QuantumXCT:通过量子纠缠和生成建模学习细胞间通信中的相互作用诱导态转换
QuantumXCT: Learning Interaction-Induced State Transformation in Cell-Cell Communication via Quantum Entanglement and Generative Modeling
AI总结:
QuantumXCT通过量子纠缠和生成建模,学习细胞间通信中的相互作用诱导态转换,揭示复杂生物系统中的通信程序发现新范式。
摘要:
从单细胞转录组学推断细胞间通信(CCC)仍然受限于对curated配体-受体数据库的依赖,这些数据库主要捕捉共表达而非信号对细胞状态的系统级影响。本文引入QuantumXCT,一种混合量子-经典生成框架,将CCC重新定义为学习细胞状态分布之间由相互作用诱导的态转换的问题。通过将转录组谱编码到高维希尔伯特空间中,QuantumXCT训练参数化量子电路以学习一个单位元变换,该变换将基线非相互作用的细胞状态映射到相互作用状态。这种方法能够在不需要先验生物学假设的情况下发现由通信驱动的细胞状态分布变化。我们通过具有已知地面真相相互作用的合成数据和卵巢癌-成纤维细胞共培养模型的单细胞RNA-seq数据验证QuantumXCT。QuantumXCT模型准确恢复了复杂的调控依赖性,包括反馈结构,并识别出主导的通信枢纽,如PDGFB-PDGFRB-STAT3轴。重要的是,所学的量子电路是可解释的:其纠缠拓扑被翻译成具有生物学意义的相互作用网络,而事后贡献分析量化了单个相互作用对观察到的态转换的相对影响。值得注意的是,通过将CCC推断从静态相互作用查找转移到学习数据驱动的态转换,QuantumXCT提供了一个生成框架用于建模细胞间通信。这项工作建立了一个新的范式,用于在复杂生物系统中发现通信程序,并突显了量子机器学习在单细胞生物学中的潜力。
英文摘要:
Inferring cell-cell communication (CCC) from single-cell transcriptomic data remains challenging. Most existing methods retrieve curated ligand-receptor pairs, score their coordinated average expression and apply statistical testing, a static and indirect strategy that tends to overlook intracellular signaling consequences, context dependence and higher-order interactions. Here, we introduce QuantumXCT, a hybrid quantum-classical framework that defines CCC as learnable transformations between cellular state distributions induced by cell-cell interaction. By encoding transcriptomic profiles into a high-dimensional Hilbert space, QuantumXCT trains parameterized quantum circuits to learn a unitary transformation mapping a baseline non-interacting cellular state to an interacting state, and infers CCC under explicitly stated modeling assumptions. Unlike methods restricted to curated ligand-receptor pairs, QuantumXCT can evaluate any cross-cell gene pair. On synthetic data with known ground-truth interactions, QuantumXCT ranked the programmed intercellular interactions above non-interacting gene pairs (ROC-AUC 0.93). On an ovarian cancer-fibroblast mono- and co-culture model, it identified a PDGFB-PDGFRB-STAT3 axis reproducible across bootstrap resamples, amplitude encodings and search algorithms, and consistent with published perturbation experiments. The learned circuit is interpretable: its entangling topology translates into interaction networks, and post hoc contribution analysis quantifies the influence of individual interactions on the observed state transitions. QuantumXCT provides an interpretable, hypothesis-generating framework for de novo discovery of communication programs, and delineates both the potential and the current limits of quantum machine learning in single-cell biology.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。