Researchers from Texas A&M University present scTenifoldXct, a semi-supervised computational tool for detecting ligand-receptor (LR)-mediated cell-cell interactions and mapping cellular communication graphs. Their 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. The researchers apply scTenifoldXct to real datasets for testing and demonstrate that their method detects interactions with high consistency compared with other methods. More importantly, scTenifoldXct uncovers weak but biologically relevant interactions overlooked by other methods. They 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.
Availability – The method scTenifoldXct, and two example notebooks have been deposited at: https://github.com/cailab-tamu/scTenifoldXct
Article: Yang, Yongjian, et al. “scTenifoldXct: A semi-supervised method for predicting cell-cell interactions and mapping cellular communication graphs.” Cell Systems 14.4 (2023): 302-311. [abstract]