2025-10-08 トロント大学(U of T)
<関連情報>
- https://www.utoronto.ca/news/ai-generated-genomes-promise-advance-precision-cancer-care-study
- https://www.cell.com/cell-genomics/fulltext/S2666-979X(25)00225-3
生成AIを用いた合成癌ゲノムのin silico生成 In silico generation of synthetic cancer genomes using generative AI
Ander Díaz-Navarro ∙ Xindi Zhang ∙ Wei Jiao ∙ Bo Wang ∙ Lincoln Stein
Cell Genomics Published:August 12, 2025
DOI:https://doi.org/10.1016/j.xgen.2025.100969
Graphical abstract
Highlights
- OncoGAN is a multimodel ensemble pipeline designed to generate synthetic cancer genomes
- Key features like mutational signatures, genomic patterns, or CNA-SV are modeled
- Features are simulated to match eight tumor-specific profiles
- Synthetic donors have no access restrictions and preserve real donors’ privacy
Summary
Understanding how genomic alterations drive cancer is key to advancing precision oncology. To detect these alterations, accurate algorithms are used; however, due to privacy concerns, few deeply sequenced cancer genomes can be shared, limiting benchmarking and representing a major obstacle to the improvement of analytic tools. To address this, we developed OncoGAN, a generative AI model combining adversarial networks and variational autoencoders to create realistic synthetic cancer genomes. Trained on large-scale genomic datasets, OncoGAN accurately reproduces somatic mutations, copy number alterations, and structural variants across cancer types while preserving donors’ privacy. The synthetic genomes reflect tumor-specific mutational signatures and positional mutation patterns. Using DeepTumour, we validated the synthetic data’s fidelity, showing high concordance between generated and predicted tumors. Moreover, augmenting the training data with synthetic genomes improved DeepTumour’s accuracy, underscoring OncoGAN’s potential to generate shareable datasets with known ground truths for benchmarking and enhancement of cancer genome analysis tools.
