pepmg_

Study summary · research use only

AI-guided CAR designs and targeted pathway modulation to enhance multi-antigen CAR T cell durability and overcome antigen escape

Study · human · Nature communications · 2026 · DOI 10.1038/s41467-025-68272-5 · PMID 41547950

Plain-language summary

Paraphrased from the published abstract below — not a verdict on whether anything works.

In this study (species not specified; includes patient-derived leukemia samples and solid tumor models), the authors describe an AI-guided platform, CARMSeD, for predicting CAR T cell constructs prone to self-activation and dysfunction. Bispecific CD20/CD19 CAR T cells were reported to show improved persistence and anti-tumor activity. A PROTAC-based module was reported to degrade AKT3, associated with FOXO4-driven mitochondrial changes, central memory differentiation, and reduced mTOR signaling. The authors also describe a trispecific CAR T platform co-expressing a secretable CD3/CD22 bispecific engager, reported to eliminate tumors in CD19/CD20-negative models across patient-derived leukemia samples and solid tumor models. The authors describe this as an AI-guided CAR T strategy combining structure-based optimization and intracellular modulation aimed at persistence and antigen coverage.

Abstract

The persistence of CAR T cells and antigen escape remain major barriers to durable therapeutic success in hematologic malignancies. Our study integrates AI-guided design with targeted protein degradation to overcome these challenges. Utilizing an in-silico library of CAR constructs followed by an in vitro screening, we developed a predictive model, CARMSeD, which forecasts constructs prone to self-activation and dysfunction. Optimized bispecific CD20/CD19 CAR T cells demonstrate superior persistence and anti-tumor efficacy. To further improve durability, the platform incorporates a PROTAC-based module that selectively degrades AKT3, promoting FOXO4-driven mitochondrial fitness, central memory differentiation, and reduced mTOR signaling. We extended this strategy to develop a trispecific CAR T platform co-expressing a secretable CD3/CD22 bispecific engager, achieving potent tumor eradication even in CD19/CD20-negative malignancies demonstrates efficacy across patient-derived leukemia samples and solid tumor models. Together, our study introduces a next-generation AI-guided CAR T strategy that integrates structure-based optimization and intracellular modulation to improve persistence, broaden antigen coverage, and ensure durable therapeutic efficacy.

Read the full study on PubMed ↗ Open-access full text ↗

pepmg summarizes the peer-reviewed literature and links to every source — it sells nothing, ships nothing, and gives no medical, dosing, or human-use guidance. Don't just trust this summary: follow the citation to its source and read it yourself. Research use only.