EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Explainable deep neural networks for predicting sample phenotypes from single-cell transcriptomics

Jordi Martorell-Marugán iD, Raúl López-Domínguez iD, Juan Antonio Villatoro-García iD, Daniel Toro-Domínguez iD, Marco Chierici iD, Giuseppe Jurman iD, Pedro Carmona-Sáez iD

Briefings in Bioinformatics · 22.11.2024 · 26 (1)

DOI: 10.1093/bib/bbae673 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 15.01.2025. Verfasst von Jordi Martorell-Marugán und 6 weiteren Autor:innen. Beteiligte Einrichtung: GENYO, Centre for Genomics and Oncological Research: Pfizer / University of Granada / Andalusian Regional Government, PTS Granada, Avenida de la Ilus…. Hauptthemen laut MEDLINE: Single-Cell Analysis, Neural Networks, Computer, Transcriptome, Gene Expression Profiling. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: FEDER/Junta de Andalucía-Consejería de Universidad, Investigación e Innovación, Universidad de Granada.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recent advances in single-cell RNA-Sequencing (scRNA-Seq) technologies have revolutionized our ability to gather molecular insights into different phenotypes at the level of individual cells. The analysis of the resulting data poses significant challenges, and proper statistical methods are required to analyze and extract information from scRNA-Seq datasets. Sample classification based on gene expression data has proven effective and valuable for precision medicine applications. However, standard classification schemas are often not suitable for scRNA-Seq due to their unique characteristics, and new algorithms are required to effectively analyze and classify samples at the single-cell level. Furthermore, existing methods for this purpose have limitations in their usability. Those reasons motivated us to develop singleDeep, an end-to-end pipeline that streamlines the analysis of scRNA-Seq data training deep neural networks, enabling robust prediction and characterization of sample phenotypes. We used singleDeep to make predictions on scRNA-Seq datasets from different conditions, including systemic lupus erythematosus, Alzheimer’s disease and coronavirus disease 2019. Our results demonstrate strong diagnostic performance, validated both internally and externally. Moreover, singleDeep outperformed traditional machine learning methods and alternative single-cell approaches. In addition to prediction accuracy, singleDeep provides valuable insights into cell types and gene importance estimation for phenotypic characterization. This functionality provided additional and valuable information in our use cases. For instance, we corroborated that some interferon signature genes are consistently relevant for autoimmunity across all immune cell types in lupus. On the other hand, we discovered that genes linked to dementia have relevant roles in specific brain cell populations, such as APOE in astrocytes.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Single-Cell AnalysisNeural Networks, ComputerTranscriptomeGene Expression ProfilingDeep LearningHumansPhenotypeAlzheimer DiseaseCOVID-19AlgorithmsLupus Erythematosus, SystemicSequence Analysis, RNASARS-CoV-2

Stichwörter der Autor:innen

Alzheimer’s diseaseartificial intelligencecomplex diseasesdeep learningsingle-cell RNA-Sequencingsystemic lupus erythematosus

Autor:innen und Institutionen

  • GENYO, Centre for Genomics and Oncological Research: Pfizer / University of Granada / Andalusian Regional Government, PTS Granada, Avenida de la Ilustración 114, Granada 18016, Spain.
  • Fundación para la Investigación Biosanitaria de Andalucía Oriental-Alejandro Otero (FIBAO), Avenida de Madrid 15, Granada 18012, Spain.
  • Department of Statistics and Operational Research, University of Granada, Avenida de la Fuente Nueva S/N, Granada 18071, Spain.
  • Unit of Inflammatory Diseases, Department of Environmental Medicine, Karolinska Institutet, Nobels väg 13, Solna 171 77, Sweden.
  • Data Science for Health Research Unit, Fondazione Bruno Kessler, Via Sommarive 18, Trento 38123, Italy.

ORCID-Profile: Jordi Martorell-Marugán, Raúl López-Domínguez, Juan Antonio Villatoro-García, Daniel Toro-Domínguez, Marco Chierici, Giuseppe Jurman, Pedro Carmona-Sáez

Förderung

  • FEDER/Junta de Andalucía-Consejería de Universidad, Investigación e Innovación
  • Universidad de Granada

Zitieren

APA

Martorell-Marugán, J., López-Domínguez, R., Villatoro-García, J. A., Toro-Domínguez, D., Chierici, M., Jurman, G., & Carmona-Sáez, P. (2024). Explainable deep neural networks for predicting sample phenotypes from single-cell transcriptomics. Briefings in Bioinformatics, 26(1). https://doi.org/10.1093/bib/bbae673

Vancouver

Martorell-Marugán J, López-Domínguez R, Villatoro-García JA, Toro-Domínguez D, Chierici M, Jurman G, et al. Explainable deep neural networks for predicting sample phenotypes from single-cell transcriptomics. Briefings in Bioinformatics. 2024;26(1). doi:10.1093/bib/bbae673

BibTeX
@article{MartorellMarugn2024,
  author = {Martorell-Marugán, Jordi and López-Domínguez, Raúl and Villatoro-García, Juan Antonio and Toro-Domínguez, Daniel and Chierici, Marco and Jurman, Giuseppe and Carmona-Sáez, Pedro},
  title = {Explainable deep neural networks for predicting sample phenotypes from single-cell transcriptomics},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  volume = {26},
  number = {1},
  doi = {10.1093/bib/bbae673}
}
Kostenlos starten →