The Application of Artificial Intelligence in Tumor Immunotherapy: Integrating Multi-Omics Data to Achieve Efficacy Prediction and Combination Strategies
DOI:
https://doi.org/10.65455/q72yq328关键词:
Artificial Intelligence, Tumor Immunotherapy, Multi-Omics, Efficacy Prediction, Combination Therapy, Machine Learning摘要
Immune checkpoint inhibitors (ICIs) have revolutionized cancer treatment, yet only a minority of patients achieve durable clinical benefit due to primary or acquired resistance. This heterogeneity necessitates precise predictive biomarkers and rational combination strategies. The rapid accumulation of multi-omics data-including genomics, transcriptomics, radiomics, pathomics, and microbiomics-offers unprecedented opportunities to decode tumor-immune interactions. Artificial intelligence, particularly machine learning and deep learning, excels at integrating high-dimensional, heterogeneous data to build interpretable efficacy prediction models and accelerate the discovery of synergistic combination regimens. In this review, we systematically summarize AI-based multimodal integration frameworks (e.g:deep multimodal fusion, graph neural networks, and single-cell omics models) and key technologies. We critically analyze the types and characteristics of multi-omics data used in immunotherapy prediction. Furthermore, we discuss AI-driven applications in personalized stratification, combination therapy target discovery, and drug synergy prediction. Finally, we identify current bottlenecks-including interpretability, data standardization, clinical validation, and model generalizability-and propose future directions. This review provides a systematic reference for transitioning from empirical treatment to data-driven precision immunotherapy.
参考
[1]CHEN H, YANG H, GUO L, et al. The Role of Immune Checkpoint Inhibitors in Cancer Therapy: Mechanism and Therapeutic Advances. MedComm, 2025, 6(10): e70412.
[2]HASLAM A, PRASAD V. Estimation of the Percentage of US Patients With Cancer Who Are Eligible for and Respond to Checkpoint Inhibitor Immunotherapy Drugs. JAMA Network Open, 2019, 2(5): e192535. DOI: https://doi.org/10.1001/jamanetworkopen.2019.2535
[3]OISAKEDE E O, et al. Predictive models for immune checkpoint inhibitor response in cancer: A review of current approaches and future directions. Drug Resistance Updates, 2025, 216: 104980. DOI: https://doi.org/10.1016/j.critrevonc.2025.104980
[4]WU Z Q, BOEN J, JINDAL S, et al. Spatial multi-omics and deep learning reveal fingerprints of immunotherapy response and resistance in hepatocellular carcinoma. bioRxiv, 2025. DOI: https://doi.org/10.1101/2025.06.11.656869
[5]TREVINO A E, WU Z Q, BOEN J, et al. Spatial omics and deep learning define an immunotherapy resistance niche in hepatocellular carcinoma. Journal for ImmunoTherapy of Cancer, 2025, 13. DOI: https://doi.org/10.1136/jitc-2025-SITC2025.0478
[6]BHUSHAN R, RAI S, JANGRA P, et al. The role of artificial intelligence in predicting cancer immunotherapy response. Oral Oncology Reports, 2025, 16: 100767. DOI: https://doi.org/10.1016/j.oor.2025.100767
[7]SALEEM M, WATSON A E, ANWAAR A, et al. Optimizing Immunotherapy: The Synergy of Immune Checkpoint Inhibitors with Artificial Intelligence in Melanoma Treatment. Biomolecules, 2025, 15: 589. DOI: https://doi.org/10.3390/biom15040589
[8]MUHAMMAD S, LI B, ZHONG W D, et al. AI-enhanced synergistic chemo-immunotherapy: From mechanistic insights to clinical translation. Critical Reviews in Oncology/Hematology, 2025, 217: 105064. DOI: https://doi.org/10.1016/j.critrevonc.2025.105064
[9]CRISTESCU R, MOGG R, AYERS M, et al. Pan-tumor genomic biomarkers for PD-1 checkpoint blockade-based immunotherapy. Science, 2018, 362(6411): eaar3593. DOI: https://doi.org/10.1126/science.aar3593
[10]AUSLANDER N, ZHANG G, LEE J S, et al. Robust prediction of response to immune checkpoint blockade therapy in metastatic melanoma. Nature Medicine, 2018, 24(10): 1542-1548. DOI: https://doi.org/10.1038/s41591-018-0157-9
[11]JIANG P, GU S, PAN D, et al. Signatures of T cell dysfunction and exclusion predict cancer immunotherapy response. Nature Medicine, 2018, 24(10): 1550-1558. DOI: https://doi.org/10.1038/s41591-018-0136-1
[12]YE B C, FAN J, XUE L, et al. iMLGAM: Integrated Machine Learning and Genetic Algorithm-driven Multiomics analysis for pan-cancer immunotherapy response prediction. 2025, 4(2): e70011 DOI: https://doi.org/10.1002/imt2.70011
[13]GSCHWIND A, OSSOWSKI S. AI Model for Predicting Anti-PD1 Response in Melanoma Using Multi-Omics Biomarkers. Cancers, 2025, 17: 714. DOI: https://doi.org/10.3390/cancers17050714
[14]ZHANG Y, VU T, PALMER D C, et al. A T-cell resilience model associated with response to immunotherapy in multiple tumor types. Nature Medicine, 2022, 28(7): 1421-1431. DOI: https://doi.org/10.1038/s41591-022-01799-y
[15]ZHANG X F, YIN Z X, CHEN X Y, et al. Machine learning–guided single-cell multiomics uncovers GDF15-driven immunosuppressive niches in NSCLC: A translational framework for overcoming anti-PD-1 resistance. BMC Biology, 2025, 23: 200. DOI: https://doi.org/10.1016/j.tranon.2025.102459
[16]KUENZI B M, PARK J, FONG S H, et al. Predicting drug response and synergy using a deep learning model of human cancer cells. Cancer Cell, 2020, 38(5): 672-684.e6. DOI: https://doi.org/10.1016/j.ccell.2020.09.014
[17]JEONG H, OH J, CHOI Y L. GraphTME: a framework for predicting response to immune checkpoint inhibitors by interpreting cell-cell interactions in the tumour microenvironment using spatial transcriptomics of tumour tissue. bioRxiv, 2025. DOI: https://doi.org/10.1101/2025.07.24.665835
[18]TREBESCHI S, DRAGO S G, BIRKBAK N J, et al. Predicting response to cancer immunotherapy using noninvasive radiomic biomarkers. Annals of Oncology, 2019, 30(6): 998-1004. DOI: https://doi.org/10.1093/annonc/mdz108
[19]XIE D, et al. Predicting the immune therapy response of advanced non-small cell lung cancer based on primary tumor and lymph node radiomics features. Frontiers in Medicine, 2025, 12: 1541376. DOI: https://doi.org/10.3389/fmed.2025.1541376
[20]HUANG Y, et al. Development of a computed tomography radiomics and CD38 integrated model: predicting immunotherapy response and investigating biological implications in non-small cell lung cancer. Journal of Thoracic Disease, 2026, 18(2): 58. DOI: https://doi.org/10.21037/jtd-2025-1828
[21]LIMETA A, JI B, LEVIN M, et al. Meta-analysis of the gut microbiota in predicting response to cancer immunotherapy in metastatic melanoma. Journal for ImmunoTherapy of Cancer, 2020, 8(2): e001314. DOI: https://doi.org/10.1172/jci.insight.140940
[22]LIU D, SCHILLING B, LIU D, et al. Integrative molecular and clinical modeling of clinical outcomes to PD1 blockade in patients with metastatic melanoma. Nature Medicine, 2019, 25(12): 1916-1927. DOI: https://doi.org/10.1038/s41591-019-0654-5
[23]KIM S T, CRISTESCU R, BASS A J, et al. Comprehensive molecular characterization of clinical responses to PD-1 inhibition in metastatic gastric cancer. Nature Medicine, 2018, 24(9): 1449-1458. DOI: https://doi.org/10.1038/s41591-018-0101-z
[24]ALTER O, OBERMAN D B, ZVIRAN A. Abstract 3687: Multi-tensor AI/ML discovery and validation of whole-transcriptome predictors of survival in response to immunotherapy from multi-omic clinical data. Cancer Research, 2025, 85(8_Supplement_1): 3687. DOI: https://doi.org/10.1158/1538-7445.AM2025-3687
[25]XU J, WANG T, LI J, et al. A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma. npj Precision Oncology, 2025, 9: 185. DOI: https://doi.org/10.1038/s41698-025-00979-6
[26]LIU H, et al. Multimodal deep learning for predicting PD-L1 biomarker and clinical immunotherapy outcomes of esophageal cancer. Frontiers in Immunology, 2025, 16: 1540013. DOI: https://doi.org/10.3389/fimmu.2025.1540013
[27]JOHANNET P, COUDRAY N, DONNELLY D M, et al. Using machine learning algorithms to predict immunotherapy response in patients with advanced melanoma. Clinical Cancer Research, 2021, 27(1): 131-140. DOI: https://doi.org/10.1158/1078-0432.CCR-20-2415
[28]ARANGO-ARGOTY G, et al. Pretrained transformers applied to clinical studies improve predictions of treatment efficacy and associated biomarkers. Nature Communications, 2025, 16: 2101. DOI: https://doi.org/10.1038/s41467-025-57181-2
[29]SI H, KUMAR S, LATA S, et al. Mechanistically Explainable AI Model for Predicting Synergistic Cancer Therapy Combinations. Current Oncology, 2025, 32: 548. DOI: https://doi.org/10.3390/curroncol32100548
##submission.downloads##
已出版
##submission.dataAvailability##
The data that support the findings of this study are available from the corresponding author upon reasonable request.
期次
栏目
##submission.license##
##submission.copyrightStatement##
##submission.license.cc.by4.footer##