Is your data alignable? Principled and interpretable alignability testing and integration of single-cell data

arXiv:2308.01839v2 Announce Type: replace-cross
Abstract: Single-cell data integration can provide a comprehensive molecular view of cells, and many algorithms have been developed to remove unwanted technical or biological variations and integrate heterogeneous single-cell datasets. Despite their wide usage, existing methods suffer from several fundamental limitations. In particular, we lack a rigorous statistical test for whether two high-dimensional single-cell datasets are alignable (and therefore should even be aligned). Moreover, popular methods can substantially distort the data during alignment, making the aligned …

abstract algorithms arxiv cells cs.cv data data integration datasets integration limitations q-bio.gn q-bio.qm stat.ap stat.ml technical testing type usage view