IRnet: Immunotherapy response prediction using pathway knowledge-informed graph neural network.

Publication date: Aug 07, 2024

Immune checkpoint inhibitors (ICIs) are potent and precise therapies for various cancer types, significantly improving survival rates in patients who respond positively to them. However, only a minority of patients benefit from ICI treatments. Identifying ICI responders before treatment could greatly conserve medical resources, minimize potential drug side effects, and expedite the search for alternative therapies. Our goal is to introduce a novel deep-learning method to predict ICI treatment responses in cancer patients. The proposed deep-learning framework leverages graph neural network and biological pathway knowledge. We trained and tested our method using ICI-treated patients’ data from several clinical trials covering melanoma, gastric cancer, and bladder cancer. Our results demonstrate that this predictive model outperforms current state-of-the-art methods and tumor microenvironment-based predictors. Additionally, the model quantifies the importance of pathways, pathway interactions, and genes in its predictions. A web server for IRnet has been developed and deployed, providing broad accessibility to users at https://irnet. missouri. edu. IRnet is a competitive tool for predicting patient responses to immunotherapy, specifically ICIs. Its interpretability also offers valuable insights into the mechanisms underlying ICI treatments.

Open Access PDF

Concepts Keywords
Cancer Biological pathway
Competitive Checkpoint inhibitors
Graph Graph neural network
Immunotherapy Immunotherapy response
Missouri Machine learning
Model interpretability

Semantics

Type Source Name
disease MESH noma
disease MESH tumor immune evasion
drug DRUGBANK Honey
disease MESH microsatellite instability
disease MESH death
drug DRUGBANK Abacavir
drug DRUGBANK Coenzyme M
pathway KEGG Bladder cancer
disease MESH bladder cancer
pathway KEGG Gastric cancer
disease MESH gastric cancer
pathway KEGG Melanoma
disease MESH melanoma
disease MESH drug side effects
disease MESH cancer
pathway REACTOME Signal Transduction
drug DRUGBANK Alpha-1-proteinase inhibitor
disease MESH adenocarcinoma
drug DRUGBANK Trestolone
drug DRUGBANK Iron
drug DRUGBANK Flunarizine
drug DRUGBANK 5-amino-1 3 4-thiadiazole-2-thiol
drug DRUGBANK Saquinavir
drug DRUGBANK Ranitidine
drug DRUGBANK Aspartame
drug DRUGBANK Tropicamide
drug DRUGBANK Nivolumab
drug DRUGBANK Pembrolizumab
drug DRUGBANK Ipilimumab
drug DRUGBANK Atezolizumab
disease MESH glioblastoma
disease MESH renal carcinoma
pathway KEGG Metabolic pathways
drug DRUGBANK Amino acids
drug DRUGBANK L-Arginine
drug DRUGBANK ATP
pathway KEGG Ferroptosis
drug DRUGBANK Hyaluronic acid
pathway KEGG Necroptosis
pathway KEGG Apoptosis
disease MESH infectious diseases
pathway KEGG Pentose phosphate pathway
pathway KEGG Phenylalanine metabolism
pathway KEGG Endocytosis
disease MESH immune disease
disease MESH pathogenesis
disease MESH T cell exhaustion
disease MESH small cell lung cancer
pathway KEGG Small cell lung cancer
drug DRUGBANK Docetaxel
disease MESH NonSmall Cell Lung Cancer
disease MESH Biliary Tract Cancer
drug DRUGBANK Glycerol phenylbutyrate
drug DRUGBANK (S)-Des-Me-Ampa
drug DRUGBANK Inosine
drug DRUGBANK Activated charcoal
drug DRUGBANK Dextrose unspecified form
disease MESH infection
pathway KEGG Fatty acid metabolism
disease MESH acute myeloid leukemia
pathway KEGG Acute myeloid leukemia
disease MESH systemic lupus erythematosus
pathway KEGG Systemic lupus erythematosus
disease MESH immune tolerance
disease MESH Metastasis

Original Article

(Visited 5 times, 1 visits today)

Leave a Comment

Your email address will not be published. Required fields are marked *