EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AttentionPert: accurately modeling multiplexed genetic perturbations with multi-scale effects

Ding Bai, Caleb N Ellington, Shentong Mo, Le Song, Eric P Xing

Bioinformatics · 28.06.2024 · 40 (Supplement_1) · i453-i461

DOI: 10.1093/bioinformatics/btae244 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 28.06.2024. Verfasst von Ding Bai und 4 weiteren Autor:innen. Beteiligte Einrichtung: Machine Learning Department, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, 00000, United Arabic Emirates. Hauptthemen laut MEDLINE: Computational Biology. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIGMS NIH HHS, NIH HHS, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Genetic perturbations (e.g. knockouts, variants) have laid the foundation for our understanding of many diseases, implicating pathogenic mechanisms and indicating therapeutic targets. However, experimental assays are fundamentally limited by the number of measurable perturbations. Computational methods can fill this gap by predicting perturbation effects under novel conditions, but accurately predicting the transcriptional responses of cells to unseen perturbations remains a significant challenge. Results We address this by developing a novel attention-based neural network, AttentionPert, which accurately predicts gene expression under multiplexed perturbations and generalizes to unseen conditions. AttentionPert integrates global and local effects in a multi-scale model, representing both the nonuniform system-wide impact of the genetic perturbation and the localized disturbance in a network of gene–gene similarities, enhancing its ability to predict nuanced transcriptional responses to both single and multi-gene perturbations. In comprehensive experiments, AttentionPert demonstrates superior performance across multiple datasets outperforming the state-of-the-art method in predicting differential gene expressions and revealing novel gene regulations. AttentionPert marks a significant improvement over current methods, particularly in handling the diversity of gene perturbations and in predicting out-of-distribution scenarios. Availability and implementation Code is available at https://github.com/BaiDing1234/AttentionPert.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Computational BiologyHumansGene Regulatory NetworksNeural Networks, ComputerGene Expression Profiling

Autor:innen und Institutionen

  • Machine Learning Department, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, 00000, United Arabic Emirates.
  • Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA, 15213, United States.
  • Machine Learning Department, Carnegie Mellon University, Pittsburgh, PA, 15213, United States.

Förderung

  • NIGMS NIH HHS
  • NIH HHS
  • National Institutes of Health

Zitieren

APA

Bai, D., Ellington, C. N., Mo, S., Song, L., & Xing, E. P. (2024). AttentionPert: accurately modeling multiplexed genetic perturbations with multi-scale effects. Bioinformatics, 40(Supplement_1), i453-i461. https://doi.org/10.1093/bioinformatics/btae244

Vancouver

Bai D, Ellington CN, Mo S, Song L, Xing EP. AttentionPert: accurately modeling multiplexed genetic perturbations with multi-scale effects. Bioinformatics. 2024;40(Supplement_1):i453-i461. doi:10.1093/bioinformatics/btae244

BibTeX
@article{Bai2024,
  author = {Bai, Ding and Ellington, Caleb N and Mo, Shentong and Song, Le and Xing, Eric P},
  title = {AttentionPert: accurately modeling multiplexed genetic perturbations with multi-scale effects},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {Supplement_1},
  pages = {i453--i461},
  doi = {10.1093/bioinformatics/btae244}
}
Kostenlos starten →