EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY-NC-ND 4.0

On knowing a gene: A distributional hypothesis of gene function

Jason J Kwon, Joshua Pan, Guadalupe Gonzalez, William C Hahn, Marinka Zitnik

Cell Systems · 2024-06 · 15 (6) · 488-496

DOI: 10.1016/j.cels.2024.04.008 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Cell Systems, 2024-06. Verfasst von Jason J Kwon und 4 weiteren Autor:innen. Beteiligte Einrichtung: Dana-Farber Cancer Institute and Harvard Medical School, Department of Medical Oncology, Boston, MA 02215, USA; Broad Institute of MIT and Harvard, C…. Hauptthemen laut MEDLINE: Semantics, Natural Language Processing. Die Arbeit wurde bisher 18-mal zitiert (Crossref) und nennt 95 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NCI NIH HHS, NICHD NIH HHS, AstraZeneca.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As words can have multiple meanings that depend on sentence context, genes can have various functions that depend on the surrounding biological system. This pleiotropic nature of gene function is limited by ontologies, which annotate gene functions without considering biological contexts. We contend that the gene function problem in genetics may be informed by recent technological leaps in natural language processing, in which representations of word semantics can be automatically learned from diverse language contexts. In contrast to efforts to model semantics as "is-a" relationships in the 1990s, modern distributional semantics represents words as vectors in a learned semantic space and fuels current advances in transformer-based models such as large language models and generative pre-trained transformers. A similar shift in thinking of gene functions as distributions over cellular contexts may enable a similar breakthrough in data-driven learning from large biological datasets to inform gene function.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SemanticsNatural Language ProcessingHumansGenesGene OntologyComputational BiologyAnimals

Stichwörter der Autor:innen

artificial intelligencedistributed representationsgene functionlarge language modelslexical semanticsmachine learningtransformersword embeddings

Autor:innen und Institutionen

  • Dana-Farber Cancer Institute and Harvard Medical School, Department of Medical Oncology, Boston, MA 02215, USA; Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA.
  • Department of Computing, Faculty of Engineering, Imperial College, London SW7 2AZ, UK.
  • Dana-Farber Cancer Institute and Harvard Medical School, Department of Medical Oncology, Boston, MA 02215, USA; Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA. Electronic address: william_hahn@dfci.harvard…
  • Broad Institute of MIT and Harvard, Cambridge, MA 02142, USA; Harvard Medical School, Department of Biomedical Informatics, Boston, MA 02115, USA; Harvard Data Science Initiative, Harvard University, Cambridge, MA 02138…

Förderung

  • NCI NIH HHS
  • NICHD NIH HHS
  • AstraZeneca
  • National Cancer Institute
  • NIH
  • Aligning Science Across Parkinson's
  • National Science Foundation
  • Chan Zuckerberg Initiative

Zitieren

APA

Kwon, J. J., Pan, J., Gonzalez, G., Hahn, W. C., & Zitnik, M. (2024). On knowing a gene: A distributional hypothesis of gene function. Cell Systems, 15(6), 488-496. https://doi.org/10.1016/j.cels.2024.04.008

Vancouver

Kwon JJ, Pan J, Gonzalez G, Hahn WC, Zitnik M. On knowing a gene: A distributional hypothesis of gene function. Cell Systems. 2024;15(6):488-496. doi:10.1016/j.cels.2024.04.008

BibTeX
@article{Kwon2024,
  author = {Kwon, Jason J and Pan, Joshua and Gonzalez, Guadalupe and Hahn, William C and Zitnik, Marinka},
  title = {On knowing a gene: A distributional hypothesis of gene function},
  journal = {Cell Systems},
  year = {2024},
  volume = {15},
  number = {6},
  pages = {488--496},
  doi = {10.1016/j.cels.2024.04.008}
}
Kostenlos starten →