DeePathNet：基于转换器的深度学习模型，将多组学数据与癌症路径整合在一起。

IF 2 Q3 ONCOLOGY

Cancer research communications Pub Date : 2024-12-01 DOI:10.1158/2767-9764.CRC-24-0285

Zhaoxiang Cai, Rebecca C Poulos, Adel Aref, Phillip J Robinson, Roger R Reddel, Qing Zhong

{"title":"DeePathNet：基于转换器的深度学习模型，将多组学数据与癌症路径整合在一起。","authors":"Zhaoxiang Cai, Rebecca C Poulos, Adel Aref, Phillip J Robinson, Roger R Reddel, Qing Zhong","doi":"10.1158/2767-9764.CRC-24-0285","DOIUrl":null,"url":null,"abstract":"Significance: DeePathNet integrates cancer-specific biological pathways using transformer-based deep learning for enhanced cancer analysis. It outperforms existing models in predicting drug responses, cancer types, and subtypes. By enabling pathway-level biomarker discovery, DeePathNet represents a significant advancement in cancer research and could lead to more effective treatments.","PeriodicalId":72516,"journal":{"name":"Cancer research communications","volume":" ","pages":"3151-3164"},"PeriodicalIF":2.0000,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11652962/pdf/","citationCount":"0","resultStr":"{\"title\":\"DeePathNet: A Transformer-Based Deep Learning Model Integrating Multiomic Data with Cancer Pathways.\",\"authors\":\"Zhaoxiang Cai, Rebecca C Poulos, Adel Aref, Phillip J Robinson, Roger R Reddel, Qing Zhong\",\"doi\":\"10.1158/2767-9764.CRC-24-0285\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Significance: DeePathNet integrates cancer-specific biological pathways using transformer-based deep learning for enhanced cancer analysis. It outperforms existing models in predicting drug responses, cancer types, and subtypes. By enabling pathway-level biomarker discovery, DeePathNet represents a significant advancement in cancer research and could lead to more effective treatments.\",\"PeriodicalId\":72516,\"journal\":{\"name\":\"Cancer research communications\",\"volume\":\" \",\"pages\":\"3151-3164\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2024-12-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11652962/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cancer research communications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1158/2767-9764.CRC-24-0285\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ONCOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cancer research communications","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1158/2767-9764.CRC-24-0285","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ONCOLOGY","Score":null,"Total":0}

引用次数: 0

摘要

结合机器学习的多组学数据分析有望显著改善癌症诊断和预后。传统的机器学习方法通常局限于 omic 测量，忽略了现有的领域知识，如连接各种 omic 数据类型中分子实体的生物网络。在这里，我们开发了一种基于 Transformer 的可解释深度学习模型 DeePathNet，它将癌症特异性通路信息整合到多组学数据分析中。通过使用各种大数据集，包括 ProCan-DepMapSanger、CCLE 和 TCGA，我们证明并验证了 DeePathNet 在预测药物反应以及癌症类型和亚型分类方面优于传统方法。结合生物医学知识和最先进的深度学习方法，DeePathNet 能够在通路水平上发现生物标记物，最大限度地发挥数据驱动癌症研究方法的威力。DeePathNet 可在 GitHub 上查阅：https://github.com/CMRI-ProCan/DeePathNet。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

DeePathNet: A Transformer-Based Deep Learning Model Integrating Multiomic Data with Cancer Pathways.

Significance: DeePathNet integrates cancer-specific biological pathways using transformer-based deep learning for enhanced cancer analysis. It outperforms existing models in predicting drug responses, cancer types, and subtypes. By enabling pathway-level biomarker discovery, DeePathNet represents a significant advancement in cancer research and could lead to more effective treatments.

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

Cancer research communications

自引率

0.00%

发文量