Enhanced Prediction of CAR T-Cell Cytotoxicity with Quantum-Kernel Methods

2025-07-30

AI Summary

Predicting cytotoxicity of chimeric antigen receptor (CAR) T cells is challenging due to the vast combinatorial space of co-stimulatory domains and sparse experimental data. Method: We propose a projection quantum kernel (PQK)-based quantum machine learning approach that maps classical biological features into a high-dimensional Hilbert space and performs gate-based quantum kernel computation on a 61-qubit system, significantly enhancing modeling capability in low-information regimes with limited samples. Contribution/Results: This work represents the largest-scale biomedical application of PQK to date and the first systematic use of quantum kernel methods for modeling CAR structure–function relationships. It accurately identifies critical signaling domains and their positional effects. In cytotoxicity prediction, our method substantially outperforms classical machine learning baselines, demonstrating the efficacy and frontier potential of quantum-enhanced kernel learning in data-scarce biomedical settings.

Technology Category

• Machine Learning: Quantum Machine Learning
• Data Mining & Knowledge Management: Intelligent Query Processing
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Chimeric antigen receptor (CAR) T-cells are T-cells engineered to recognize and kill specific tumor cells. Through their extracellular domains, CAR T-cells bind tumor cell antigens which triggers CAR T activation and proliferation. These processes are regulated by co-stimulatory domains present in the intracellular region of the CAR T-cell. Through integrating novel signaling components into the co-stimulatory domains, it is possible to modify CAR T-cell phenotype. Identifying and experimentally testing new CAR constructs based on libraries of co-stimulatory domains is nontrivial given the vast combinatorial space defined by such libraries. This leads to a highly data constrained, poorly explored combinatorial problem, where the experiments undersample all possible combinations. We propose a quantum approach using a Projected Quantum Kernel (PQK) to address this challenge. PQK operates by embedding classical data into a high dimensional Hilbert space and employs a kernel method to measure sample similarity. Using 61 qubits on a gate-based quantum computer, we demonstrate the largest PQK application to date and an enhancement in the classification performance over purely classical machine learning methods for CAR T cytotoxicity prediction. Importantly, we show improved learning for specific signaling domains and domain positions, particularly where there was lower information highlighting the potential for quantum computing in data-constrained problems.

Problem

• Predict CAR T-cell cytotoxicity more accurately
• Address combinatorial space of co-stimulatory domains
• Improve learning in data-constrained scenarios

Innovation

• Quantum-Kernel Methods for CAR T-Cell prediction
• Projected Quantum Kernel enhances classification performance
• Largest PQK application on 61-qubit quantum computer