MAGAN: Aligning Biological Manifolds

Matthew Amodio, Smita Krishnaswamy
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:215-223, 2018.

Abstract

It is increasingly common in many types of natural and physical systems (especially biological systems) to have different types of measurements performed on the same underlying system. In such settings, it is important to align the manifolds arising from each measurement in order to integrate such data and gain an improved picture of the system; we tackle this problem using generative adversarial networks (GANs). Recent attempts to use GANs to find correspondences between sets of samples do not explicitly perform proper alignment of manifolds. We present the new Manifold Aligning GAN (MAGAN) that aligns two manifolds such that related points in each measurement space are aligned. We demonstrate applications of MAGAN in single-cell biology in integrating two different measurement types together: cells from the same tissue are measured with both genomic (single-cell RNA-sequencing) and proteomic (mass cytometry) technologies. We show that MAGAN successfully aligns manifolds such that known correlations between measured markers are improved compared to other recently proposed models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v80-amodio18a, title = {{MAGAN}: Aligning Biological Manifolds}, author = {Amodio, Matthew and Krishnaswamy, Smita}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {215--223}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/amodio18a/amodio18a.pdf}, url = {https://proceedings.mlr.press/v80/amodio18a.html}, abstract = {It is increasingly common in many types of natural and physical systems (especially biological systems) to have different types of measurements performed on the same underlying system. In such settings, it is important to align the manifolds arising from each measurement in order to integrate such data and gain an improved picture of the system; we tackle this problem using generative adversarial networks (GANs). Recent attempts to use GANs to find correspondences between sets of samples do not explicitly perform proper alignment of manifolds. We present the new Manifold Aligning GAN (MAGAN) that aligns two manifolds such that related points in each measurement space are aligned. We demonstrate applications of MAGAN in single-cell biology in integrating two different measurement types together: cells from the same tissue are measured with both genomic (single-cell RNA-sequencing) and proteomic (mass cytometry) technologies. We show that MAGAN successfully aligns manifolds such that known correlations between measured markers are improved compared to other recently proposed models.} }
Endnote
%0 Conference Paper %T MAGAN: Aligning Biological Manifolds %A Matthew Amodio %A Smita Krishnaswamy %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-amodio18a %I PMLR %P 215--223 %U https://proceedings.mlr.press/v80/amodio18a.html %V 80 %X It is increasingly common in many types of natural and physical systems (especially biological systems) to have different types of measurements performed on the same underlying system. In such settings, it is important to align the manifolds arising from each measurement in order to integrate such data and gain an improved picture of the system; we tackle this problem using generative adversarial networks (GANs). Recent attempts to use GANs to find correspondences between sets of samples do not explicitly perform proper alignment of manifolds. We present the new Manifold Aligning GAN (MAGAN) that aligns two manifolds such that related points in each measurement space are aligned. We demonstrate applications of MAGAN in single-cell biology in integrating two different measurement types together: cells from the same tissue are measured with both genomic (single-cell RNA-sequencing) and proteomic (mass cytometry) technologies. We show that MAGAN successfully aligns manifolds such that known correlations between measured markers are improved compared to other recently proposed models.
APA
Amodio, M. & Krishnaswamy, S.. (2018). MAGAN: Aligning Biological Manifolds. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:215-223 Available from https://proceedings.mlr.press/v80/amodio18a.html.

Related Material