Single-cell omics has emerged as a powerful tool for elucidating cellular heterogeneity in health and disease. Parallel advances in artificial intelligence (AI), particularly in pattern recognition, feature extraction and predictive modelling, now offer unprecedented opportunities to translate these insights into clinical applications. Here, we propose single-cell -omics-based Disease Predictor through AI (scDisPreAI), a unified framework that leverages AI to integrate single-cell -omics data, enabling robust disease and disease-stage prediction, alongside biomarker discovery. The foundation of scDisPreAI lies in assembling a large, standardised database spanning diverse diseases and multiple disease stages. Rigorous data preprocessing, including normalisation and batch effect correction, ensures that biological rather than technical variation drives downstream models. Machine learning pipelines or deep learning architectures can then be trained in a multi-task fashion, classifying both disease identity and disease stage. Crucially, interpretability techniques such as SHapley Additive exPlanations (SHAP) values or attention weights pinpoint the genes most influential for these predictions, highlighting biomarkers that may be shared across diseases or disease stages. By consolidating predictive modelling with interpretable biomarker identification, scDisPreAI may be deployed as a clinical decision assistant, flagging potential therapeutic targets for drug repurposing and guiding tailored treatments. In this editorial, we propose the technical and methodological roadmap for scDisPreAI and emphasises future directions, including the incorporation of multi-omics, standardised protocols and prospective clinical validation, to fully harness the transformative potential of single-cell AI in precision medicine.
Zijuan Wu. Clin Transl Med. 2024;14(8):e1807.
Following the publication of the original article,1 the authors identified minor errors in Figure 1C, where the images of one group was incorrect. Because during the image acquisition, we mistakenly labelled two duplicate results from a single sample. We have made the necessary corrections to Figure 1C. More importantly, we promise that the erratum has no impact on the conclusion and description of the article.
We apologize for this error.
Metastatic solid tumours remain a major challenge in clinical medicine, demanding innovation with novel treatment approaches and new synergistic combinations. Immunotherapy with immune checkpoint inhibitors (ICIs) targeting PD-1 and PD-L1 has improved the treatment outcome for numerous tumour types in a groundbreaking way. However, resistance to immunotherapy is very frequent and ultimately impacts the vast majority of patients treated, often resulting in fatal outcome. Similarly, in advanced cancer patients cachexia is a frequent event. This is a serious debilitating syndrome characterized by severe muscle wasting, weight loss and systemic metabolic dysfunction which associates with a dismal prognosis. Cachexia further worsens clinical outcome in cancer patients and can prevent ability to continue on therapy. In this context, our recent study published in Nature, titled “Neutralizing GDF-15 can overcome anti-PD-1 and anti-PD-L1 resistance in solid tumours,” demonstrates the multifaceted roles growth differentiation factor 15 (GDF-15) plays and provides initial data on a promising novel therapeutic strategy to counteract immunotherapy resistance and cachexia.1 Here, we discuss the potential benefits of GDF-15 blockade as an emerging approach to both potentiate cancer immunotherapy and simultaneously mitigate cancer cachexia, highlighting recent advancements and their potential future clinical implications (Figure 1).
I. Melero, K. Klar and E. Leo prepared jointly the manuscript.
I. Melero is principal investigator of the trial 1 and has served as a consultant to Catalym GmbH. K. Klar and E. Leo are employees of Catalym GmbH, Martinsried, Germany, a biotechnology company developing the anti-GDF15 antibody visugromab.
The authors declare human ethics approval does not apply for this manuscript.
Recent advancements in immunometabolism have highlighted the critical role of metabolite sensors in regulating immune responses. Metabolites such as lactate, succinate, itaconate, and β-hydroxybutyrate influence immune cell function by interacting with specific sensors. These metabolites act as signaling molecules, linking cellular metabolic changes to immune responses. Lactate, a metabolite commonly produced under hypoxic conditions, has emerged as a major regulator of innate immunity. Key enzymes, including AARS1 and AARS2, function as intracellular lactate sensors, catalyzing lactylation on proteins like cGAS, which plays a central role in DNA sensing and immune activation. The lactylation of cGAS inhibits its activity, modulating immune responses by balancing inflammation and immune tolerance. Metabolite sensors, like MCT1, also contribute to immune modulation, particularly in cancer and chronic inflammatory diseases. Therapeutically, targeting these sensors offers potential for restoring immune function, especially in cancer immunotherapy. However, challenges in specificity, off-target effects, and long-term safety require further investigation. This article explores the emerging role of metabolite sensors in immune regulation, with a focus on lactate sensors, and outlines potential therapeutic strategies to enhance immune responses in metabolic diseases.
Oesophageal squamous cell carcinoma (OSCC) represents a highly aggressive malignancy with limited therapeutic options and poor prognosis. This study uncovers PCIF1 as a critical driver of OSCC progression via m6Am RNA modification, leading to translational repression of the tumour suppressor MTF2. Our results demonstrate that PCIF1 selectively suppresses MTF2 translation, activating oncogenic pathways that promote OSCC growth. In vitro and in vivo models confirm that PCIF1 knockdown reduces OSCC progression, whereas MTF2 knockdown counteracts this effect, highlighting the importance of the PCIF1-MTF2 axis. Clinical analyses further reveal that high PCIF1 expression and low MTF2 expression correlate with advanced tumour stage, poor treatment response and decreased overall survival. Furthermore, in a preclinical mouse model, PCIF1 knockout enhanced the efficacy of anti-PD1 immunotherapy, reducing tumour burden and improving histological outcomes. Notably, flow cytometry analysis indicated that PCIF1 primarily exerts its effects through tumour-intrinsic mechanisms rather than direct modulation of the immune microenvironment, distinguishing its mode of action from PD1 blockade. These findings establish PCIF1 and MTF2 as promising prognostic markers and therapeutic targets for OSCC, offering new avenues for treatment strategies and patient stratification.
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：