Smelik Martin, Diaz-Roncero Gonzalez Daniel, An Xiaojing, Heer Rakesh, Henningsohn Lars, Li Xinxiu, Wang Hui, Zhao Yelin, Benson Mikael
Division of ENT Diseases, Department of Clinical Science, Intervention and Technology (CLINTEC), Karolinska Institute, Stockholm, Sweden.
Department of Pathology, Xiyuan Hospital, China Academy of Chinese Medical Sciences, Beijing, China.
Cancer Res. 2025 Jul 2;85(13):2514-2526. doi: 10.1158/0008-5472.CAN-25-0269.
UNLABELLED: Early cancer diagnosis is crucial but challenging owing to the lack of reliable biomarkers that can be measured using routine clinical methods. The identification of biomarkers for early detection is complicated by each tumor involving changes in the interactions between thousands of genes. In addition to this staggering complexity, these interactions can vary among patients with the same diagnosis as well as within the same tumor. We hypothesized that reliable biomarkers that can be measured with routine methods could be identified by exploiting three facts: (i) the same tumor can have multiple grades of malignant transformation; (ii) these grades and their molecular changes can be characterized using spatial transcriptomics; and (iii) these changes can be integrated into models of malignant transformation using pseudotime. Pseudotime models were constructed based on spatial transcriptomic data from three independent prostate cancer studies to prioritize the genes that were most correlated with malignant transformation. The identified genes were associated with cancer grade, copy-number aberrations, hallmark pathways, and drug targets, and they encoded candidate biomarkers for prostate cancer in mRNA, IHC, and proteomics data from the sera, prostate tissue, and urine of more than 2,000 patients with prostate cancer and controls. Machine learning-based prediction models revealed that the biomarkers in urine had an AUC of 0.92 for prostate cancer and were associated with cancer grade. Overall, this study demonstrates the diagnostic potential of combining spatial transcriptomics, pseudotime, and machine learning for prostate cancer, which should be further tested in prospective studies. SIGNIFICANCE: Integrating spatial transcriptomics, pseudotime, and machine learning analyses is effective for identifying prostate cancer biomarkers that are reliable in different settings and measurable with routine methods, providing potential early diagnosis strategies. This article is part of a special series: Driving Cancer Discoveries with Computational Research, Data Science, and Machine Learning/AI.
未标注：早期癌症诊断至关重要，但由于缺乏可通过常规临床方法测量的可靠生物标志物，这一过程具有挑战性。由于每种肿瘤涉及数千个基因之间相互作用的变化，早期检测生物标志物的识别变得复杂。除了这种惊人的复杂性之外，这些相互作用在相同诊断的患者之间以及同一肿瘤内部都可能有所不同。我们假设，可以通过利用以下三个事实来识别能够用常规方法测量的可靠生物标志物：（i）同一肿瘤可以有多个恶性转化等级；（ii）这些等级及其分子变化可以使用空间转录组学来表征；（iii）这些变化可以使用伪时间整合到恶性转化模型中。基于来自三项独立前列腺癌研究的空间转录组数据构建伪时间模型，以对与恶性转化最相关的基因进行优先级排序。所识别的基因与癌症等级、拷贝数畸变、标志性通路和药物靶点相关，并且它们在来自2000多名前列腺癌患者和对照的血清、前列腺组织和尿液的mRNA、免疫组化和蛋白质组学数据中编码前列腺癌的候选生物标志物。基于机器学习的预测模型显示，尿液中的生物标志物对前列腺癌的曲线下面积（AUC）为0.92，并且与癌症等级相关。总体而言，本研究证明了将空间转录组学、伪时间和机器学习相结合用于前列腺癌的诊断潜力，这应在前瞻性研究中进一步测试。 意义：整合空间转录组学、伪时间和机器学习分析对于识别在不同环境中可靠且可通过常规方法测量的前列腺癌生物标志物是有效的，提供了潜在的早期诊断策略。本文是一个特别系列的一部分：利用计算研究、数据科学和机器学习/人工智能推动癌症发现。
Cochrane Database Syst Rev. 2018-2-6
Cochrane Database Syst Rev. 2022-5-20
Health Technol Assess. 2006-9
Clin Orthop Relat Res. 2024-9-1
Health Technol Assess. 2001
Cochrane Database Syst Rev. 2008-7-16
Nat Rev Urol. 2025-8-27
Commun Med (Lond). 2024-11-17
Technol Cancer Res Treat. 2024
Nat Commun. 2024-6-13
Zotero 插件
