References¶

Code¶

sci-vae is designed for Python >=3.6 and requires the following libraries, which will be automatically installed:

Library	Version	Reference
keras	>= 2.4.0	@misc{chollet2015keras, title={Keras}, author={Chollet, Franc{c}ois and others}, year={2015}, howpublished={url{https://keras.io}},}
Tensorflow and tensorflow-probability	>= 2.1.0	Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., Kudlur, M., Levenberg, J., Monga, R., Moore, S., Murray, D. G., Steiner, B., Tucker, P., Vasudevan, V., Warden, P., … Zheng, X. (2016). TensorFlow: A system for large-scale machine learning. 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16), 265–283. https://www.usenix.org/system/files/conference/osdi16/osdi16-abadi.pdf
NumPy	>= 1.9.0	Harris, C.R., Millman, K.J., van der Walt, S.J. et al. Array programming with NumPy. Nature 585, 357–362 (2020). DOI: 0.1038/s41586-020-2649-2
pandas	>= 1.0.3
scikit-learn	>= 0.22.2	Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., & Duchesnay, É. (2011). Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12(85), 2825–2830.
pyswarm	>= 0.6	https://github.com/tisimst/pyswarm
matplotlib	>= 3.3.3
seaborn	>= 0.11.1

We strongly encourage you to cite the other python packages. Note pyswarm and scikit-learn are only used when using the optimiser component (not your standard VAE) so these can be omitted if you don’t use them. Similarly, matplotlib and seaborn may not necessarily be used, so it depends on what aspects of this project is used in your work.

Literature¶

Label	Reference
VAE paper	Kingma, Diederik P, and Max Welling. 2014. “Auto-Encoding Variational Bayes.” In International Conference on Learning Representations.
Info VAE	Zhao, S., Song, J., & Ermon, S. (2018). InfoVAE: Information Maximizing Variational Autoencoders. ArXiv:1706.02262 [Cs, Stat]. http://arxiv.org/abs/1706.02262
VAEs applied to cancer	Simidjievski, N., Bodnar, C., Tariq, I., Scherer, P., Andres Terre, H., Shams, Z., Jamnik, M., & Liò, P. (2019). Variational Autoencoders for Cancer Data Integration: Design Principles and Computational Practice. Frontiers in Genetics, 10. https://doi.org/10.3389/fgene.2019.01205

Blogs and Githubs used¶

Link
MMD in Keras
X-VAE Keras
MMD VAE in Tensorflow
X-VAE Keras
VAE applied to cancer data
Blog by Ermon group re. InfoVAE

Data¶

Name	Link	Reference
CPTAC ccRCC paper	https://www.sciencedirect.com/science/article/pii/S0092867419311237	Clark, David J. et al. 2019. ‘Integrated Proteogenomic Characterization of Clear Cell Renal Cell Carcinoma’. Cell 179(4): 964-983.e31.
Single cell ccRCC data	https://www.sciencedirect.com/science/article/pii/S1535610821001653?via%3Dihub	Krishna, Chirag et al. 2021. ‘Single-Cell Sequencing Links Multiregional Immune Landscapes and Tissue-Resident T Cells in CcRCC to Tumor Topology and Therapy Efficacy’. Cancer Cell 39(5): 662-677.e6.
TCGA methylation data	https://www.nature.com/articles/s41585-019-0211-5	Linehan, W. M. & Ricketts, C. J. The Cancer Genome Atlas of renal cell carcinoma: findings and clinical implications. Nature Reviews Urology 16, 539–552 (2019).

Environments¶

This will be user dependent but don’t forget to cite anaconda if you use it or reticulate if you use R.