Abstract
In this work, we propose an approach to generate whole-slide image (WSI) tiles by using deep generative models infused with matched gene expression profiles. First, we train a variational autoencoder (VAE) that learns a latent, lower-dimensional representation of multi-tissue gene expression profiles. Then, we use this representation to infuse generative adversarial networks (GANs) that generate lung and brain cortex tissue tiles, resulting in a new model that we call RNA-GAN. Tiles generated by RNA-GAN were preferred by expert pathologists compared with tiles generated using traditional GANs, and in addition, RNA-GAN needs fewer training epochs to generate high-quality tiles. Finally, RNA-GAN was able to generalize to gene expression profiles outside of the training set, showing imputation capabilities. A web-based quiz is available for users to play a game distinguishing real and synthetic tiles: https://rna-gan.stanford.edu/, and the code for RNA-GAN is available here: https://github.com/gevaertlab/RNA-GAN.
Original language | English (US) |
---|---|
Article number | 100534 |
Journal | Cell Reports Methods |
Volume | 3 |
Issue number | 8 |
DOIs | |
State | Published - Aug 28 2023 |
Externally published | Yes |
Keywords
- CP: Systems biology
- artificial intelligence
- deep learning
- generative adversarial network
- generative model
- synthetic biomedical data
- variational autoencoder
ASJC Scopus subject areas
- Biotechnology
- Biochemistry
- Biochemistry, Genetics and Molecular Biology (miscellaneous)
- Genetics
- Radiology Nuclear Medicine and imaging
- Computer Science Applications