EUVIMEDEUVIMED entdecken
Crossref

SiameseCPP: a sequence-based Siamese network to predict cell-penetrating peptides by contrastive learning

Xin Zhang, Lesong Wei, Xiucai Ye iD, Kai Zhang, Saisai Teng, Zhongshen Li, Junru Jin, Min Jae Kim, Tetsuya Sakurai, Lizhen Cui, Balachandran Manavalan iD, Leyi Wei iD

Briefings in Bioinformatics · 19.01.2023 · 24 (1)

DOI: 10.1093/bib/bbac545 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 23.12.2022. Verfasst von Xin Zhang und 11 weiteren Autor:innen. Beteiligte Einrichtung: Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan, China. Hauptthemen laut MEDLINE: Cell-Penetrating Peptides. Die Arbeit wurde bisher 44-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: Natural Science Foundation of China, National Research Foundation of Korea, Ministry of Science and ICT.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Cell-penetrating peptides (CPPs) have received considerable attention as a means of transporting pharmacologically active molecules into living cells without damaging the cell membrane, and thus hold great promise as future therapeutics. Recently, several machine learning-based algorithms have been proposed for predicting CPPs. However, most existing predictive methods do not consider the agreement (disagreement) between similar (dissimilar) CPPs and depend heavily on expert knowledge-based handcrafted features.

Results

In this study, we present SiameseCPP, a novel deep learning framework for automated CPPs prediction. SiameseCPP learns discriminative representations of CPPs based on a well-pretrained model and a Siamese neural network consisting of a transformer and gated recurrent units. Contrastive learning is used for the first time to build a CPP predictive model. Comprehensive experiments demonstrate that our proposed SiameseCPP is superior to existing baseline models for predicting CPPs. Moreover, SiameseCPP also achieves good performance on other functional peptide datasets, exhibiting satisfactory generalization ability.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cell-Penetrating PeptidesAlgorithmsBiological TransportNeural Networks, ComputerMachine Learning

Substanzen

Cell-Penetrating Peptides

Autor:innen und Institutionen

  • Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR), Shandong University, Jinan, China.
  • Department of Computer Science, University of Tsukuba, Tsukuba 3058577, Japan.
  • Department of integrative Biotechnology, College of Biotechnology & Bioengineering, Sungkyunkwan University, Seobu-ro, Jangan-gu, Suwon-si, Gyeonggi-do 16419, Republic of Korea.

ORCID-Profile: Xiucai Ye, Balachandran Manavalan, Leyi Wei

Förderung

  • Natural Science Foundation of China
  • National Research Foundation of Korea
  • Ministry of Science and ICT

Zitieren

APA

Zhang, X., Wei, L., Ye, X., Zhang, K., Teng, S., Li, Z., Jin, J., Kim, M. J., Sakurai, T., Cui, L., Manavalan, B., & Wei, L. (2023). SiameseCPP: a sequence-based Siamese network to predict cell-penetrating peptides by contrastive learning. Briefings in Bioinformatics, 24(1). https://doi.org/10.1093/bib/bbac545

Vancouver

Zhang X, Wei L, Ye X, Zhang K, Teng S, Li Z, et al. SiameseCPP: a sequence-based Siamese network to predict cell-penetrating peptides by contrastive learning. Briefings in Bioinformatics. 2023;24(1). doi:10.1093/bib/bbac545

BibTeX
@article{Zhang2023,
  author = {Zhang, Xin and Wei, Lesong and Ye, Xiucai and Zhang, Kai and Teng, Saisai and Li, Zhongshen and Jin, Junru and Kim, Min Jae and Sakurai, Tetsuya and Cui, Lizhen and Manavalan, Balachandran and Wei, Leyi},
  title = {SiameseCPP: a sequence-based Siamese network to predict cell-penetrating peptides by contrastive learning},
  journal = {Briefings in Bioinformatics},
  year = {2023},
  volume = {24},
  number = {1},
  doi = {10.1093/bib/bbac545}
}
Kostenlos starten →