EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BioDSNN: a dual-stream neural network with hybrid biological knowledge integration for multi-gene perturbation response prediction

Yuejun Tan, Linhai Xie, Hong Yang, Qingyuan Zhang, Jinyuan Luo, Yanchun Zhang

Briefings in Bioinformatics · 22.11.2024 · 26 (1)

DOI: 10.1093/bib/bbae617 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 25.11.2024. Verfasst von Yuejun Tan und 5 weiteren Autor:innen. Beteiligte Einrichtung: The Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510000, China. Hauptthemen laut MEDLINE: Neural Networks, Computer, Gene Regulatory Networks, Computational Biology. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of China, Joint Research Fund of Guangzhou and University, Independent Research Project of the State Key Laboratory of Proteomics.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Studying the outcomes of genetic perturbation based on single-cell RNA-seq data is crucial for understanding genetic regulation of cells. However, the high cost of cellular experiments and single-cell sequencing restrict us from measuring the full combination space of genetic perturbations and cell types. Consequently, a bunch of computational models have been proposed to predict unseen combinations based on existing data. Among them, generative models, e.g. variational autoencoder and diffusion models, have the superiority in capturing the perturbed data distribution, but lack a biologically understandable foundation for generalization. On the other side of the spectrum, Gene Regulation Networks or gene pathway knowledge have been exploited for more reasonable generalization enhancement. Unfortunately, they do not reach a balanced processing of the two data modalities, leading to a degraded fitting ability. Hence, we propose a dual-stream architecture. Before the information from two modalities are merged, the sequencing data are learned with a generative model while three types of knowledge data are comprehensively processed with graph networks and a masked transformer, enforcing a deep understanding of single-modality data, respectively. The benchmark results show an approximate 20% reduction in terms of mean squared error, proving the effectiveness of the model.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerGene Regulatory NetworksComputational BiologyHumansAlgorithmsSingle-Cell Analysis

Stichwörter der Autor:innen

biological knowledgegenetic perturbation predictmasked attentionvariational autoencoder

Autor:innen und Institutionen

  • The Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou 510000, China.
  • School of Computer Science and Technology, Zhejiang Normal University, Jinhua 321000, China.
  • State Key Laboratory of Proteomics, National Center for Protein Sciences (Beijing), Beijing 100000, China.
  • International Academy of Phronesis Medicine, Guangzhou 510000, China.

Förderung

  • Natural Science Foundation of China
  • Joint Research Fund of Guangzhou and University
  • Independent Research Project of the State Key Laboratory of Proteomics

Zitieren

APA

Tan, Y., Xie, L., Yang, H., Zhang, Q., Luo, J., & Zhang, Y. (2024). BioDSNN: a dual-stream neural network with hybrid biological knowledge integration for multi-gene perturbation response prediction. Briefings in Bioinformatics, 26(1). https://doi.org/10.1093/bib/bbae617

Vancouver

Tan Y, Xie L, Yang H, Zhang Q, Luo J, Zhang Y. BioDSNN: a dual-stream neural network with hybrid biological knowledge integration for multi-gene perturbation response prediction. Briefings in Bioinformatics. 2024;26(1). doi:10.1093/bib/bbae617

BibTeX
@article{Tan2024,
  author = {Tan, Yuejun and Xie, Linhai and Yang, Hong and Zhang, Qingyuan and Luo, Jinyuan and Zhang, Yanchun},
  title = {BioDSNN: a dual-stream neural network with hybrid biological knowledge integration for multi-gene perturbation response prediction},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  volume = {26},
  number = {1},
  doi = {10.1093/bib/bbae617}
}
Kostenlos starten →