基于甲基化数量性状位点的未知原发癌深度学习分类器。

IF 3 3区 医学 Q2 CLINICAL NEUROLOGY
Adam Walker, Camila S Fang, Chanel Schroff, Jonathan Serrano, Varshini Vasudevaraja, Yiying Yang, Sarra Belakhoua, Arline Faustin, Christopher M William, David Zagzag, Sarah Chiang, Andres Martin Acosta, Misha Movahed-Ezazi, Kyung Park, Andre L Moreira, Farbod Darvishian, Kristyn Galbraith, Matija Snuderl
{"title":"基于甲基化数量性状位点的未知原发癌深度学习分类器。","authors":"Adam Walker, Camila S Fang, Chanel Schroff, Jonathan Serrano, Varshini Vasudevaraja, Yiying Yang, Sarra Belakhoua, Arline Faustin, Christopher M William, David Zagzag, Sarah Chiang, Andres Martin Acosta, Misha Movahed-Ezazi, Kyung Park, Andre L Moreira, Farbod Darvishian, Kristyn Galbraith, Matija Snuderl","doi":"10.1093/jnen/nlae123","DOIUrl":null,"url":null,"abstract":"<p><p>Cancer of unknown primary (CUP) constitutes between 2% and 5% of human malignancies and is among the most common causes of cancer death in the United States. Brain metastases are often the first clinical presentation of CUP; despite extensive pathological and imaging studies, 20%-45% of CUP are never assigned a primary site. DNA methylation array profiling is a reliable method for tumor classification but tumor-type-specific classifier development requires many reference samples. This is difficult to accomplish for CUP as many cases are never assigned a specific diagnosis. Recent studies identified subsets of methylation quantitative trait loci (mQTLs) unique to specific organs, which could help increase classifier accuracy while requiring fewer samples. We performed a retrospective genome-wide methylation analysis of 759 carcinoma samples from formalin-fixed paraffin-embedded tissue samples using Illumina EPIC array. Utilizing mQTL specific for breast, lung, ovarian/gynecologic, colon, kidney, or testis (BLOCKT) (185k total probes), we developed a deep learning-based methylation classifier that achieved 93.12% average accuracy and 93.04% average F1-score across a 10-fold validation for BLOCKT organs. Our findings indicate that our organ-based DNA methylation classifier can assist pathologists in identifying the site of origin, providing oncologists insight on a diagnosis to administer appropriate therapy, improving patient outcomes.</p>","PeriodicalId":16682,"journal":{"name":"Journal of Neuropathology and Experimental Neurology","volume":" ","pages":"147-154"},"PeriodicalIF":3.0000,"publicationDate":"2025-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11747144/pdf/","citationCount":"0","resultStr":"{\"title\":\"Deep learning-based classifier for carcinoma of unknown primary using methylation quantitative trait loci.\",\"authors\":\"Adam Walker, Camila S Fang, Chanel Schroff, Jonathan Serrano, Varshini Vasudevaraja, Yiying Yang, Sarra Belakhoua, Arline Faustin, Christopher M William, David Zagzag, Sarah Chiang, Andres Martin Acosta, Misha Movahed-Ezazi, Kyung Park, Andre L Moreira, Farbod Darvishian, Kristyn Galbraith, Matija Snuderl\",\"doi\":\"10.1093/jnen/nlae123\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Cancer of unknown primary (CUP) constitutes between 2% and 5% of human malignancies and is among the most common causes of cancer death in the United States. Brain metastases are often the first clinical presentation of CUP; despite extensive pathological and imaging studies, 20%-45% of CUP are never assigned a primary site. DNA methylation array profiling is a reliable method for tumor classification but tumor-type-specific classifier development requires many reference samples. This is difficult to accomplish for CUP as many cases are never assigned a specific diagnosis. Recent studies identified subsets of methylation quantitative trait loci (mQTLs) unique to specific organs, which could help increase classifier accuracy while requiring fewer samples. We performed a retrospective genome-wide methylation analysis of 759 carcinoma samples from formalin-fixed paraffin-embedded tissue samples using Illumina EPIC array. Utilizing mQTL specific for breast, lung, ovarian/gynecologic, colon, kidney, or testis (BLOCKT) (185k total probes), we developed a deep learning-based methylation classifier that achieved 93.12% average accuracy and 93.04% average F1-score across a 10-fold validation for BLOCKT organs. Our findings indicate that our organ-based DNA methylation classifier can assist pathologists in identifying the site of origin, providing oncologists insight on a diagnosis to administer appropriate therapy, improving patient outcomes.</p>\",\"PeriodicalId\":16682,\"journal\":{\"name\":\"Journal of Neuropathology and Experimental Neurology\",\"volume\":\" \",\"pages\":\"147-154\"},\"PeriodicalIF\":3.0000,\"publicationDate\":\"2025-02-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11747144/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Neuropathology and Experimental Neurology\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1093/jnen/nlae123\",\"RegionNum\":3,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CLINICAL NEUROLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Neuropathology and Experimental Neurology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/jnen/nlae123","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CLINICAL NEUROLOGY","Score":null,"Total":0}
引用次数: 0

摘要

原发性未知癌症(CUP)占人类恶性肿瘤的2%至5%,是美国癌症死亡的最常见原因之一。脑转移通常是CUP的第一个临床表现;尽管进行了广泛的病理和影像学研究,但20%-45%的CUP从未确定原发部位。DNA甲基化阵列分析是一种可靠的肿瘤分类方法,但肿瘤类型特异性分类器的开发需要大量参考样本。这对于CUP来说很难做到,因为许多病例从未被指定具体的诊断。最近的研究发现了特定器官特有的甲基化数量性状位点(mqtl)子集,这有助于提高分类器的准确性,同时需要更少的样本。我们使用Illumina EPIC阵列对759例福尔马林固定石蜡包埋组织样本进行了回顾性全基因组甲基化分析。利用针对乳腺、肺、卵巢/妇科、结肠、肾脏或睾丸(BLOCKT)的mQTL特异性(总共185k探针),我们开发了一个基于深度学习的甲基化分类器,在BLOCKT器官的10倍验证中,平均准确率达到93.12%,平均得分为93.04%。我们的研究结果表明,我们基于器官的DNA甲基化分类器可以帮助病理学家识别起源部位,为肿瘤学家提供诊断的洞察力,以实施适当的治疗,改善患者的预后。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Deep learning-based classifier for carcinoma of unknown primary using methylation quantitative trait loci.

Cancer of unknown primary (CUP) constitutes between 2% and 5% of human malignancies and is among the most common causes of cancer death in the United States. Brain metastases are often the first clinical presentation of CUP; despite extensive pathological and imaging studies, 20%-45% of CUP are never assigned a primary site. DNA methylation array profiling is a reliable method for tumor classification but tumor-type-specific classifier development requires many reference samples. This is difficult to accomplish for CUP as many cases are never assigned a specific diagnosis. Recent studies identified subsets of methylation quantitative trait loci (mQTLs) unique to specific organs, which could help increase classifier accuracy while requiring fewer samples. We performed a retrospective genome-wide methylation analysis of 759 carcinoma samples from formalin-fixed paraffin-embedded tissue samples using Illumina EPIC array. Utilizing mQTL specific for breast, lung, ovarian/gynecologic, colon, kidney, or testis (BLOCKT) (185k total probes), we developed a deep learning-based methylation classifier that achieved 93.12% average accuracy and 93.04% average F1-score across a 10-fold validation for BLOCKT organs. Our findings indicate that our organ-based DNA methylation classifier can assist pathologists in identifying the site of origin, providing oncologists insight on a diagnosis to administer appropriate therapy, improving patient outcomes.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
5.40
自引率
6.20%
发文量
118
审稿时长
6-12 weeks
期刊介绍: Journal of Neuropathology & Experimental Neurology is the official journal of the American Association of Neuropathologists, Inc. (AANP). The journal publishes peer-reviewed studies on neuropathology and experimental neuroscience, book reviews, letters, and Association news, covering a broad spectrum of fields in basic neuroscience with an emphasis on human neurological diseases. It is written by and for neuropathologists, neurologists, neurosurgeons, pathologists, psychiatrists, and basic neuroscientists from around the world. Publication has been continuous since 1942.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信