Disentangled Representations of Cellular Identity
We introduce a disentangled representation for cellular identity that constructs a latent cellular state from a linear combination of condition specific basis vectors that are then decoded into gene expression levels. The basis vectors are learned with a deep autoencoder model from single-cell RNA-seq data. Linear arithmetic in the disentangled representation successfully predicts nonlinear gene expression interactions between biological pathways in unobserved treatment conditions. We are able to recover the mean gene expression profiles of unobserved conditions with an average Pearson r = 0.73, which outperforms two linear baselines, one with an average r = 0.43 and another with an average r = 0.19. Disentangled representations hold the promise to provide new explanatory power for the interaction of biological pathways and the prediction of effects of unobserved conditions for applications such as combinatorial therapy and cellular reprogramming. Our work is motivated by recent advances in deep generative models that have enabled synthesis of images and natural language with desired properties from interpolation in a “latent representation” of the data.
KeywordsSingle-cell RNA seq Gene expression Generative modeling Deep learning
We acknowledge the members of the Gifford and Sherwood labs for helpful discussion.
- 2.Ghahramani, A., Watt, F.M., Luscombe, N.M.: Generative adversarial networks simulate gene expression and predict perturbations in single cells. bioArXiv preprint (2018). https://doi.org/10.1101/262501
- 3.Bojanowski, P., Joulin, A., Lopez-Paz, D., Szlam, A.: Optimizing the latent space of generative networks. arXiv preprint arXiv:1707.05776 (2017)
- 8.Yeo, G.H.T., Lin, L., Qi, Y.C., Gifford, D.K., Sherwood, R.I.: Elucidation of combinatorial signaling logic with multiplexed barcodelet single-cell RNA-seq (2018, in prep)Google Scholar
- 10.Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? In: Advances in Neural Information Processing Systems, pp. 5574–5584 (2017)Google Scholar
- 11.Kingma, D.P., Mohamed, S., Rezende, D.J., Welling, M.: Semi-supervised learning with deep generative models. In: Advances in Neural Information Processing Systems, pp. 3581–3589 (2014)Google Scholar
- 12.Li, H., Xu, Z., Taylor, G., Goldstein, T.: Visualizing the loss landscape of neural nets. arXiv preprint arXiv:1712.09913 (2017)
- 13.Lopez, R., Regier, J., Cole, M., Jordan, M., Yosef, N.: A deep generative model for gene expression profiles from single-cell RNA sequencing. arXiv preprint arXiv:1709.02082 (2017)
- 19.Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434 (2015)
- 26.White, T.: Sampling generative networks. arXiv preprint arXiv:1609.04468 (2016)