Description
AI scientists create artificial human genomes using deep neural networks—an advancement that may help improve individual privacy and accelerate biomedical research.
Summary
- Artificial genomes created by deep neural networks may accelerate biomedicine.
- In the area of genomics, availability of data for research has its unique challenges, as genetic data sets are often not accessible due to privacy restrictions.
- Generative models and AGs have the potential to become valuable assets in genetic studies by providing a rich yet compact representation of existing genomes and high-quality, easy-access and anonymous alternatives for private databases,” wrote researchers Burak Yelmen, Linda Ongaro, Davide Marnetto, Francesco Montinaro, and Luca Pagani from the University of Tartu in Estonia, along with researchers Aurélien Decelle, Flora Jay, Cyril Furtlehner, and Corentin Tallec from the Université Paris-Sud and Université Paris-Saclay.
- However, the researchers point out that tracing generating samples back to the original would be a very complex undertaking.