虚拟细胞的验证：基准、基线与批评
目前的验证主要依靠基准与挑战赛。多项独立研究报告深度扰动模型尚不能稳定超越简单线性基线；文献库中尚无神经肿瘤领域虚拟细胞的临床验证报告。
验证
如何检验结论：基准、基线、挑战赛与批评。
Neftel 式 GBM 状态判定能否跨平台复现？GlioState 再分析（初稿）
在 GlioState 对公开数据（GSE131928）的再分析中，肿瘤水平的状态构成在 Smart-seq2 与 10X 之间中等程度复现（6 个共有肿瘤、24 个肿瘤×状态值的 Spearman ρ=0.82；优势状态 6 例中 4 例一致）；不使用任何特征基因的分类器在留出的 10X 细胞上还原了基于特征基因的状态判定，平衡准确率 0.75（随机水平 0.25；单标志基因基线 0.53）。这只检验状态定义的可重复性，并非对任何治疗反应或虚拟细胞模型的检验，且标签不是金标准。
关键证据： VC0059 VC0060 VC0069 VC0092 · 预印本 · 共引用 8 条
关联证据
- VC0019 Predicting cellular responses to perturbation across diverse contexts with State. — Adduri AK et al., Cell, 2026
- VC0058 Virtual Cell Challenge 2026: Benchmarking zero-shot generalization across cellular contexts. — Arc Virtual Cell Initiative Team, Goodarzi H., Cell, 2026
- VC0078 Biological domain shift and statistical nesting concerns in generative AI-based spatial tumor growth prediction for pediatric diffuse midline glioma. — Li W, Sun X, Pei S., BMC medicine, 2026
- VC0054 · 预印本 An Empirical Comparison of Virtual Cell Models: Perturbation Prediction, Representation, and the Baseline Gap — Denvis O., Research Square, 2026
- VC0056 Systematic evaluation of single-cell foundation model interpretability: attention-derived edge scores add no incremental value over gene-level features for perturbation-target prediction. — Kendiukhov I., BMC genomics, 2026
- VC0077 Generative AI for spatial tumor growth on MRI: a proof-of-principle study in pediatric diffuse midline glioma. — Laslo D et al., BMC medicine, 2026
- VC0053 · 预印本 Signal, Bounds, and Baselines: Principles for Evaluating Virtual Cell Perturbation Models — Vollenweider M, Bühlmann P., bioRxiv, 2026
- VC0033 · 预印本 X-Cell: Scaling Causal Perturbation Prediction Across Diverse Cellular Contexts via Diffusion Language Models — Wang C et al., bioRxiv, 2026
- VC0060 Charting the single-cell and spatial landscape of IDH-wild-type glioblastoma with GBmap. — Ruiz-Moreno C et al., Neuro-oncology, 2025
- VC0052 Systema: a framework for evaluating genetic perturbation response prediction beyond systematic variation. — Viñas Torné R, Wiatrak M, Piran Z, Fan S, Jiang L, Teichmann SA, Nitzan M, Brbić M., Nature biotechnology, 2025
- VC0048 Deep-learning-based gene perturbation effect prediction does not yet outperform simple linear baselines. — Ahlmann-Eltze C, Huber W, Anders S., Nature methods, 2025
- VC0002 Virtual Cell Challenge: Toward a Turing test for the virtual cell. — Roohani YH et al., Cell, 2025
- VC0049 Benchmarking foundation cell models for post-perturbation RNA-seq prediction. — Csendes G, Sanz G, Szalay KZ, Szalai B., BMC genomics, 2025
- VC0050 Zero-shot evaluation reveals limitations of single-cell foundation models. — Kedzierska KZ, Crawford L, Amini AP, Lu AX., Genome biology, 2025
- VC0092 · 预印本 Mapping the spatial architecture of glioblastoma from core to edge delineates niche-specific tumor cell states and intercellular interactions — Khan SM et al., bioRxiv, 2025
- VC0070 In vivo perturb-seq of cancer and microenvironment cells dissects oncologic drivers and radiotherapy responses in glioblastoma. — Liu SJ et al., Genome biology, 2024
- VC0069 A single-cell atlas of glioblastoma evolution under therapy reveals cell-intrinsic and cell-extrinsic therapeutic targets. — Wang L, Jung J, Babikir H, Shamardani K, Jain S, Feng X, Gupta N, Rosi S, Chang S, Raleigh D, Solomon D, Phillips JJ, Diaz AA., Nature cancer, 2022
- VC0059 An Integrative Model of Cellular States, Plasticity, and Genetics for Glioblastoma. — Neftel C et al., Cell, 2019