Jointly Embedding Multiple Single-Cell Omics Measurements
University of Michigan · University of Washington · +2 more institutions
Abstract
Many single-cell sequencing technologies are now available, but it is still difficult to apply multiple sequencing technologies to the same single cell. In this paper, we propose an unsupervised manifold alignment algorithm, MMD-MA, for integrating multiple measurements carried out on disjoint aliquots of a given population of cells. Effectively, MMD-MA performs an in silico co-assay by embedding cells measured in different ways into a learned latent space. In the MMD-MA algorithm, single-cell data points from multiple domains are aligned by optimizing an objective function with three components: (1) a maximum mean discrepancy (MMD) term to encourage the differently measured points to have similar…
Citation impact
- FWCI
- 89.25
- Percentile
- 100%
- References
- 23
Authors
5- LJLiu, JieCorresponding
University of Michigan
- HYHuang, Yuanhao
University of Michigan
- SRSingh, Ritambhara
University of Washington
- VJVert, Jean-Philippe
Université Paris Sciences et Lettres, École Nationale Supérieure des Mines de Paris
- NWNoble, William Stafford
University of Washington
Topics & keywords
- Adversarial system
- Computer science
- Domain (mathematical analysis)
- Generative grammar
- Task (project management)
- Key (lock)
- Identity (music)
- Code (set theory)
- Peace, Justice and strong institutions