EUVIMEDEUVIMED entdecken
Crossref

scMHNN: a novel hypergraph neural network for integrative analysis of single-cell epigenomic, transcriptomic and proteomic data

Wei Li, Bin Xiang, Fan Yang, Yu Rong, Yanbin Yin, Jianhua Yao, Han Zhang

Briefings in Bioinformatics · 22.09.2023 · 24 (6)

DOI: 10.1093/bib/bbad391 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 02.11.2023. Verfasst von Wei Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: College of Artificial Intelligence, Nankai University, Tongyan Road, 300350 Tianjin, China. Hauptthemen laut MEDLINE: Transcriptome, Epigenomics. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key project of the Natural Science Foundation of Tianjin City.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Technological advances have now made it possible to simultaneously profile the changes of epigenomic, transcriptomic and proteomic at the single cell level, allowing a more unified view of cellular phenotypes and heterogeneities. However, current computational tools for single-cell multi-omics data integration are mainly tailored for bi-modality data, so new tools are urgently needed to integrate tri-modality data with complex associations. To this end, we develop scMHNN to integrate single-cell multi-omics data based on hypergraph neural network. After modeling the complex data associations among various modalities, scMHNN performs message passing process on the multi-omics hypergraph, which can capture the high-order data relationships and integrate the multiple heterogeneous features. Followingly, scMHNN learns discriminative cell representation via a dual-contrastive loss in self-supervised manner. Based on the pretrained hypergraph encoder, we further introduce the pre-training and fine-tuning paradigm, which allows more accurate cell-type annotation with only a small number of labeled cells as reference. Benchmarking results on real and simulated single-cell tri-modality datasets indicate that scMHNN outperforms other competing methods on both cell clustering and cell-type annotation tasks. In addition, we also demonstrate scMHNN facilitates various downstream tasks, such as cell marker detection and enrichment analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

TranscriptomeEpigenomicsProteomicsGene Expression ProfilingNeural Networks, Computer

Stichwörter der Autor:innen

cell-type annotationdata integrationhypergraph neural networksingle-cell multi-omicstri-modality

Autor:innen und Institutionen

  • College of Artificial Intelligence, Nankai University, Tongyan Road, 300350 Tianjin, China.
  • AI Lab, Tencent, Gaoxin 9th South Road, 518000 Shenzhen, China.
  • CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Yueyang Road, 200031 Shanghai, China.
  • Department of Food Science and Technology, University of Nebraska - Lincoln, 1400 R Street, 68588 Nebraska, USA.

Förderung

  • National Natural Science Foundation of China
  • Key project of the Natural Science Foundation of Tianjin City

Zitieren

APA

Li, W., Xiang, B., Yang, F., Rong, Y., Yin, Y., Yao, J., & Zhang, H. (2023). scMHNN: a novel hypergraph neural network for integrative analysis of single-cell epigenomic, transcriptomic and proteomic data. Briefings in Bioinformatics, 24(6). https://doi.org/10.1093/bib/bbad391

Vancouver

Li W, Xiang B, Yang F, Rong Y, Yin Y, Yao J, et al. scMHNN: a novel hypergraph neural network for integrative analysis of single-cell epigenomic, transcriptomic and proteomic data. Briefings in Bioinformatics. 2023;24(6). doi:10.1093/bib/bbad391

BibTeX
@article{Li2023,
  author = {Li, Wei and Xiang, Bin and Yang, Fan and Rong, Yu and Yin, Yanbin and Yao, Jianhua and Zhang, Han},
  title = {scMHNN: a novel hypergraph neural network for integrative analysis of single-cell epigenomic, transcriptomic and proteomic data},
  journal = {Briefings in Bioinformatics},
  year = {2023},
  volume = {24},
  number = {6},
  doi = {10.1093/bib/bbad391}
}
Kostenlos starten →