Treffer: A deep learning model for prediction of lysine crotonylation sites by fusing multi-features based on multi-head self-attention mechanism.

Title:
A deep learning model for prediction of lysine crotonylation sites by fusing multi-features based on multi-head self-attention mechanism.
Authors:
Liang Y; School of Science, Xi'an Polytechnic University, Xi'an, 710048, People's Republic of China. yunyunliang88@163.com., Li M; School of Science, Xi'an Polytechnic University, Xi'an, 710048, People's Republic of China.
Source:
Scientific reports [Sci Rep] 2025 May 29; Vol. 15 (1), pp. 18940. Date of Electronic Publication: 2025 May 29.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Nature Publishing Group Country of Publication: England NLM ID: 101563288 Publication Model: Electronic Cited Medium: Internet ISSN: 2045-2322 (Electronic) Linking ISSN: 20452322 NLM ISO Abbreviation: Sci Rep Subsets: MEDLINE
Imprint Name(s):
Original Publication: London : Nature Publishing Group, copyright 2011-
MeSH Terms:
Deep Learning* , Lysine*/metabolism , Protein Processing, Post-Translational*, Neural Networks, Computer ; Humans ; Histones/metabolism ; Natural Language Processing
References:
IEEE/ACM Trans Comput Biol Bioinform. 2022 Nov-Dec;19(6):3624-3634. (PMID: 34546927)
Sci Rep. 2020 Nov 24;10(1):20447. (PMID: 33235255)
Cell Death Dis. 2021 Jul 14;12(7):703. (PMID: 34262024)
Bioinformatics. 2022 Jan 12;38(3):648-654. (PMID: 34643684)
Brief Bioinform. 2021 Nov 5;22(6):. (PMID: 34002774)
Epigenetics Chromatin. 2021 Feb 6;14(1):10. (PMID: 33549150)
Bioinformatics. 2022 Sep 15;38(18):4271-4277. (PMID: 35866985)
Mol Ther. 2022 Aug 3;30(8):2856-2867. (PMID: 35526094)
Brief Bioinform. 2022 Jan 17;23(1):. (PMID: 34864888)
Brief Bioinform. 2022 Sep 20;23(5):. (PMID: 35945157)
IEEE J Biomed Health Inform. 2020 Oct;24(10):3012-3019. (PMID: 32142462)
Bioinformatics. 2010 Mar 1;26(5):680-2. (PMID: 20053844)
Brief Bioinform. 2022 May 13;23(3):. (PMID: 35438149)
Cell. 2014 Oct 9;159(2):458-458.e1. (PMID: 25303536)
Cell Res. 2017 Jul;27(7):898-915. (PMID: 28497810)
Comput Struct Biotechnol J. 2022 Jun 16;20:3268-3279. (PMID: 35832615)
Artif Intell Med. 2017 Nov;83:75-81. (PMID: 28283358)
Anal Biochem. 2020 Nov 15;609:113903. (PMID: 32805274)
Proc Natl Acad Sci U S A. 2018 Mar 6;115(10):2365-2370. (PMID: 29463709)
PLoS One. 2019 Nov 21;14(11):e0223993. (PMID: 31751380)
Genomics. 2018 Sep;110(5):239-246. (PMID: 29107015)
Comput Struct Biotechnol J. 2022 Dec 01;21:120-127. (PMID: 36544479)
Brief Bioinform. 2022 Sep 20;23(5):. (PMID: 35988921)
Mol Cell Biochem. 1973 Nov 15;2(1):3-14. (PMID: 4587539)
Brief Bioinform. 2022 Jul 18;23(4):. (PMID: 35667011)
IEEE/ACM Trans Comput Biol Bioinform. 2023 May-Jun;20(3):1926-1934. (PMID: 36399585)
Sci Adv. 2020 Mar 13;6(11):eaay4697. (PMID: 32201722)
Front Med (Lausanne). 2023 Oct 31;10:1281880. (PMID: 38020152)
J Mol Biol. 2022 Jun 15;434(11):167549. (PMID: 35662472)
IEEE Trans Pattern Anal Mach Intell. 2023 Jun;45(6):7933-7938. (PMID: 36441895)
Brief Bioinform. 2021 Jul 20;22(4):. (PMID: 33099604)
Anal Bioanal Chem. 2018 Jul;410(17):4051-4060. (PMID: 29637251)
J Biosci. 2020;45:. (PMID: 33184251)
Nature. 2021 Aug;596(7873):583-589. (PMID: 34265844)
IEEE/ACM Trans Comput Biol Bioinform. 2021 Mar-Apr;18(2):784-789. (PMID: 32224462)
Annu Rev Biochem. 1981;50:783-814. (PMID: 6791580)
Brief Bioinform. 2022 Mar 10;23(2):. (PMID: 35189635)
J Mol Graph Model. 2017 Oct;77:200-204. (PMID: 28886434)
Cell. 2011 Sep 16;146(6):1016-28. (PMID: 21925322)
Brief Bioinform. 2021 Nov 5;22(6):. (PMID: 34037687)
Nucleic Acids Res. 2008 Jan;36(Database issue):D202-5. (PMID: 17998252)
J Clin Invest. 2018 Mar 1;128(3):1190-1198. (PMID: 29457784)
Brief Bioinform. 2022 Jan 17;23(1):. (PMID: 34882222)
Brief Bioinform. 2023 Jan 19;24(1):. (PMID: 36631407)
Mol Cell. 2017 Sep 7;67(5):853-866.e5. (PMID: 28803779)
Grant Information:
12101480 National Natural Science Foundation of China; QTZX23002 Fundamental Research Funds for the Central Universities
Contributed Indexing:
Keywords: Bidirectional gated recurrent unit; Convolutional neural network; Hand-crafted features; Lysine crotonylation sites; Multi-head self-attention mechanism; Natural Language processing
Substance Nomenclature:
K3Z4F929H6 (Lysine)
0 (Histones)
Entry Date(s):
Date Created: 20250529 Date Completed: 20250529 Latest Revision: 20250601
Update Code:
20250601
PubMed Central ID:
PMC12122789
DOI:
10.1038/s41598-025-04058-5
PMID:
40442183
Database:
MEDLINE

Weitere Informationen

Lysine crotonylation (Kcr) is an important post-translational modification, which is present in both histone and non-histone proteins, and plays a key role in a variety of biological processes such as metabolism and cell differentiation. Therefore, rapid and accurate identification of this modification has become a key task to study its biological effects. In the past few years, some calculation methods have been developed, but there is room for improvement in prediction performance. In this paper, we propose an effective model named DeepMM-Kcr, which is based on multiple features and an innovative deep learning framework. Multiple features are extracted from natural language processing features and hand-crafted features, where natural language processing features include token embedding and positional embedding encoded by transformer, and hand-crafted features include one-hot, amino acid index and position-weighted amino acid composition, and encoded by bidirectional long short-term memory network. Then natural language processing features and hand-crafted features are fusing by multi-head self-attention mechanism. Finally, a deep learning framework is constructed based on convolutional neural network, bidirectional gated recurrent unit and multilayer perceptron for robust prediction of Kcr sites. On the independent test set, the accuracy of DeepMM-Kcr is highest among the existing models. The experimental results show that our model has very good performance in predicting Kcr sites. The source datasets and codes (in Python) are publicly available at https://github.com/yunyunliang88/DeepMM-Kcr .
(© 2025. The Author(s).)

Declarations. Competing interests: The authors declare no competing interests.