Cellular State Transformations using Generative Adversarial Networks
This work addresses the challenge of modeling cellular state transformations in biology, but it appears incremental as it applies an existing GAN method to a new biological domain.
The authors tackled the problem of simulating realistic transitions between cellular states by using a generative adversarial network (GAN) to perturb gene expression profiles, resulting in biologically meaningful perturbations that follow the original data distribution and allow identification of key genes.
We introduce a novel method to unite deep learning with biology by which generative adversarial networks (GANs) generate transcriptome perturbations and reveal condition-defining gene expression patterns. We find that a generator conditioned to perturb any input gene expression profile simulates a realistic transition between source and target RNA expression states. The perturbed samples follow a similar distribution to original samples from the dataset, also suggesting these are biologically meaningful perturbations. Finally, we show that it is possible to identify the genes most positively and negatively perturbed by the generator and that the enriched biological function of the perturbed genes are realistic. We call the framework the Transcriptome State Perturbation Generator (TSPG), which is open source software available at https://github.com/ctargon/TSPG.