{"title":"基于生物背景的机器学习有助于识别肝内胆管癌的微血管侵犯。","authors":"Shuaishuai Xu, Mingyu Wan, Chanqi Ye, Ruyin Chen, Qiong Li, Xiaochen Zhang, Jian Ruan","doi":"10.1093/carcin/bgae052","DOIUrl":null,"url":null,"abstract":"<p><p>Intrahepatic cholangiocarcinoma is a rare disease associated with a poor prognosis, primarily due to early recurrence and metastasis. An important feature of this condition is microvascular invasion (MVI). However, current predictive models based on imaging have limited efficacy in this regard. This study employed a random forest model to construct a predictive model for MVI identification and uncover its biological basis. Single-cell transcriptome sequencing, whole exome sequencing, and proteome sequencing were performed. The area under the curve of the prediction model in the validation set was 0.93. Further analysis indicated that MVI-associated tumor cells exhibited functional changes related to epithelial-mesenchymal transition and lipid metabolism due to alterations in the nuclear factor-kappa B and mitogen-activated protein kinase signaling pathways. Tumor cells were also differentially enriched for the interleukin-17 signaling pathway. There was less infiltration of SLC30A1+ CD8+ T cells expressing cytotoxic genes in MVI-associated intrahepatic cholangiocarcinoma, whereas there was more infiltration of myeloid cells with attenuated expression of the major histocompatibility complex II pathway. Additionally, MVI-associated intercellular communication was closely related to the SPP1-CD44 and ANXA1-FPR1 pathways. These findings resulted in a brilliant predictive model and fresh insights into MVI.</p>","PeriodicalId":9446,"journal":{"name":"Carcinogenesis","volume":" ","pages":"721-734"},"PeriodicalIF":3.3000,"publicationDate":"2024-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Machine learning based on biological context facilitates the identification of microvascular invasion in intrahepatic cholangiocarcinoma.\",\"authors\":\"Shuaishuai Xu, Mingyu Wan, Chanqi Ye, Ruyin Chen, Qiong Li, Xiaochen Zhang, Jian Ruan\",\"doi\":\"10.1093/carcin/bgae052\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Intrahepatic cholangiocarcinoma is a rare disease associated with a poor prognosis, primarily due to early recurrence and metastasis. An important feature of this condition is microvascular invasion (MVI). However, current predictive models based on imaging have limited efficacy in this regard. This study employed a random forest model to construct a predictive model for MVI identification and uncover its biological basis. Single-cell transcriptome sequencing, whole exome sequencing, and proteome sequencing were performed. The area under the curve of the prediction model in the validation set was 0.93. Further analysis indicated that MVI-associated tumor cells exhibited functional changes related to epithelial-mesenchymal transition and lipid metabolism due to alterations in the nuclear factor-kappa B and mitogen-activated protein kinase signaling pathways. Tumor cells were also differentially enriched for the interleukin-17 signaling pathway. There was less infiltration of SLC30A1+ CD8+ T cells expressing cytotoxic genes in MVI-associated intrahepatic cholangiocarcinoma, whereas there was more infiltration of myeloid cells with attenuated expression of the major histocompatibility complex II pathway. Additionally, MVI-associated intercellular communication was closely related to the SPP1-CD44 and ANXA1-FPR1 pathways. These findings resulted in a brilliant predictive model and fresh insights into MVI.</p>\",\"PeriodicalId\":9446,\"journal\":{\"name\":\"Carcinogenesis\",\"volume\":\" \",\"pages\":\"721-734\"},\"PeriodicalIF\":3.3000,\"publicationDate\":\"2024-10-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Carcinogenesis\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1093/carcin/bgae052\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Carcinogenesis","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/carcin/bgae052","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
摘要
肝内胆管癌(ICC)是一种罕见的疾病,预后较差,主要原因是早期复发和转移。这种疾病的一个重要特征是微血管侵犯(MVI)。然而,目前基于成像的预测模型在这方面的效果有限。本研究采用随机森林模型构建了一个用于识别MVI的预测模型,并揭示了其生物学基础。研究人员进行了单细胞转录组测序、全外显子组测序和蛋白质组测序。在验证集中,预测模型的曲线下面积为 0.93。进一步分析表明,由于 NF-kappa B 和 MAPK 信号通路的改变,MVI 相关肿瘤细胞表现出与上皮-间质转化和脂质代谢相关的功能变化。肿瘤细胞在 IL-17 信号通路上也有不同程度的富集。在 MVI 相关 ICC 中,表达细胞毒性基因的 SLC30A1+ CD8+ T 细胞浸润较少,而骨髓细胞浸润较多,MHC II 通路表达减弱。此外,MVI相关的细胞间通讯与SPP1-CD44和ANXA1-FPR1通路密切相关。这些发现建立了一个出色的预测模型,并使人们对 MVI 有了新的认识。
Machine learning based on biological context facilitates the identification of microvascular invasion in intrahepatic cholangiocarcinoma.
Intrahepatic cholangiocarcinoma is a rare disease associated with a poor prognosis, primarily due to early recurrence and metastasis. An important feature of this condition is microvascular invasion (MVI). However, current predictive models based on imaging have limited efficacy in this regard. This study employed a random forest model to construct a predictive model for MVI identification and uncover its biological basis. Single-cell transcriptome sequencing, whole exome sequencing, and proteome sequencing were performed. The area under the curve of the prediction model in the validation set was 0.93. Further analysis indicated that MVI-associated tumor cells exhibited functional changes related to epithelial-mesenchymal transition and lipid metabolism due to alterations in the nuclear factor-kappa B and mitogen-activated protein kinase signaling pathways. Tumor cells were also differentially enriched for the interleukin-17 signaling pathway. There was less infiltration of SLC30A1+ CD8+ T cells expressing cytotoxic genes in MVI-associated intrahepatic cholangiocarcinoma, whereas there was more infiltration of myeloid cells with attenuated expression of the major histocompatibility complex II pathway. Additionally, MVI-associated intercellular communication was closely related to the SPP1-CD44 and ANXA1-FPR1 pathways. These findings resulted in a brilliant predictive model and fresh insights into MVI.
期刊介绍:
Carcinogenesis: Integrative Cancer Research is a multi-disciplinary journal that brings together all the varied aspects of research that will ultimately lead to the prevention of cancer in man. The journal publishes papers that warrant prompt publication in the areas of Biology, Genetics and Epigenetics (including the processes of promotion, progression, signal transduction, apoptosis, genomic instability, growth factors, cell and molecular biology, mutation, DNA repair, genetics, etc.), Cancer Biomarkers and Molecular Epidemiology (including genetic predisposition to cancer, and epidemiology), Inflammation, Microenvironment and Prevention (including molecular dosimetry, chemoprevention, nutrition and cancer, etc.), and Carcinogenesis (including oncogenes and tumor suppressor genes in carcinogenesis, therapy resistance of solid tumors, cancer mouse models, apoptosis and senescence, novel therapeutic targets and cancer drugs).