EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LSMMD-MA: scaling multimodal data integration for single-cell genomics data analysis

Laetitia Meng-Papaxanthos iD, Ran Zhang iD, Gang Li iD, Marco Cuturi iD, William Stafford Noble iD, Jean-Philippe Vert iD

Bioinformatics · 2023

DOI: 10.1093/bioinformatics/btad420 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, 2023. Verfasst von Laetitia Meng-Papaxanthos und 5 weiteren Autor:innen. Beteiligte Einrichtung: Google Research, Brain Team, Google, Brandschenkestrasse 110, Zurich 8002, Switzerland. Hauptthemen laut MEDLINE: Genomics, Genome. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 21 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NHGRI NIH HHS, NIH HHS, NIH.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation Modality matching in single-cell omics data analysis—i.e. matching cells across datasets collected using different types of genomic assays—has become an important problem, because unifying perspectives across different technologies holds the promise of yielding biological and clinical discoveries. However, single-cell dataset sizes can now reach hundreds of thousands to millions of cells, which remain out of reach for most multimodal computational methods. Results We propose LSMMD-MA, a large-scale Python implementation of the MMD-MA method for multimodal data integration. In LSMMD-MA, we reformulate the MMD-MA optimization problem using linear algebra and solve it with KeOps, a CUDA framework for symbolic matrix computation in Python. We show that LSMMD-MA scales to a million cells in each modality, two orders of magnitude greater than existing implementations. Availability and implementation LSMMD-MA is freely available at https://github.com/google-research/large_scale_mmdma and archived at https://doi.org/10.5281/zenodo.8076311.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GenomicsGenomeResearch DesignData AnalysisSingle-Cell AnalysisSoftware

Autor:innen und Institutionen

  • Google Research, Brain Team, Google, Brandschenkestrasse 110, Zurich 8002, Switzerland.
  • Department of Genome Sciences, University of Washington, 3720 15th Ave NE, Seattle, WA 98195, United States.
  • eScience Institute, University of Washington, 3910 15th Ave NE, Seattle, WA 98195, United States.
  • Google Research, Brain Team, Google, 8 Rue de Londres, Paris 75009, France.
  • Apple ML Research, Apple, 7 Av. d'Iéna, Paris 75116, France.
  • Paul G. Allen School of Computer Science and Engineering, University of Washington, 185 E Stevens Way NE, Seattle, WA 98195, United States.

ORCID-Profile: Laetitia Meng-Papaxanthos, Ran Zhang, Gang Li, Marco Cuturi, William Stafford Noble, Jean-Philippe Vert

Förderung

  • NHGRI NIH HHS
  • NIH HHS
  • NIH

Zitieren

APA

Meng-Papaxanthos, L., Zhang, R., Li, G., Cuturi, M., Noble, W. S., & Vert, J. P. (2023). LSMMD-MA: scaling multimodal data integration for single-cell genomics data analysis. Bioinformatics. https://doi.org/10.1093/bioinformatics/btad420

Vancouver

Meng-Papaxanthos L, Zhang R, Li G, Cuturi M, Noble WS, Vert JP. LSMMD-MA: scaling multimodal data integration for single-cell genomics data analysis. Bioinformatics. 2023. doi:10.1093/bioinformatics/btad420

BibTeX
@article{MengPapaxanthos2023,
  author = {Meng-Papaxanthos, Laetitia and Zhang, Ran and Li, Gang and Cuturi, Marco and Noble, William Stafford and Vert, Jean-Philippe},
  title = {LSMMD-MA: scaling multimodal data integration for single-cell genomics data analysis},
  journal = {Bioinformatics},
  year = {2023},
  doi = {10.1093/bioinformatics/btad420}
}
Kostenlos starten →