Explore the vast range of titles available.

Given that cancer mortality is usually a result of late diagnosis, efforts in the field of early detection are paramount to reducing cancer-related deaths and improving patient outcomes. Increasing evidence indicates that metastasis is an early event in patients with aggressive cancers, often occurring even before primary lesions are clinically detectable. Metastases are usually formed from cancer cells that spread to distant non-malignant tissues via the blood circulation, termed circulating tumour cells (CTCs). CTCs have been detected in patients with early stage cancers and, owing to their association with metastasis, might indicate the presence of aggressive disease, thus providing a possible means to expedite diagnosis and treatment initiation for such patients while avoiding overdiagnosis and overtreatment of those with slow-growing, indolent tumours. The utility of CTCs as an early diagnostic tool has been investigated, although further improvements in the efficiency of CTC detection are required. In this Perspective, we discuss the clinical significance of early haematogenous dissemination of cancer cells, the potential of CTCs to facilitate early detection of clinically relevant cancers, and the technological advances that might improve CTC capture and, thus, diagnostic performance in this setting.The authors of this Perspective propose that, with further improvement in detection efficiency, circulating tumour cells (CTCs), which are released early during cancer development, have the potential to be used for the early detection of clinically relevant, aggressive cancers. Thus, use of CTCs as diagnostic biomarkers might improve outcomes by enabling the identification of cancers at a stage at which they are more amenable to treatment while avoiding overtreatment of patients with indolent tumours.

The number of publications on deep learning for cancer diagnostics is rapidly increasing, and systems are frequently claimed to perform comparable with or better than clinicians. However, few systems have yet demonstrated real-world medical utility. In this Perspective, we discuss reasons for the moderate progress and describe remedies designed to facilitate transition to the clinic. Recent, presumably influential, deep learning studies in cancer diagnostics, of which the vast majority used images as input to the system, are evaluated to reveal the status of the field. By manipulating real data, we then exemplify that much and varied training data facilitate the generalizability of neural networks and thus the ability to use them clinically. To reduce the risk of biased performance estimation of deep learning systems, we advocate evaluation in external cohorts and strongly advise that the planned analyses, including a predefined primary analysis, are described in a protocol preferentially stored in an online repository. Recommended protocol items should be established for the field, and we present our suggestions.The number of publications on deep learning for cancer diagnostics is rapidly increasing, but clinical translation is slow. This Perspective advocates performance estimation in external cohorts and strongly advises that a primary analysis is predefined in a standardized protocol preferentially stored in an online repository.

Somatic mutations in cancer cells can generate tumour-specific neoepitopes, which are recognized by autologous T cells in the host. As neoepitopes are not subject to central immune tolerance and are not expressed in healthy tissues, they are attractive targets for therapeutic cancer vaccines. Because the vast majority of cancer mutations are unique to the individual patient, harnessing the full potential of this rich source of targets requires individualized treatment approaches. Many computational algorithms and machine-learning tools have been developed to identify mutations in sequence data, to prioritize those that are more likely to be recognized by T cells and to design tailored vaccines for every patient. In this Review, we fill the gaps between the understanding of basic mechanisms of T cell recognition of neoantigens and the computational approaches for discovery of somatic mutations and neoantigen prediction for cancer immunotherapy. We present a new classification of neoantigens, distinguishing between guarding, restrained and ignored neoantigens, based on how they confer proficient antitumour immunity in a given clinical context. Such context-based differentiation will contribute to a framework that connects neoantigen biology to the clinical setting and medical peculiarities of cancer, and will enable future neoantigen-based therapies to provide greater clinical benefit.Mutations in cancer cells can generate tumour-specific neoepitopes, which are attractive targets for anticancer vaccines. This Review discusses the mechanisms of neoantigen T cell recognition and computational approaches to predict which neoantigens might confer proficient antitumour immunity in a given clinical context.

Molecular imaging has experienced enormous advancements in the areas of imaging technology, imaging probe and contrast development, and data quality, as well as machine learning-based data analysis. Positron emission tomography (PET) and its combination with computed tomography (CT) or magnetic resonance imaging (MRI) as a multimodality PET–CT or PET–MRI system offer a wealth of molecular, functional and morphological data with a single patient scan. Despite the recent technical advances and the availability of dozens of disease-specific contrast and imaging probes, only a few parameters, such as tumour size or the mean tracer uptake, are used for the evaluation of images in clinical practice. Multiparametric in vivo imaging data not only are highly quantitative but also can provide invaluable information about pathophysiology, receptor expression, metabolism, or morphological and functional features of tumours, such as pH, oxygenation or tissue density, as well as pharmacodynamic properties of drugs, to measure drug response with a contrast agent. It can further quantitatively map and spatially resolve the intertumoural and intratumoural heterogeneity, providing insights into tumour vulnerabilities for target-specific therapeutic interventions. Failure to exploit and integrate the full potential of such powerful imaging data may lead to a lost opportunity in which patients do not receive the best possible care. With the desire to implement personalized medicine in the cancer clinic, the full comprehensive diagnostic power of multiplexed imaging should be utilized.In this Review, Schwenck et al. discuss how PET imaging of cancer has advanced through its combination with CT and MRI and the development of an array of imaging probes, and how these innovations now need to be fully integrated into the clinic to improve cancer diagnostics and guide therapy.

In recent years, exceptional technological advances have enabled the identification and interrogation of rare circulating tumour cells (CTCs) from blood samples of patients, leading to new fields of research and fostering the promise for paradigm-changing, liquid biopsy-based clinical applications. Analysis of CTCs has revealed distinct biological phenotypes, including the presence of CTC clusters and the interaction between CTCs and immune or stromal cells, impacting metastasis formation and providing new insights into cancer vulnerabilities. Here we review the progress made in understanding biological features of CTCs and provide insight into exploiting these developments to design future clinical tools for improving the diagnosis and treatment of cancer.As well-established players in the metastatic cascade, circulating tumour cells (CTCs) hold promise for improved cancer diagnosis and disease monitoring. In this Review, Ring et al. overview the current understanding of CTC biology, highlighting specific opportunities and vulnerabilities for future CTC-focused therapies.

Colorectal cancer (CRC) is among the most common malignancies with limited treatments other than surgery. The tumor microenvironment (TME) profiling enables the discovery of potential therapeutic targets. Here, we profile 54,103 cells from tumor and adjacent tissues to characterize cellular composition and elucidate the potential origin and regulation of tumor-enriched cell types in CRC. We demonstrate that the tumor-specific FAP + fibroblasts and SPP1 + macrophages were positively correlated in 14 independent CRC cohorts containing 2550 samples and validate their close localization by immuno-fluorescent staining and spatial transcriptomics. This interaction might be regulated by chemerin, TGF-β, and interleukin-1, which would stimulate the formation of immune-excluded desmoplasic structure and limit the T cell infiltration. Furthermore, we find patients with high FAP or SPP1 expression achieved less therapeutic benefit from an anti-PD-L1 therapy cohort. Our results provide a potential therapeutic strategy by disrupting FAP + fibroblasts and SPP1 + macrophages interaction to improve immunotherapy. Tumour microenvironment profiling during colorectal cancer progression may enable the discovery of therapeutic targets. Here, single cell and spatial RNA sequencing of tumour and adjacent normal tissues reveals an interaction between FAP + fibroblasts and SPP1 + macrophages that could be disrupted as an immunotherapy strategy.

The stromal compartment of the tumor microenvironment consists of a heterogeneous set of tissue-resident and tumor-infiltrating cells, which are profoundly moulded by cancer cells. An outstanding question is to what extent this heterogeneity is similar between cancers affecting different organs. Here, we profile 233,591 single cells from patients with lung, colorectal, ovary and breast cancer ( n  = 36) and construct a pan-cancer blueprint of stromal cell heterogeneity using different single-cell RNA and protein-based technologies. We identify 68 stromal cell populations, of which 46 are shared between cancer types and 22 are unique. We also characterise each population phenotypically by highlighting its marker genes, transcription factors, metabolic activities and tissue-specific expression differences. Resident cell types are characterised by substantial tissue specificity, while tumor-infiltrating cell types are largely shared across cancer types. Finally, by applying the blueprint to melanoma tumors treated with checkpoint immunotherapy and identifying a naïve CD4 + T-cell phenotype predictive of response to checkpoint immunotherapy, we illustrate how it can serve as a guide to interpret scRNA-seq data. In conclusion, by providing a comprehensive blueprint through an interactive web server, we generate the first panoramic view on the shared complexity of stromal cells in different cancers.

Gastric cancer (GC) represents a significant burden of cancer-related mortality worldwide, underscoring an urgent need for the development of early detection strategies and precise postoperative interventions. However, the identification of non-invasive biomarkers for early diagnosis and patient risk stratification remains underexplored. Here, we conduct a targeted metabolomics analysis of 702 plasma samples from multi-center participants to elucidate the GC metabolic reprogramming. Our machine learning analysis reveals a 10-metabolite GC diagnostic model, which is validated in an external test set with a sensitivity of 0.905, outperforming conventional methods leveraging cancer protein markers (sensitivity < 0.40). Additionally, our machine learning-derived prognostic model demonstrates superior performance to traditional models utilizing clinical parameters and effectively stratifies patients into different risk groups to guide precision interventions. Collectively, our findings reveal the metabolic landscape of GC and identify two distinct biomarker panels that enable early detection and prognosis prediction respectively, thus facilitating precision medicine in GC. Gastric cancer detection by endoscopy is intrusive and time-consuming, and early detection is key to improving survival. Here, the authors propose a metabolite-based model to enable early detection.

Although more than a decade has passed since the approval of immune checkpoint inhibitors (ICIs) for the treatment of melanoma and non-small-cell lung, breast and gastrointestinal cancers, many patients still show limited response. US Food and Drug Administration (FDA)-approved biomarkers include programmed cell death 1 ligand 1 (PDL1) expression, microsatellite status (that is, microsatellite instability-high (MSI-H)) and tumour mutational burden (TMB), but these have limited utility and/or lack standardized testing approaches for pan-cancer applications. Tissue-based analytes (such as tumour gene signatures, tumour antigen presentation or tumour microenvironment profiles) show a correlation with immune response, but equally, these demonstrate limited efficacy, as they represent a single time point and a single spatial assessment. Patient heterogeneity as well as inter- and intra-tumoural differences across different tissue sites and time points represent substantial challenges for static biomarkers. However, dynamic biomarkers such as longitudinal biopsies or novel, less-invasive markers such as blood-based biomarkers, radiomics and the gut microbiome show increasing potential for the dynamic identification of ICI response, and patient-tailored predictors identified through neoadjuvant trials or novel ex vivo tumour models can help to personalize treatment. In this Perspective, we critically assess the multiple new static, dynamic and patient-specific biomarkers, highlight the newest consortia and trial efforts, and provide recommendations for future clinical trials to make meaningful steps forwards in the field. In this Perspective, Holder et al. discuss the limitations of current predictive biomarkers of response to immune checkpoint inhibitors and the need to further explore static, dynamic and patient-specific biomarkers using novel tools, such as machine learning and consortia-level initiatives.

Artificial intelligence (AI) has been commoditized. It has evolved from a specialty resource to a readily accessible tool for cancer researchers. AI-based tools can boost research productivity in daily workflows, but can also extract hidden information from existing data, thereby enabling new scientific discoveries. Building a basic literacy in these tools is useful for every cancer researcher. Researchers with a traditional biological science focus can use AI-based tools through off-the-shelf software, whereas those who are more computationally inclined can develop their own AI-based software pipelines. In this article, we provide a practical guide for non-computational cancer researchers to understand how AI-based tools can benefit them. We convey general principles of AI for applications in image analysis, natural language processing and drug discovery. In addition, we give examples of how non-computational researchers can get started on the journey to productively use AI in their own work. This Review provides an introductory guide to artificial intelligence (AI)-based tools for non-computational cancer researchers. Here, Perez-Lopez et al. outline the general principles of AI for image analysis, natural language processing and drug discovery, as well as how researchers can get started with each of them.