TG468: A Text Graph Convolutional Network for Predicting Clinical Response to Immune Checkpoint Inhibitor Therapy

Abstract

AbstractImmunotherapy has achieved significant success in tumor treatment. However, due to disease heterogeneity, only a fraction of patients respond well to immune checkpoint inhibitor (ICI) treatment. To address this issue, we developed a Text Graph Convolutional Network (Text GCN) model called TG468 for clinical response prediction, which uses the patient’s whole exome sequencing (WES) data across different cohorts to capture the molecular profile and heterogeneity of tumors. TG468 can effectively distinguish survival time for patients who received ICI therapy and outperforms single gene biomarkers and TMB, indicating its strong predictive ability for the clinical response of ICI therapy. Moreover, the prediction results obtained from TG468 allow for the identification of immune status differences among specific patient types in the TCGA dataset. This rationalizes the model prediction results. Overall, TG468 could be a useful tool for predicting clinical outcomes and the prognosis of patients treated with immunotherapy. This could further promote the application of ICI therapy in the clinic.