Investigation of CRS-associated cytokines in CAR-T therapy with meta-GNN and pathway crosstalk

Abstract

Background Chimeric antigen receptor T-cell (CAR-T) therapy is a new and efficient cellular immunotherapy. The therapy shows significant efficacy, but also has serious side effects, collectively known as cytokine release syndrome (CRS). At present, some CRS-related cytokines and their roles in CAR-T therapy have been confirmed by experimental studies. However, the mechanism of CRS remains to be fully understood. Methods Based on big data for human protein interactions and meta-learning graph neural network, we employed known CRS-related cytokines to comprehensively investigate the CRS associated cytokines in CAR-T therapy through protein interactions. Subsequently, the clinical data for 119 patients who received CAR-T therapy were examined to validate our prediction results. Finally, we systematically explored the roles of the predicted cytokines in CRS occurrence by protein interaction network analysis, functional enrichment analysis, and pathway crosstalk analysis. Results We identified some novel cytokines that would play important roles in biological process of CRS, and investigated the biological mechanism of CRS from the perspective of functional analysis. Conclusions 128 cytokines and related molecules had been found to be closely related to CRS in CAR-T therapy, where several important ones such as IL6, IFN-γ, TNF-α, ICAM-1, VCAM-1 and VEGFA were highlighted, which can be the key factors to predict CRS.

Meta-DHGNN: method for CRS-related cytokines analysis in CAR-T therapy based on meta-learning directed heterogeneous graph neural network

“…On that basis, this study incorporates a dataset comprising 1615 cytokines and proteins. The prediction results exhibit varying probabilities of being linked to CRS [ 22 ]. To facilitate the model’s assessment on the biological dataset, a total of 200 cytokines and proteins were selected from both ends of the Meta-GNN probabilistic sequencing results to predict CRS-related cytokines for classification testing.…”

“…The comparison between the predictions of the Meta-DHGNN and Meta-GNN [ 22 ] is shown in Figure 6 , showing that 74 cytokines are in common and 62 are unique upon a more accurate cytokine interaction network.…”

Biomarkers for prediction of CAR T therapy outcomes: current and future perspectives

“…The migration and infiltration into tumor tissue are the main obstacles of CAR T efficiency in solid tumors (128) but also play an important role in hematologic malignancies (81, 97). Adequate expression of adhesion molecules (e.g., LFA-1, VCAM-1, ICAM-1, VEGFA, and others), chemokines (e.g., CCL3, CCL4, CXCL9, CXCL10, CXCL11, CXCL12, and others), and other guidance molecules are of paramount importance for effective CAR T cell homing (96,(129)(130)(131)(132)(133)(134)(135). Therefore, inadequate expression of these navigation-related molecules could serve as a negative predictive factor for the progression and outcome of CAR T cell therapy (96,131,132).…”

Serious adverse events and coping strategies of CAR-T cells in the treatment of malignant tumors

“…As a result of the high production of cytokines during CAR-T cells therapy, CRS is the most common SAEs of immune system ( 28 ). It was found that 128 cytokines may be closely related to CRS, among which IL6, IFN-γ, TNF-α, ICAM-1, VCAM-1, VEGFA and other important factors may be the key factors to predict CRS ( 29 ). Additionally, it causes SAEs throughout the body in a variety of systems ( 30 ).…”