Link to bioRxiv paper:
http://biorxiv.org/cgi/content/short/2023.04.26.538432v1?rss=1

Authors: So, E., Hayat, S., Kadambat Nair, S., Wang, B., Haibe-Kains, B.

Abstract:
Cell-cell interactions coordinate various functions across cell-types in health and disease. Novel single-cell techniques allow us to investigate cellular crosstalk at single-cell resolution. Cell-cell interactions are mediated by underlying gene-gene networks, however most current methods are unable to account for complex inter-connections within the cell as well as incorporate the effect of pathway and protein complexes on interactions. Therefore, to utilise relations of cells to ligands and receptors as well as multiple annotations, we present GraphComm - a new graph-based deep learning method for predicting cell-cell communication in single-cell RNAseq datasets. By learning off of a prior model and fine-tuning a network on single-cell transcriptomic data, GraphComm is able to predict cell-cell communication (CCC) activity across cells, and its impact on downstream pathways, spatially adjacent cells and changes due to drug perturbations.

Copy rights belong to original authors. Visit the link for more info

Podcast created by Paper Player, LLC