/bib/bbad443. View

15.

Yu Y, Ding P, Gao H, Liu G, Zhang F, Yu B . Cooperation of local features and global representations by a dual-branch network for transcription factor binding sites prediction. Brief Bioinform. 2023; 24(2). DOI: 10.1093/bib/bbad036. View

16.

Hassan M, Tayara H, Chong K . Meta-IL4: An ensemble learning approach for IL-4-inducing peptide prediction. Methods. 2023; 217:49-56. DOI: 10.1016/j.ymeth.2023.07.002. View

17.

Chaudhary K, Kumar R, Singh S, Tuknait A, Gautam A, Mathur D . A Web Server and Mobile App for Computing Hemolytic Potency of Peptides. Sci Rep. 2016; 6:22843. PMC: 4782144. DOI: 10.1038/srep22843. View

18.

Kumar V, Kumar R, Agrawal P, Patiyal S, Raghava G . A Method for Predicting Hemolytic Potency of Chemically Modified Peptides From Its Structure. Front Pharmacol. 2020; 11:54. PMC: 7045810. DOI: 10.3389/fphar.2020.00054. View

19.

Jing Y, Zhang S, Wang H . DapNet-HLA: Adaptive dual-attention mechanism network based on deep learning to predict non-classical HLA binding sites. Anal Biochem. 2023; 666:115075. DOI: 10.1016/j.ab.2023.115075. View

20.

Wu X, Bartel D . kpLogo: positional k-mer analysis reveals hidden specificity in biological sequences. Nucleic Acids Res. 2017; 45(W1):W534-W538. PMC: 5570168. DOI: 10.1093/nar/gkx323. View