RT Journal Article
SR Electronic
T1 TopoGAN: unsupervised manifold alignment of single-cell data
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 2022.04.27.489829
DO 10.1101/2022.04.27.489829
A1 Akash Singh
A1 Marcel J.T. Reinders
A1 Ahmed Mahfouz
A1 Tamim Abdelaal
YR 2022
UL http://biorxiv.org/content/early/2022/04/29/2022.04.27.489829.abstract
AB Motivation Single-cell technologies allow deep characterization of different molecular aspects of cells. Integrating these modalities provides a comprehensive view of cellular identity. Current integration methods rely on overlapping features or cells to link datasets measuring different modalities, limiting their application to experiments where different molecular layers are profiled in different subsets of cells.Results We present TopoGAN, a method for unsupervised manifold alignment of single-cell datasets with non-overlapping cells or features. We use topological autoencoders to obtain latent representations of each modality separately. A topology-guided Generative Adversarial Network then aligns these latent representations into a common space. We show that TopoGAN outperforms state-of-the-art manifold alignment methods in complete unsupervised settings. Interestingly, the topological autoencoder for individual modalities also showed better performance in preserving the original structure of the data in the low-dimensional representations when compared to using UMAP or a variational autoencoder. Taken together, we show that the concept of topology preservation might be a powerful tool to align multiple single modality datasets, unleashing the potential of multi-omic interpretations of cells.Availability and implementation Implementation available on GitHub (https://github.com/AkashCiel/TopoGAN). All datasets used in this study are publicly available.Contact t.r.m.abdelaal{at}lumc.nlCompeting Interest StatementThe authors have declared no competing interest.