EUVIMEDEUVIMED entdecken
Crossref

Tumor Resource Allocation using Transcriptomes and AI

Bhavya Dwivedi

American Journal for Young Scientists · 20.07.2026

DOI: 10.67194/ajfys.v2i4.001 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal for Young Scientists, online erschienen am 20.07.2026. Verfasst von Bhavya Dwivedi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cancer cells survive by reprogramming their gene expression to support growth, metabolism, and immune evasion, but they must balance these competing demands. Here, we analyze transcriptome data from twelve cancer types to determine what tumors are biologically optimized for. We apply a machine-learning framework combining a variational autoencoder with classifiers to learn compact representations of gene expression and accurately distinguish cancer types, achieving about 98% accuracy. The learned latent features reveal dominant biological pathways, including metabolic, immune, and proliferative programs. By viewing cancer as a system that must make trade-offs to survive, this approach helps identify the biological pathways that each tumor relies on most and could be targeted by treatment.

Zitieren

APA

Dwivedi, B. (2026). Tumor Resource Allocation using Transcriptomes and AI. American Journal for Young Scientists. https://doi.org/10.67194/ajfys.v2i4.001

Vancouver

Dwivedi B. Tumor Resource Allocation using Transcriptomes and AI. American Journal for Young Scientists. 2026. doi:10.67194/ajfys.v2i4.001

BibTeX
@article{Dwivedi2026,
  author = {Dwivedi, Bhavya},
  title = {Tumor Resource Allocation using Transcriptomes and AI},
  journal = {American Journal for Young Scientists},
  year = {2026},
  doi = {10.67194/ajfys.v2i4.001}
}
Kostenlos starten →