EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Species-agnostic transfer learning for cross-species transcriptomics data integration without gene orthology

Youngjun Park iD, Nils P Muttray, Anne-Christin Hauschild

Briefings in Bioinformatics · 22.01.2024 · 25 (2)

DOI: 10.1093/bib/bbae004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 01.02.2024. Verfasst von Youngjun Park und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Informatics, University Medical Center Göttingen, Göttingen, Germany. Hauptthemen laut MEDLINE: Algorithms, Zebrafish. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: German Ministry of Education and Research, International Max Planck Research School for Genome Science, Göttingen Graduate Center for Neurosciences, Biophysics, und Molecular Biosciences.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Novel hypotheses in biomedical research are often developed or validated in model organisms such as mice and zebrafish and thus play a crucial role. However, due to biological differences between species, translating these findings into human applications remains challenging. Moreover, commonly used orthologous gene information is often incomplete and entails a significant information loss during gene-id conversion. To address these issues, we present a novel methodology for species-agnostic transfer learning with heterogeneous domain adaptation. We extended the cross-domain structure-preserving projection toward out-of-sample prediction. Our approach not only allows knowledge integration and translation across various species without relying on gene orthology but also identifies similar GO among the most influential genes composing the latent space for integration. Subsequently, during the alignment of latent spaces, each composed of species-specific genes, it is possible to identify functional annotations of genes missing from public orthology databases. We evaluated our approach with four different single-cell sequencing datasets focusing on cell-type prediction and compared it against related machine-learning approaches. In summary, the developed model outperforms related methods working without prior knowledge when predicting unseen cell types based on other species’ data. The results demonstrate that our novel approach allows knowledge transfer beyond species barriers without the dependency on known gene orthology but utilizing the entire gene sets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsZebrafishMiceHumansAnimalsGene Expression ProfilingSpecies SpecificityMachine Learning

Stichwörter der Autor:innen

cross-speciesdomain adaptationsingle-cell sequencingtranscriptomicstransfer learning

Autor:innen und Institutionen

  • Department of Medical Informatics, University Medical Center Göttingen, Göttingen, Germany.
  • International Max Planck Research Schools for Genome Science, Georg-August-Universität Göttingen Göttingen, Germany.
  • Applied Statistics, Georg-August-Universität Göttingen Göttingen, Germany.
  • Campus-Institute Data Science (CIDAS), Georg-August-Universität Göttingen Göttingen, Germany.

ORCID-Profile: Youngjun Park

Förderung

  • German Ministry of Education and Research
  • International Max Planck Research School for Genome Science
  • Göttingen Graduate Center for Neurosciences, Biophysics, und Molecular Biosciences

Zitieren

APA

Park, Y., Muttray, N. P., & Hauschild, A. C. (2024). Species-agnostic transfer learning for cross-species transcriptomics data integration without gene orthology. Briefings in Bioinformatics, 25(2). https://doi.org/10.1093/bib/bbae004

Vancouver

Park Y, Muttray NP, Hauschild AC. Species-agnostic transfer learning for cross-species transcriptomics data integration without gene orthology. Briefings in Bioinformatics. 2024;25(2). doi:10.1093/bib/bbae004

BibTeX
@article{Park2024,
  author = {Park, Youngjun and Muttray, Nils P and Hauschild, Anne-Christin},
  title = {Species-agnostic transfer learning for cross-species transcriptomics data integration without gene orthology},
  journal = {Briefings in Bioinformatics},
  year = {2024},
  volume = {25},
  number = {2},
  doi = {10.1093/bib/bbae004}
}
Kostenlos starten →