scTenifoldXct: A semi-supervised method for predicting cell-cell interactions and mapping cellular communication graphs

We present scTenifoldXct, a semi-supervised computational tool for detecting ligand-receptor (LR)-mediated cell-cell interactions and mapping cellular communication graphs. Our method is based on manifold alignment, using LR pairs as inter-data correspondences to embed ligand and receptor genes expressed in interacting cells into a unified latent space. Neural networks are employed to minimize the distance between corresponding genes while preserving the structure of gene regression networks. We apply scTenifoldXct to real datasets for testing and demonstrate that our method detects interactions with high consistency compared with other methods. More importantly, scTenifoldXct uncovers weak but biologically relevant inter-actions overlooked by other methods. We also demonstrate how scTenifoldXct can be used to compare different samples, such as healthy vs. diseased and wild type vs. knockout, to identify differential interactions, thereby revealing functional implications associated with changes in cellular communication status.

Automated summary

scTenifoldXct is a semi-supervised computational tool for detecting ligand-receptor-mediated cell-cell interactions and mapping cellular communication graphs. It uses manifold alignment to embed ligand and receptor genes expressed in interacting cells into a latent space, with LR pairs as correspondences. scTenifoldXct demonstrates highly consistent detection of interactions compared to other methods and reveals biologically relevant interactions overlooked by other methods. It can also compare different samples to identify differential interactions and uncover functional implications associated with changes in cellular communication status.