Immune Cell Knowledge Graph

An interactive tool for immune cell type specific gene set annotations backed by >24K published studies

Immune Cell Knowledge Graph

Publication:

Literature-scaled immunological gene set annotation using AI-powered immune cell knowledge graph (ICKG)

Authors: Shan He1, Yukun Tan1, Matthew Gubin2, Qing Ye1, Hind Rafei3, Weiyi Peng4, Katayoun Rezvani2, Vakul Mohanty1*

, Ken Chen1*

1 Department of Bioinformatics and Computational Biology, The University of Texas MD Anderson Cancer Center, Houston, Texas 77030, USA
3 Department of Immunology, The University of Texas MD Anderson Cancer Center, Houston, Texas 77030, USA
3 Department of Stem Cell Transplantation and Cellular Therapy, The University of Texas MD Anderson Cancer Center, Houston, Texas 77030, USA
3Department of Biology and Biochemistry, The University of Houston, Houston, TX, USA

Gene Set Annotation

Analyze a set of genes to discover their functional enrichment in specific immune cell types via PageRank. PageRank works by traversing the graph and determining node importance based on network connectivity, giving more weight to well-connected nodes

- Demo example: NK subgraph showing how genes in NK_inhibitory gene set are linked to "inhibitory immune checkpoint" according to literatures

- Manuscript reference: "ICKGs outperform traditional enrichment methods in gene set annotation"

Input your genes of interest and select a cell type to identify significant pathway associations supported by published literatures.

Initializing...
Validation
Processing
Analysis
Completion
Analyzing genes, please wait...

Example Results Comparison

Compare the results of traditional Over-Representation Analysis (ORA) with our Immune Cell Knowledge Graph (ICKG) approach on several gene sets. Click on the links below to view detailed results for each example.

CD4 Unassigned Gene Set

This example shows the pathway analysis results for CD4 T cell unassigned gene set. ICKG results provide more cell type specific and literature-backed pathway associations compared to traditional ORA.

ORA Results ICKG Results

CD4 Dysfunction Gene Set

Analysis of genes associated with CD4 T cell dysfunction. The ICKG approach reveals functional relationships backed by literature evidence, highlighting immune checkpoint pathways and exhaustion markers.

ORA Results ICKG Results

CD8 Unassigned Gene Set

Pathway analysis for CD8 T cell unassigned gene set, demonstrating how ICKG can identify relevant biological pathways that may be missed by traditional ORA approaches.

ORA Results ICKG Results

CD8 Chromatin Gene Set

This example shows analysis of chromatin-associated genes in CD8 T cells. ICKG analysis reveals specific functional relationships related to epigenetic regulation and its impact on T cell function.

ORA Results ICKG Results

Frequently Asked Questions

What is the Immune Cell Knowledge Graph? ▼
The Immune Cell Knowledge Graph is constructed by integrating relevant published literature and weaving together biomedical entities from independent studies. Researchers can leverage these graphs to perform cell type specific gene set annotations.
Which cell types are currently supported? ▼
The tool currently supports four major immune cell types: - NK Cells (Natural Killer Cells) - T Cells - B Cells - Macrophages
How do I use the Gene Set Annotation feature? ▼
To use the Gene Set Annotation feature: 1. Enter your genes of interest (one per line) in the text area 2. Select the relevant cell type from the dropdown menu 3. Click "Analyze" to see pathway relationships and statistical significance The tool will return pathway associations supported by published literature.