• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

PathMethy：一种基于 DNA 甲基化的癌症起源追踪可解释 AI 框架。

PathMethy: an interpretable AI framework for cancer origin tracing based on DNA methylation.

机构信息

National Institute for Data Science in Health and Medicine, Xiamen University, No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361102, China.

School of Informatics, Xiamen University, No. 4221-121 South Xiang'an Road, Xiamen, Fujian 361005, China.

出版信息

Brief Bioinform. 2024 Sep 23;25(6). doi: 10.1093/bib/bbae497.

DOI:10.1093/bib/bbae497
PMID:39391931
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11467402/
Abstract

Despite advanced diagnostics, 3%-5% of cases remain classified as cancer of unknown primary (CUP). DNA methylation, an important epigenetic feature, is essential for determining the origin of metastatic tumors. We presented PathMethy, a novel Transformer model integrated with functional categories and crosstalk of pathways, to accurately trace the origin of tumors in CUP samples based on DNA methylation. PathMethy outperformed seven competing methods in F1-score across nine cancer datasets and predicted accurately the molecular subtypes within nine primary tumor types. It not only excelled at tracing the origins of both primary and metastatic tumors but also demonstrated a high degree of agreement with previously diagnosed sites in cases of CUP. PathMethy provided biological insights by highlighting key pathways, functional categories, and their interactions. Using functional categories of pathways, we gained a global understanding of biological processes. For broader access, a user-friendly web server for researchers and clinicians is available at https://cup.pathmethy.com.

摘要

尽管有先进的诊断技术，仍有 3%-5%的病例被归类为不明原发癌（CUP）。DNA 甲基化是一种重要的表观遗传特征，对于确定转移瘤的起源至关重要。我们提出了 PathMethy，这是一种新型的 Transformer 模型，集成了功能类别和途径的串扰，可根据 DNA 甲基化准确追踪 CUP 样本中肿瘤的起源。PathMethy 在九个癌症数据集的 F1 分数上优于七种竞争方法，并准确预测了九个原发性肿瘤类型中的分子亚型。它不仅擅长追踪原发性和转移性肿瘤的起源，而且在 CUP 病例中与先前诊断的部位高度一致。PathMethy 通过突出关键途径、功能类别及其相互作用提供了生物学见解。使用途径的功能类别，我们全面了解了生物学过程。为了更广泛的访问，我们为研究人员和临床医生提供了一个用户友好的网络服务器，网址是 https://cup.pathmethy.com。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/4fdfc9a3c189/bbae497f7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/6afaa2459426/bbae497f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/8c4c7f2294b4/bbae497f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/df98e04f88af/bbae497f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/a85f89aca9eb/bbae497f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/30886de38632/bbae497f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/8581de5fe664/bbae497f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/4fdfc9a3c189/bbae497f7.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/6afaa2459426/bbae497f1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/8c4c7f2294b4/bbae497f2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/df98e04f88af/bbae497f3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/a85f89aca9eb/bbae497f4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/30886de38632/bbae497f5.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/8581de5fe664/bbae497f6.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/bf93/11467402/4fdfc9a3c189/bbae497f7.jpg

相似文献

1
PathMethy: an interpretable AI framework for cancer origin tracing based on DNA methylation.PathMethy：一种基于 DNA 甲基化的癌症起源追踪可解释 AI 框架。
Brief Bioinform. 2024 Sep 23;25(6). doi: 10.1093/bib/bbae497.
2
CUP-AI-Dx: A tool for inferring cancer tissue of origin and molecular subtype using RNA gene-expression data and artificial intelligence.CUP-AI-Dx：一种使用 RNA 基因表达数据和人工智能推断癌症组织来源和分子亚型的工具。
EBioMedicine. 2020 Nov;61:103030. doi: 10.1016/j.ebiom.2020.103030. Epub 2020 Oct 9.
3
Image-based deep learning model using DNA methylation data predicts the origin of cancer of unknown primary.基于图像的深度学习模型使用 DNA 甲基化数据预测未知原发性癌症的起源。
Neoplasia. 2024 Sep;55:101021. doi: 10.1016/j.neo.2024.101021. Epub 2024 Jun 28.
4
Tracing unknown tumor origins with a biological-pathway-based transformer model.基于生物途径的变换模型追踪未知肿瘤起源。
Cell Rep Methods. 2024 Jun 17;4(6):100797. doi: 10.1016/j.crmeth.2024.100797.
5
Evaluating DNA Methylation, Gene Expression, Somatic Mutation, and Their Combinations in Inferring Tumor Tissue-of-Origin.评估DNA甲基化、基因表达、体细胞突变及其组合在推断肿瘤组织起源中的作用。
Front Cell Dev Biol. 2021 May 3;9:619330. doi: 10.3389/fcell.2021.619330. eCollection 2021.
6
erarchical tumor artificial intelligence classifier traces tissue of origin and tumor type in primary and metastasized tumors using DNA methylation.分层肿瘤人工智能分类器利用DNA甲基化追踪原发性和转移性肿瘤的组织起源和肿瘤类型。
NAR Cancer. 2023 Apr 19;5(2):zcad017. doi: 10.1093/narcan/zcad017. eCollection 2023 Jun.
7
A molecular approach integrating genomic and DNA methylation profiling for tissue of origin identification in lung-specific cancer of unknown primary.一种分子方法，将基因组和 DNA 甲基化分析整合起来，用于鉴定不明原发部位肺特异性癌的组织来源。
J Transl Med. 2022 Apr 5;20(1):158. doi: 10.1186/s12967-022-03362-2.
8
A Linear Regression and Deep Learning Approach for Detecting Reliable Genetic Alterations in Cancer Using DNA Methylation and Gene Expression Data.基于 DNA 甲基化和基因表达数据的线性回归和深度学习方法在癌症中检测可靠的遗传改变。
Genes (Basel). 2020 Aug 12;11(8):931. doi: 10.3390/genes11080931.
9
Epigenetic Profiling of CUP.CUP 的表观遗传学分析。
Cancer Discov. 2016 Nov;6(11):1203. doi: 10.1158/2159-8290.CD-NB2016-118. Epub 2016 Sep 22.
10
The practical utility of AI-assisted molecular profiling in the diagnosis and management of cancer of unknown primary: an updated review.人工智能辅助分子谱分析在不明原发癌的诊断和治疗中的实际应用：最新综述。
Virchows Arch. 2024 Feb;484(2):369-375. doi: 10.1007/s00428-023-03708-1. Epub 2023 Nov 24.

本文引用的文献

1
Tracing unknown tumor origins with a biological-pathway-based transformer model.基于生物途径的变换模型追踪未知肿瘤起源。
Cell Rep Methods. 2024 Jun 17;4(6):100797. doi: 10.1016/j.crmeth.2024.100797.
2
Pathformer: a biological pathway informed transformer for disease diagnosis and prognosis using multi-omics data.Pathformer：一种基于生物通路的Transformer，用于使用多组学数据进行疾病诊断和预后。
Bioinformatics. 2024 May 2;40(5). doi: 10.1093/bioinformatics/btae316.
3
DNA methylation profiling to determine the primary sites of metastatic cancers using formalin-fixed paraffin-embedded tissues.
利用福尔马林固定石蜡包埋组织进行 DNA 甲基化分析，以确定转移性癌症的原发部位。
Nat Commun. 2023 Sep 14;14(1):5686. doi: 10.1038/s41467-023-41015-0.
4
Mitochondrial cytochrome P450 1B1 is involved in pregnenolone synthesis in human brain cells.线粒体细胞色素 P450 1B1 参与人脑细胞中孕烯醇酮的合成。
J Biol Chem. 2023 Aug;299(8):105035. doi: 10.1016/j.jbc.2023.105035. Epub 2023 Jul 11.
5
erarchical tumor artificial intelligence classifier traces tissue of origin and tumor type in primary and metastasized tumors using DNA methylation.分层肿瘤人工智能分类器利用DNA甲基化追踪原发性和转移性肿瘤的组织起源和肿瘤类型。
NAR Cancer. 2023 Apr 19;5(2):zcad017. doi: 10.1093/narcan/zcad017. eCollection 2023 Jun.
6
Accurate prediction of pan-cancer types using machine learning with minimal number of DNA methylation sites.使用机器学习和最少数量的 DNA 甲基化位点进行泛癌症类型的准确预测。
J Mol Cell Biol. 2023 Aug 3;15(4). doi: 10.1093/jmcb/mjad023.
7
Transformer for one stop interpretable cell type annotation.用于一站式可解释细胞类型注释的 Transformer。
Nat Commun. 2023 Jan 14;14(1):223. doi: 10.1038/s41467-023-35923-4.
8
DRPreter: Interpretable Anticancer Drug Response Prediction Using Knowledge-Guided Graph Neural Networks and Transformer.DRPreter：基于知识引导图神经网络和转换器的可解释抗癌药物反应预测
Int J Mol Sci. 2022 Nov 11;23(22):13919. doi: 10.3390/ijms232213919.
9
Molecular substructure tree generative model for de novo drug design.用于从头药物设计的分子子结构树生成模型。
Brief Bioinform. 2022 Mar 10;23(2). doi: 10.1093/bib/bbab592.
10
Computational challenges in detection of cancer using cell-free DNA methylation.使用游离DNA甲基化检测癌症中的计算挑战。
Comput Struct Biotechnol J. 2021 Dec 7;20:26-39. doi: 10.1016/j.csbj.2021.12.001. eCollection 2022.