Cell-cell interactions (CCIs) play critical roles in many biological processes such as cellular differentiation, tissue homeostasis, and immune response. With the rapid development of high throughput single-cell RNA sequencing (scRNA-seq) technologies, it is of high importance to identify CCIs from the ever-increasing scRNA-seq data. However, limited by the algorithmic constraints, current computational methods based on statistical strategies ignore some key latent information contained in scRNA-seq data with high sparsity and heterogeneity.
Researchers at the Harbin Institute of Technology have developed a deep learning framework named DeepCCI to identify meaningful CCIs from scRNA-seq data. Applications of DeepCCI to a wide range of publicly available datasets from diverse technologies and platforms demonstrate its ability to predict significant CCIs accurately and effectively. Powered by the flexible and easy-to-use software, DeepCCI can provide the one-stop solution to discover meaningful intercellular interactions and build CCI networks from scRNA-seq data.
Workflow of the DeepCCI
(a) DeepCCI takes the scRNA-seq data as input. (b) DeepCCI clusters cells using the AE and the GCN jointly. (c) ScRNA-seq data with cell types. (d) LRIDB contains validated L–R interactions that were collected from several publicly literature-supported databases. (e) DeepCCI predicts the interactions between cell clusters using ResNet and GCN jointly. (f) DeepCCI offers several visualization outputs for different analytical tasks
Availability – The source code of DeepCCI is available online at https://github.com/JiangBioLab/DeepCCI