Generative adversarial networks uncover epidermal regulators and predict single cell perturbations Generative adversarial networks uncover epidermal regulators and predict single cell perturbations
Paper summary Single cells behave in complex and sometimes seemingly random ways. We have applied Generative Adversarial Networks (GANs), a form of artificial intelligence, to make sense of the way genes are controlled in skin cells. A GAN involves two separate neural networks, a ‘generator’ and a ‘discriminator’. The generator simulates cells and the discriminator tries to tell the difference between the fake data created by the simulator, and data from real cells. As they compete against each other they improve at their tasks and provide new insights into the way cells behave. Our neural network approach allows us to understand the relationship between different genes and how this contributes to cell behaviour. One of the networks, the generator, is responsible for simulating cells and we use this to predict how genes are controlled under different conditions, effectively simulating what would previously have been laborious and painstaking experiments. GANs also make it possible to compare data from multiple labs produced in different conditions, opening up the opportunity to answer new questions.
dx.doi.org
sci-hub
scholar.google.com
Generative adversarial networks uncover epidermal regulators and predict single cell perturbations
Arsham Ghahramani and Fiona M Watt and Nicholas M Luscombe
bioRxiv: The preprint server for biology - 2018 via Local CrossRef
Keywords:


Summary by David Stutz 1 month ago
Loading...
Your comment:
Summary by arshamg 4 months ago
Loading...
Is there any objective evaluation that this approach is better than another or a simple baseline? What evaluation would I use to compare against the performance of this model?

Generative models for scRNA-seq are new so there's not currently a way to compare different generative models. There are ways to compare different dimensionality reduction methods, especially if you have a ground-truth mixture of labelled cells. Our main objective measure of performance is the predictions we make (e.g. prediction of genes that change over differentiation in the skin) and how these match up to real skin cell behaviour.

Your comment:


ShortScience.org allows researchers to publish paper summaries that are voted on and ranked!
About

Sponsored by: and