Traditional antigen discovery has relied heavily on bulk omics. RNA sequencing of tumour biopsies identifies transcripts that are elevated in tumours relative to normal tissues, and mass spectrometry of immunopeptidomes identifies the peptides actually presented on human leukocyte antigen molecules. These approaches have been enormously productive, yielding the tumour-associated antigens that underpin therapeutic cancer vaccines, bispecific antibodies, and adoptive cell therapies. Yet they share a structural blind spot: they measure abundance, not arrangement. A transcript that is highly expressed in a tumour may also be expressed in a vital healthy tissue, and a peptide that appears abundant in a dissociated tumour sample may, in the intact tissue, be presented only on stromal cells rather than on the malignant compartment itself. Dissociation destroys the spatial relationships that the immune system, operating in intact tissue, would encounter.

Proximity labelling technologies emerged precisely to address this limitation. By fusing an engineered enzyme, such as a promiscuous biotin ligase or a peroxidase, to a protein of interest, researchers can covalently tag molecules that come within a few tens of nanometres of that protein in living cells. The tagged molecules can then be enriched and identified by mass spectrometry, producing a snapshot of the local molecular neighbourhood rather than the global composition of the cell. Applied to tumour biology, proximity labelling offers a way to ask what molecules physically congregate around a given marker protein, information that bulk profiling cannot provide. The microenvironment of a membrane protein, its partners, its neighbours in the plasma membrane, and the proteins trafficked alongside it, constitutes a layer of biological organisation that is invisible to standard transcriptomics and only partially accessible to conventional proteomics.

The challenge that arises once proximity data are generated is computational. A proximity labelling experiment produces a network-like structure: bait proteins, their tagged neighbours, the abundances of those neighbours, and the connections among them across conditions and cell states. Representing this as a simple list discards most of its meaning. Graph-structured data demand graph-aware analysis, and this is where modern graph learning methods become relevant. Graph neural networks and related architectures are designed to learn representations of nodes in a network that incorporate information from their local neighbourhoods, so that the identity of a protein is encoded not only by its own properties but by the company it keeps. In biological settings, this inductive bias is often exactly right: function in cellular systems is relational, and proteins that occupy similar network positions frequently share functional roles even when their sequences are unrelated.

Applying graph learning to proximity data in the tumour context creates an opportunity to formalise an intuition that immunologists have long held informally. An antigen that is safe to target therapeutically is not simply one that is absent from healthy tissue in a bulk measurement; it is one whose presentation is unlikely to occur on healthy cells under the conditions the immune system will actually encounter. Proximity provides a proxy for this contextual specificity. A candidate antigen that is consistently found in the immediate molecular neighbourhood of validated tumour markers, and that participates in the same spatial programmes as known malignant-surface proteins, carries more evidence of tumour association than a candidate identified by expression alone. Graph learning allows this evidence to be aggregated systematically across many candidates and many data modalities, rather than assessed one protein at a time by expert curation.

The therapeutic stakes of this problem are considerable. CAR T cell therapy, which engineers a patient’s T cells to recognise a surface antigen, has produced remarkable outcomes in haematological malignancies where a truly tumour-restricted target such as CD19 exists. Solid tumours have proven far more resistant, and a major reason is the absence of comparable target antigens. The antigens that are available on solid tumours, such as HER2, EGFR, or B7-H3, are frequently shared with essential healthy tissues, and targeting them produces on-target off-tumour toxicity that can be dose-limiting or fatal. The field has responded with a variety of engineering strategies, including logic-gated CARs that require two antigens to be present simultaneously, tunable affinity receptors that respond only to high antigen density, and adaptor systems that allow dosing control. All of these strategies depend on knowing which combinations of antigens are jointly specific to tumours, and this is a question about spatial co-organisation that proximity-guided approaches are well positioned to answer.

There is also a deeper immunological rationale for thinking in terms of proximity. The immune synapse itself is a proximity phenomenon: a T cell commits to killing only after sustained engagement with a target cell, integrating signals from many receptor-ligand interactions across the contact interface. Antigens that cluster together on the tumour surface may be recognised more effectively than antigens presented in isolation, because multivalent engagement strengthens T cell receptor signalling and can overcome the inhibitory signals that tumours deploy. Conversely, an antigen that is spatially segregated from co-stimulatory context may be immunologically silent even if it is abundant. Understanding the spatial organisation of tumour antigens therefore has implications not only for target selection but for predicting the quality of the immune response that targeting will provoke.

The tumour microenvironment adds further layers of complexity that proximity-aware methods are suited to capture. Tumours are not homogeneous masses of malignant cells; they are ecosystems containing fibroblasts, endothelial cells, macrophages, T cells, and extracellular matrix, all arranged in structured architectures that vary between patients and between regions of the same tumour. A candidate antigen expressed by tumour-associated fibroblasts, for example, might be attractive for stromal targeting strategies but inappropriate for direct tumour-cell killing. Distinguishing the malignant compartment from the reactive stromal compartment requires information about which proteins co-localise with which, and dissociated single-cell methods, while powerful, lose the tissue architecture that defines these compartments. Proximity labelling performed in intact systems, combined with graph-based inference, offers a route to recovering some of this architectural information from molecular data.

From a machine learning perspective, the tumour antigen problem illustrates a broader trend in computational biology: the shift from classification of individual entities to inference over relational structures. Early bioinformatics treated each gene or protein as an independent feature, and predictive models were built on expression vectors. The realisation that biological molecules operate in networks led to a family of methods that propagate information across interaction graphs, including network propagation algorithms, random walk approaches, and eventually graph neural networks. Each generation of methods has expanded the kinds of questions that can be asked. Where earlier approaches could ask whether a protein is connected to known disease genes, graph learning can ask whether a protein occupies a network position characteristic of disease-relevant molecules, a subtler and often more robust criterion. In the antigen discovery setting, this means the model can learn what the neighbourhood of a validated tumour antigen looks like and then score uncharacterised candidates by the similarity of their neighbourhoods.

Validation remains the essential counterweight to computational prediction, and the history of antigen discovery offers sobering lessons about candidates that looked compelling in silico but failed in vivo. A predicted proximity antigen must survive several successive tests: confirmation that the protein is genuinely presented on the tumour cell surface by human leukocyte antigen molecules, demonstration that healthy tissues lack comparable presentation, evidence that T cells capable of recognising the presented peptide exist in patients, and finally evidence that engaging those T cells produces tumour killing without tissue damage. Each of these tests is demanding, and attrition between stages is high. Computational methods that incorporate proximity information improve the front end of this pipeline by enriching the candidate list for molecules likely to pass the later stages, which is a meaningful advance even though no computational prediction can substitute for experimental validation.

The timing of this work within the broader technological landscape is notable. Spatial transcriptomics and spatial proteomics have matured rapidly, multiplexed imaging now routinely profiles dozens of proteins in intact tissue sections, and proximity labelling has been adapted to an expanding range of model systems. Meanwhile, immunopeptidomics has improved in sensitivity to the point where thousands of presented peptides can be catalogued from limited clinical material. The convergence of these technologies with graph-based machine learning creates conditions in which antigen discovery can become less dependent on serendipity. Historically, many successful tumour antigens were found through patient-specific approaches, such as isolating tumour-infiltrating lymphocytes and identifying their targets, which is powerful but slow and individualised. A systematic, proximity-informed discovery framework aims to generalise this process, producing catalogues of candidate antigens that can serve the broader population of patients.

There are also implications beyond T cell therapy. Antibody-drug conjugates require surface antigens with sufficient differential expression and internalisation behaviour, and the proximity context of an antigen can inform predictions about its trafficking and its accessibility to circulating antibodies. Bispecific molecules that bridge tumour cells and T cells depend on pairs of antigens whose joint expression pattern is tumour-restricted, and proximity data speak directly to co-localisation. Even vaccine design benefits, since peptide antigens that arise in the context of a tumour-specific molecular programme are more likely to elicit responses that discriminate tumour from self. In each of these therapeutic modalities, the fundamental question is the same: which molecular features distinguish the tumour cell surface in its intact context, and how confidently can that distinction be made for a given patient population.

As the field moves forward, the integration of proximity-guided graph learning into antigen discovery pipelines will likely be judged by a practical standard: whether the candidates it surfaces translate into therapies with wider therapeutic windows than those discovered by expression-based approaches alone. The conceptual contribution, however, may prove equally durable. By treating the tumour cell surface as a structured, relational system rather than a list of abundances, this line of work aligns the computational representation of tumour biology with the way the immune system itself reads that biology, through contact, context, and the molecular neighbourhoods in which every antigen is embedded.

Subject of Research: Proximity-guided graph learning reveals tumour-associated proximity antigens

Article Title: Proximity-guided graph learning reveals tumour-associated proximity antigens

Article References: Scandore, C., Malone, C. F., May, C. K., de Regt, A. K., Guernsey, J., Ma, H., Dephoure, N., Setter, B., Howell, R. A., Johnson, K. R., Farr, C. L., Romero, S., Vignale, L., Vittum, T., Dawson, E., Habtetsion, T., Nardi, F., Woodruff, B., Mathay, M., … Fadeyi, O. O. (2026). Proximity-guided graph learning reveals tumour-associated proximity antigens. Nature. https://doi.org/10.1038/s41586-026-11003-7

Image Credits: AI Generated

DOI: 10.1038/s41586-026-11003-7

Keywords: Proximity-guided, graph, learning, reveals, tumour-associated, proximity, antigens, scientific research

The technological foundation of scRNA-seq lies in its ability to capture transcriptomic profiles of thousands to millions of individual cells, rather than averaging gene expression across bulk tissue samples. This single-cell resolution enables researchers to delineate the cellular heterogeneity within tumours, unmask rare cell types, and trace dynamic cellular states that collectively influence tumour progression and therapeutic resistance. Unlike traditional bulk RNA sequencing, which blurs distinctions between cell types, scRNA-seq reveals the nuanced cellular architecture and gene expression programs that underpin cancer biology, offering a powerful lens through which to assess intratumoral diversity.

Despite its roots in basic cancer biology, the clinical promise of scRNA-seq is steadily unfolding. The translation of these molecular insights into clinical applications could radically improve diagnostic precision, prognostic accuracy, and therapeutic stratification. As emphasized in a comprehensive recent review by Boxer et al., the body of scRNA-seq cancer research now coalesces around four central objectives with direct clinical implications: deciphering tumour heterogeneity, characterizing the tumour microenvironment, uncovering mechanisms of therapy resistance, and guiding personalized treatment strategies. Each of these goals directs the growing momentum in translational oncology towards more sophisticated, patient-tailored interventions.

Tumour heterogeneity remains a foremost challenge in oncology, often driving variable patient outcomes and complicating treatment. Single-cell sequencing elucidates this heterogeneity by capturing the spectrum of malignant cell subpopulations coexisting within a single tumour. Researchers have identified distinct, transcriptionally defined cancer cell states that correlate with metastatic potential, proliferative capacity, and therapeutic susceptibility. This deepened knowledge has revealed lineage plasticity and epigenetic reprogramming as central components of cancer evolution. Consequently, scRNA-seq stands to redefine tumour classification beyond histopathology and genomic mutations, paving the way for molecularly informed diagnoses.

Equally critical, the tumour microenvironment—once considered a passive backdrop—has been exposed as a dynamic and influential player in oncogenesis. Single-cell analysis has catalogued immune cell subsets, cancer-associated fibroblasts, endothelial cells, and myeloid populations that engage in complex crosstalk with malignant cells. These interactions modulate immune evasion, angiogenesis, and metastatic dissemination. Notably, dissecting the immune landscape at single-cell resolution has elucidated the mechanisms underpinning responses and resistance to immunotherapies. Such insights facilitate the identification of predictive biomarkers and novel immunomodulatory targets, offering avenues to potentiate clinical efficacy.

Resistance to therapy, encompassing both innate and acquired forms, is a central obstacle in achieving durable remissions. scRNA-seq has shed light on subclonal populations harboring resistance-associated transcriptional programs and survival niches within the tumour microenvironment that protect vulnerable cells from treatment-induced apoptosis. This granular analysis enables the tracing of evolutionary trajectories under therapeutic pressure, informing combination treatments and adaptive therapeutic regimens designed to preempt or overcome resistance. In the clinical context, monitoring such cellular dynamics through longitudinal sampling and single-cell profiling holds promise for dynamic therapy adjustment.

In guiding personalized therapies, scRNA-seq empowers clinicians and researchers to detect actionable molecular alterations and pathway activations present within specific tumour compartments. This approach surpasses the limitations of bulk sequencing by revealing cell-type-specific vulnerabilities, including rare but clinically actionable subpopulations. Personalized cancer vaccines, targeted therapies, and cell-based immunotherapies can be optimized with these data, enhancing precision medicine paradigms. Moreover, single-cell transcriptomics aids in patient stratification by identifying molecular signatures predictive of therapeutic response and adverse events.

Despite these groundbreaking advances, scRNA-seq technology currently faces notable technical and analytical challenges. Sample dissociation methods may induce transcriptional artifacts or selectively bias cell representation, while the high dimensionality of single-cell data demands sophisticated computational methodologies to integrate biological variation with technical noise. Additionally, the inherent cost and complexity of scRNA-seq limit its widespread clinical adoption at present. Addressing these limitations requires concerted interdisciplinary efforts encompassing improved experimental protocols, robust bioinformatics pipelines, and scalable platforms suitable for clinical laboratory environments.

Looking towards the future, integration of scRNA-seq with complementary modalities such as spatial transcriptomics, single-cell epigenomics, and proteomics promises to deliver a more holistic view of tumour biology and microenvironmental architecture. Spatial context, in particular, is critical as cell-to-cell interactions and tissue organization critically influence cancer progression and therapeutic responses, yet remain elusive in standard single-cell suspension analyses. Clinically viable multiplexed imaging combined with single-cell sequencing will likely unlock novel biomarkers and therapeutic targets embedded within the spatial tumor ecosystem.

The rise of machine learning and artificial intelligence applied to large-scale single-cell datasets is another impetus toward scalable clinical translation. These computational advances facilitate pattern recognition, cell identity classification, and predictive modeling that can accelerate the discovery of robust diagnostic and prognostic signatures. Automated workflows capable of integrating multi-omic single-cell data promise to redefine clinical decision-making by delivering actionable insights with increasing precision and speed.

It is becoming increasingly evident that future clinical oncology will rely heavily on multi-dimensional data incorporating single-cell transcriptomic profiles alongside genomic, proteomic, and clinical parameters. Digital pathology integrated with single-cell omics could enable routine molecular phenotyping, uncovering subclonal populations and microenvironmental features driving malignancy in real time. Such comprehensive molecular portraits hold the key to truly personalized cancer care, where treatments are dynamically tailored to individual tumour ecosystems.

In parallel, ongoing clinical trials are beginning to incorporate single-cell sequencing technologies to monitor tumour evolution, immune responses, and minimal residual disease. These studies will provide crucial evidence regarding the utility of scRNA-seq as a biomarker tool and guide its standardized incorporation into clinical workflows. Importantly, ethical and logistical considerations surrounding patient consent, data privacy, and equitable access will need to be thoroughly addressed as single-cell technologies transition into clinical settings.

In conclusion, the clinical applications of single-cell RNA sequencing in oncology stand poised at the cusp of revolutionizing cancer diagnostics and therapeutics. The technology’s unparalleled resolution reveals the vibrant and complex cellular tapestry of tumours, opening new paths for precision medicine tailored to the unique biology of each patient’s cancer. While technical hurdles remain, rapid advancements in experimental and computational techniques, along with growing clinical adoption, promise to transform scRNA-seq from a primarily investigational tool into a cornerstone of modern oncology practice. The decade ahead is likely to witness single-cell transcriptomics driving unprecedented improvements in cancer patient outcomes, making what was once the province of basic science a pivotal asset in the clinic.

Subject of Research: Clinical applications of single-cell RNA sequencing in patient-derived tumour samples

Article Title: Emerging clinical applications of single-cell RNA sequencing in oncology

Article References: Boxer, E., Feigin, N., Tschernichovsky, R. et al. Emerging clinical applications of single-cell RNA sequencing in oncology. Nat Rev Clin Oncol 22, 315–326 (2025). https://doi.org/10.1038/s41571-025-01003-3

Image Credits: AI Generated

DOI: https://doi.org/10.1038/s41571-025-01003-3

Keywords: single-cell RNA sequencing, oncology, tumour heterogeneity, tumour microenvironment, therapy resistance, precision medicine, immuno-oncology, spatial transcriptomics