Intercellular Communication Guides the Prediction of Intracellular Gene Regulatory Relationships

Area of Science:

• Computational biology
• Systems biology
• Genomics

Background:

• Cellular communication via ligand-receptor signaling is crucial for gene expression and cellular functions.
• Existing methods fail to capture synergistic interactions between cellular communication and gene regulatory networks.
• Current approaches cannot construct complete cellular communication networks, limiting biological interpretation.

Purpose of the Study:

• To develop a computational framework for predicting intracellular gene regulatory relationships.
• To construct comprehensive cellular communication networks.
• To address limitations in current methods for modeling cellular communication and gene regulation.

Main Methods:

• An end-to-end computational framework integrating ligand-receptor interactions, signaling pathways, and transcription factor networks.
• Deep learning models for accurate prediction of receptor-mediated regulatory relationships.
• Application to diverse spatial transcriptomic datasets.

Main Results:

• The framework successfully predicts receptor-mediated target gene regulatory relationships.
• Demonstrated efficiency across various spatial transcriptomic data.
• Provided a valuable tool for uncovering biological processes.

Conclusions:

• The proposed framework enhances the understanding of intracellular mechanisms driven by cellular communication.
• It offers a more complete and interpretable model of cellular communication networks.
• This approach advances the study of gene regulation in biological systems.