Artificial Intelligence in cancer immunotherapy: from biomarker discovery to precision treatment

Cancer immunotherapy, particularly immune checkpoint inhibitors (ICIs) and cellular immunotherapies, has transformed the treatment landscape for many malignancies. However, substantial heterogeneity in treatment response, primary and acquired resistance, immune-related adverse events, and the complexity of the tumor immune microenvironment remain major challenges to the broader application of immunotherapy. The rapid development of artificial intelligence (AI), including machine learning, deep learning, generative AI, and multimodal models, provides new opportunities to address these challenges. By integrating clinical, pathological, imaging, genomic, transcriptomic, proteomic, and single-cell or spatial data, AI-based approaches can identify complex patterns and biomarkers that may not be readily captured using conventional analytical methods. These advances are increasingly supporting patient stratification, treatment-response prediction, immune profiling, and the development of personalized immunotherapy strategies.The goal of this Research Topic is to highlight emerging advances in AI-enabled cancer immunotherapy and to address the challenges that currently limit the translation of AI discoveries into clinically useful precision treatment strategies. Particular emphasis will be placed on developing and validating robust AI models for predicting immunotherapy response and resistance, identifying clinically relevant biomarkers, characterizing the tumor immune microenvironment, and anticipating immune-related adverse events. Recent advances in multi-omics integration, single-cell and spatial transcriptomics, digital pathology, medical imaging, and multimodal AI provide opportunities to improve patient stratification and treatment selection. AI applications in CAR-T/TCR-T therapies, neoantigen prediction, personalized cancer vaccines, drug and antibody discovery, and combination immunotherapy may further expand personalized treatment approaches. Contributions involving generative AI and large language models, explainable and causal AI, real-world data, and clinical decision-support systems are also encouraged. Ultimately, this Research Topic seeks to promote interdisciplinary research that bridges computational innovation with biological validation and clinical translation.We welcome original research articles, systematic reviews, meta-analyses, methodological studies, reviews, perspectives, and short communications addressing AI applications in cancer immunotherapy. Topics of interest include, but are not limited to:• AI-based prediction of immunotherapy response and resistance, including immune checkpoint inhibitors and combination therapies.• AI-driven biomarker discovery and patient stratification, including predictive and prognostic biomarkers.• AI-assisted characterization of the tumor immune microenvironment, using pathology, imaging, and molecular data.• Multi-omics, single-cell, and spatial transcriptomics integration for immunotherapy research.• Prediction, early detection, and management of immune-related adverse events (irAEs).• AI applications in cellular immunotherapy, including CAR-T, TCR-T, and related approaches.• AI-assisted neoantigen prediction and personalized cancer vaccine design.• Generative AI, large language models, multimodal AI, explainable AI, and causal AI in immunotherapy.• Clinical translation and implementation, including real-world data, clinical decision support, validation, reproducibility, ethics, and data security.• AI-assisted drug, antibody, and immune-target discovery for next-generation immunotherapies. Topic editors: Shaozhuo Huang, Chen Yang, Yongjian Chen Source: https://www.frontiersin.org/research-topics/86810/artificial-intelligence-in-cancer-immunotherapy-from-biomarker-discovery-to-precision-treatment