人工智能虚拟细胞发展现况与其在肿瘤研究中的应用前景

黄炜; 石汉平

doi:10.16689/j.cnki.cn11-9349/r.2026.01.003

PDF(940 KB)

肿瘤代谢与营养电子杂志 ›› 2026, Vol. 13 ›› Issue (1) : 13-19. DOI: 10.16689/j.cnki.cn11-9349/r.2026.01.003

专家论坛

人工智能虚拟细胞发展现况与其在肿瘤研究中的应用前景

¹黄炜, ^1,2石汉平

作者信息 +

The current development status of artificial intelligence virtual cells and their application prospects in tumor research

¹Huang Wei, ^1,2Shi Hanping

Author information +

文章历史 +

摘要

随着人工智能与单细胞技术的快速发展,人工智能虚拟细胞凭借“机制+数据”融合建模能力,成为突破肿瘤研究复杂性与异质性挑战的关键工具。本文系统梳理人工智能虚拟细胞的理论基础、发展现况及肿瘤研究应用前景。在理论层面,人工智能虚拟细胞以“分子-通路-细胞-微环境”层级关联为生物学基础,结合生成式模型、图神经网络、Transformer等人工智能算法,通过多尺度建模实现从分子机制到组织功能的跨层级整合。在技术进展方面,人工智能虚拟细胞已实现多组学数据整合、空间数据融入及“建模-可视化-部署”工具链构建。在肿瘤研究中,人工智能虚拟细胞可解析代谢重编程与免疫逃逸机制、加速抗肿瘤药物高通量筛选与联合方案优化,并通过患者特异性模型及虚拟临床试验推动临床转化。当前人工智能虚拟细胞面临模型泛化性、数据标准化、算法可解释性及计算资源需求大等挑战,未来需通过建立多中心标准化数据集、开发可解释人工智能算法及优化模型架构,进一步推动其在肿瘤精准诊疗中的应用。

Abstract

With the rapid development of artificial intelligence and single-cell technology, artificial intelligence virtual cells, relying on their "mechanism + data" integrated modeling capabilities, have become a key tool to break through the challenges of complexity and heterogeneity in tumor research. This article systematically reviews the theoretical basis, current development status and application prospects in tumor research of artificial intelligence virtual cells. At the theoretical level, artificial intelligence virtual cells are based on the biological foundation of the hierarchical association of "molecules-pathways-cells-microenvironment", combined with artificial intelligence algorithms such as generative models, graph neural networks, and Transformers, to achieve cross-level integration from molecular mechanisms to tissue functions through multi-scale modeling. In terms of technological progress, artificial intelligence virtual cells have achieved multi-omics data integration, spatial data fusion, and the construction of a "modeling-visualization-deployment" tool chain. In tumor research, artificial intelligence virtual cells can analyze metabolic reprogramming and immune escape mechanisms, accelerate high-throughput screening of anti-tumor drugs and optimization of combination regimens, and promote clinical transformation through patient-specific models and virtual clinical trials. At present, artificial intelligence virtual cells are confronted with challenges such as model generalization, data standardization, algorithm interpretability, and high demand for computing resources. In the future, it is necessary to further promote their application in precision diagnosis and treatment of tumors by establishing multi-center standardized datasets, developing interpretable artificial intelligence algorithms, and optimizing model architectures.

导出引用

黄炜, 石汉平. 人工智能虚拟细胞发展现况与其在肿瘤研究中的应用前景[J]. 肿瘤代谢与营养电子杂志. 2026, 13(1): 13-19 https://doi.org/10.16689/j.cnki.cn11-9349/r.2026.01.003

Huang Wei, Shi Hanping. The current development status of artificial intelligence virtual cells and their application prospects in tumor research[J]. Electronic Journal of Metabolism and Nutrition of Cancer. 2026, 13(1): 13-19 https://doi.org/10.16689/j.cnki.cn11-9349/r.2026.01.003

参考文献

[1] YAN H, WENG D, LI D, et al. Prior knowledge-guided multilevel graph neural network for tumor risk prediction and interpretation via multi-omics data integration [J]. Brief Bioinform, 2024, 25(3): bbae184.
[2] FANG S J, YIN Z D, CAI Q, et al. Harnessing artificial intelligence for brain disease: advances in diagnosis, drug discovery, and closed-loop therapeutics [J]. Front Neurol,2025,16:1615523.
[3] JIAN L, BAI X, MA S. Stochastic dynamical analysis for the complex infectious disease model driven by multisource noises [J]. PLoS One, 2024, 19(1): e0296183.
[4] HANSEN J, JAIN A R, NENOV P, et al. From transcriptomics to digital twins of organ function [J]. Front Cell Dev Biol,2024,12:1240384.
[5] BUNNE C, ROOHANI Y, ROSEN Y, et al. How to build the virtual cell with artificial intelligence: Priorities and opportunities [J]. Cell,2024,187(25):7045-7063.
[6] OGILVIE L A, WIERLING C, KESSLER T, et al. Predictive Modeling of Drug Treatment in the Area of Personalized Medicine [J]. Cancer Inform,2015,14(Suppl 4):95-103.
[7] SOVé R J, JAFARNEJAD M, ZHAO C, et al. QSP-IO: A Quantitative Systems Pharmacology Toolbox for Mechanistic Multiscale Modeling for Immuno-Oncology Applications [J]. CPT Pharmacometrics Syst Pharmacol,2020,9(9):484-497.
[8] SUN C, WANG A, ZHOU Y, et al. Spatially resolved multi-omics highlights cell-specific metabolic remodeling and interactions in gastric cancer [J]. Nat Commun,2023,14(1):2692.
[9] WANG S, QIAN L, CAO T, et al. Advances in the Study of CircRNAs in Tumor Drug Resistance [J]. Front Oncol,2022,12:868363.
[10] WU B X, WU Z, HOU Y Y, et al. Application of three-dimensional (3D) bioprinting in anti-cancer therapy [J]. Heliyon, 2023, 9(10): e20475.
[11] FEI X, KONG L, SHI C, et al. Identification of Prognosis-Related Molecular Subgroups and Construction of a Prognostic Prediction Model Using Immune-Related Genes in Pancreatic Cancer [J]. J Oncol,2022,2022:7117014.
[12] CORTESI M, GIORDANO E. Driving cell response through deep learning, a study in simulated 3D cell cultures [J]. Heliyon, 2024, 10(9): e29395.
[13] SAVULESCU A F, JACOBS C, NEGISHI Y, et al. Pinpointing Cell Identity in Time and Space [J]. Front Mol Biosci,2020,7:209.
[14] HALLOU A, HE R, SIMONS B D, et al. A computational pipeline for spatial mechano-transcriptomics [J]. Nat Methods,2025,22(4):737-750.
[15] ZHANG J, UBAS A A, DE BORJA R, et al. Tahoe-100m: a giga-scale single-cell perturbation atlas for context-dependent gene function and cellular modeling [J]. BioRxiv, 2025: 2025.02. 20.639398.
[16] OLIVIERO-DURMUS A, JANATI Y, MOULINES E, et al. Generative modelling meets Bayesian inference: a new paradigm for inverse problems [J]. Philos Trans A Math Phys Eng Sci,2025,383(2299):20240334.
[17] KUMAR R, SPORN K, PRABHAKAR V, et al. Computational and imaging approaches for precision characterization of bone, cartilage, and synovial biomolecules [J]. J Pers Med, 2025, 15(7).
[18] SCHAFFER L V, HU M, QIAN G, et al. Multimodal cell maps as a foundation for structural and functional genomics [J]. Nature,2025,642(8066):222-231.
[19] LYU R, QU Y, DIVARIS K, et al. Methodological considerations in longitudinal analyses of microbiome data: a comprehensive review [J]. Genes (Basel), 2023, 15(1).
[20] ROOHANI Y H, HUA T J, TUNG P Y, et al. Virtual cell challenge: toward a turing test for the virtual cell [J]. Cell,2025,188(13):3370-3374.
[21] PUNIYA B L. Artificial-intelligence-driven innovations in mechanistic computational modeling and digital twins for biomedical applications [J]. J Mol Biol,2025,437(17):169181.
[22] HAO M, GONG J, ZENG X, et al. Large-scale foundation model on single-cell transcriptomics [J]. Nat Methods,2024,21(8):1481-1491.
[23] CUI H, WANG C, MAAN H, et al. ScGPT: toward building a foundation model for single-cell multi-omics using generative AI [J]. Nat Methods,2024,21(8):1470-1480.
[24] BIAN H, CHEN Y, DONG X, et al. ScMulan: a multitask generative pre-trained language model for single-cell analysis [J]. bioRxiv, 2024: 2024.01.25.577152.
[25] HETMANN M, PARIGGER L, SIRELKHATIM H, et al. Folding the human proteome using BioNeMo: a fused dataset of structural models for machine learning purposes [J]. Sci Data,2024,11(1):591.
[26] PARK S Y, CHOI D H, SONG J, et al. Driving towards digital biomanufacturing by CHO genome-scale models [J]. Trends Biotechnol,2024,42(9):1192-1203.
[27] BELL A T F, MITCHELL J T, KIEMEN A L, et al. PanIN and CAF transitions in pancreatic carcinogenesis revealed with spatial data integration [J]. Cell Syst,2024,15(8):753-769.e5.
[28] XU V A, LEE H, LONG B, et al. MAGMA: microbial and algal growth modeling application [J]. N Biotechnol,2025,85:16-22.
[29] KIEMEN A L, BRAXTON A M, GRAHN M P, et al. CODA: quantitative 3D reconstruction of large tissues at cellular resolution [J]. Nat Methods,2022,19(11):1490-1499.
[30] GHAFFARIZADEH A, HEILAND R, FRIEDMAN S H, et al. PhysiCell: an open source physics-based cell simulator for 3-D multicellular systems [J]. PLoS Comput Biol, 2018, 14(2): e1005991.
[31] HEILAND R, BERGMAN D, LYONS B, et al. PhysiCell Studio: a graphical tool to make agent-based modeling more accessible [J]. GigaByte, 2024, 2024: gigabyte128.
[32] JOHNSON J A I, BERGMAN D R, ROCHA H L, et al. Human interpretable grammar encodes multicellular systems biology models to democratize virtual cell laboratories [J]. Cell,2025,188(17):4711-4733.e37.
[33] LI W, MAO Z, XIAO Z, et al. Large language model for knowledge synthesis and AI-enhanced biomanufacturing [J]. Trends Biotechnol,2025,43(8):1864-1875.
[34] MEDLOCK G L, PAPIN J A. Guiding the refinement of biochemical knowledgebases with ensembles of metabolic networks and machine learning [J]. Cell Syst,2020,10(1):109-119.e3.
[35] GUINN S, KINNY-K?STER B, TANDURELLA J A, et al. Transfer learning reveals cancer-associated fibroblasts are associated with epithelial-mesenchymal transition and inflammation in cancer cells in pancreatic ductal adenocarcinoma [J]. Cancer Res,2024,84(9):1517-1533.
[36] RAHAT M A, BITTERMAN H, LAHAT N. Molecular mechanisms regulating macrophage response to hypoxia [J]. Front Immunol,2011,2:45.
[37] KE X, CHEN C, SONG Y, et al. Hypoxia modifies the polarization of macrophages and their inflammatory microenvironment, and inhibits malignant behavior in cancer cells [J]. Oncol Lett,2019,18(6):5871-5878.
[38] LUO R, SUN L, XIA Y, et al. BioGPT: generative pre-trained transformer for biomedical text generation and mining [J]. Brief Bioinform, 2022, 23(6).
[39] MI H, SIVAGNANAM S, HO W J, et al. Computational methods and biomarker discovery strategies for spatial proteomics: a review in immuno-oncology [J]. Brief Bioinform, 2024, 25(5).
[40] STEELE N G, CARPENTER E S, KEMP S B, et al. Multimodal mapping of the tumor and peripheral blood immune landscape in human pancreatic cancer [J]. Nat Cancer,2020,1(11):1097-1112.
[41] LUTZ J D, MATHIAS A, GERMAN P, et al. Physiologically-based pharmacokinetic modeling of remdesivir and its metabolites to support dose selection for the treatment of pediatric patients with COVID-19 [J]. Clin Pharmacol Ther,2021,109(4):1116-1124.
[42] GAW N, HAWKINS-DAARUD A, HU L S, et al. Integration of machine learning and mechanistic models accurately predicts variation in cell density of glioblastoma using multiparametric MRI [J]. Sci Rep,2019,9(1):10063.
[43] TAO B, LI X, HAO M, et al. Organoid-guided precision medicine: from bench to bedside [J]. MedComm (2020), 2025, 6(5): e70195.
[44] KOSHIYAMA A, KAZIM E, TRELEAVEN P, et al. Towards algorithm auditing: managing legal, ethical and technological risks of AI, ML and associated algorithms [J]. R Soc Open Sci,2024,11(5):230859.
[45] TANG M, MU F, CUI C, et al. Research frontiers and trends in the application of artificial intelligence to sepsis: a bibliometric analysis [J]. Front Med (Lausanne),2022,9:1043589.
[46] PENG Y, DENG H. Medical image fusion based on machine learning for health diagnosis and monitoring of colorectal cancer [J]. BMC Med Imaging,2024,24(1):24.
[47] BABU B, VINAYACHANDRAN D, C G, et al. Bibliometric analysis of the role of artificial intelligence in detecting maxillofacial fractures [J]. Cureus, 2024, 16(12): e75630.
[48] MORALES-GALICIA A E, RINCóN-SáNCHEZ M N, RAMíREZ-MEJíA M M, et al. Outcome prediction for cholangiocarcinoma prognosis: Embracing the machine learning era [J]. World J Gastroenterol,2025,31(21):106808.
[49] ZHANG S, CUI Y, XU D, et al. A collaborative inference strategy for medical image diagnosis in mobile edge computing environment [J]. PeerJ Comput Sci, 2025, 11: e2708.
[50] CHEN C, CHEN Z, LUO W, et al. Ethical perspective on AI hazards to humans: A review [J]. Medicine (Baltimore), 2023, 102(48): e36163.
[51] PROCHASKA M, ALFANDRE D. Artificial intelligence, ethics, and hospital medicine: Addressing challenges to ethical norms and patient-centered care [J]. J Hosp Med,2024,19(12):1194-1196.
[52] SHAHIN M H, BHATTACHARYA S, SILVA D, et al. Open data revolution in clinical research: opportunities and challenges [J]. Clin Transl Sci,2020,13(4):665-674.