• 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

基于机器学习的失巢凋亡特征可预测乳腺癌的个性化治疗策略。

Machine learning based anoikis signature predicts personalized treatment strategy of breast cancer.

作者信息

Guo Xiao, Xing Jiaying, Cao Yuyan, Yang Wenchuang, Shi Xinlin, Mu Runhong, Wang Tao

机构信息

School of Pharmacy, Beihua University, Jilin, China.

School of Basic Medical Sciences, Beihua University, Jilin, China.

出版信息

Front Immunol. 2024 Nov 22;15:1491508. doi: 10.3389/fimmu.2024.1491508. eCollection 2024.

DOI:10.3389/fimmu.2024.1491508
PMID:39650663
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC11621045/
Abstract

BACKGROUND

Breast cancer remains a leading cause of mortality among women worldwide, emphasizing the urgent need for innovative prognostic tools to improve treatment strategies. Anoikis, a form of programmed cell death critical in preventing metastasis, plays a pivotal role in breast cancer progression.

METHODS

This study introduces the Artificial Intelligence-Derived Anoikis Signature (AIDAS), a novel machine learning-based prognostic tool that identifies key anoikis-related gene patterns in breast cancer. AIDAS was developed using multi-cohort transcriptomic data and validated through immunohistochemistry assays on clinical samples to ensure robustness and broad applicability.

RESULTS

AIDAS outperformed existing prognostic models in accurately predicting breast cancer outcomes, providing a reliable tool for personalized treatment. Patients with low AIDAS levels were found to be more responsive to immunotherapies, including PD-1/PD-L1 inhibitors, while high-AIDAS patients demonstrated greater susceptibility to specific chemotherapeutic agents, such as methotrexate.

CONCLUSIONS

These findings highlight the critical role of anoikis in breast cancer prognosis and underscore AIDAS's potential to guide individualized treatment strategies. By integrating machine learning with biological insights, AIDAS offers a promising approach for advancing personalized oncology. Its detailed understanding of the anoikis landscape paves the way for the development of targeted therapies, promising significant improvements in patient outcomes.

摘要

背景

乳腺癌仍是全球女性死亡的主要原因，这凸显了迫切需要创新的预后工具来改善治疗策略。失巢凋亡是一种对预防转移至关重要的程序性细胞死亡形式，在乳腺癌进展中起关键作用。

方法

本研究引入了人工智能衍生的失巢凋亡特征（AIDAS），这是一种基于机器学习的新型预后工具，可识别乳腺癌中与失巢凋亡相关的关键基因模式。AIDAS利用多队列转录组数据开发，并通过对临床样本的免疫组织化学分析进行验证，以确保其稳健性和广泛适用性。

结果

AIDAS在准确预测乳腺癌预后方面优于现有预后模型，为个性化治疗提供了可靠工具。发现AIDAS水平低的患者对免疫疗法（包括PD-1/PD-L1抑制剂）反应更强，而AIDAS水平高的患者对特定化疗药物（如甲氨蝶呤）更敏感。

结论

这些发现突出了失巢凋亡在乳腺癌预后中的关键作用，并强调了AIDAS在指导个体化治疗策略方面的潜力。通过将机器学习与生物学见解相结合，AIDAS为推进个性化肿瘤学提供了一种有前景的方法。其对失巢凋亡情况的详细了解为靶向治疗的开发铺平了道路，有望显著改善患者预后。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/d5768318ce62/fimmu-15-1491508-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/65304eb8ef57/fimmu-15-1491508-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/a664e69e667a/fimmu-15-1491508-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/2135362db5c2/fimmu-15-1491508-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/f39a34274843/fimmu-15-1491508-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/2d0fc9066ee1/fimmu-15-1491508-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/d2294b85a0cc/fimmu-15-1491508-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/f6dd70143450/fimmu-15-1491508-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/b82f6431753b/fimmu-15-1491508-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/d5768318ce62/fimmu-15-1491508-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/65304eb8ef57/fimmu-15-1491508-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/a664e69e667a/fimmu-15-1491508-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/2135362db5c2/fimmu-15-1491508-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/f39a34274843/fimmu-15-1491508-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/2d0fc9066ee1/fimmu-15-1491508-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/d2294b85a0cc/fimmu-15-1491508-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/f6dd70143450/fimmu-15-1491508-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/b82f6431753b/fimmu-15-1491508-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/4244/11621045/d5768318ce62/fimmu-15-1491508-g009.jpg

相似文献

1
Machine learning based anoikis signature predicts personalized treatment strategy of breast cancer.基于机器学习的失巢凋亡特征可预测乳腺癌的个性化治疗策略。
Front Immunol. 2024 Nov 22;15:1491508. doi: 10.3389/fimmu.2024.1491508. eCollection 2024.
2
Epigenetic profiling for prognostic stratification and personalized therapy in breast cancer.用于乳腺癌预后分层和个性化治疗的表观遗传学分析
Front Immunol. 2025 Jan 14;15:1510829. doi: 10.3389/fimmu.2024.1510829. eCollection 2024.
3
Integration of Machine Learning and Experimental Validation to Identify Anoikis-Related Prognostic Signature for Predicting the Breast Cancer Tumor Microenvironment and Treatment Response.整合机器学习与实验验证，以识别与失巢凋亡相关的预后标志物，用于预测乳腺癌肿瘤微环境和治疗反应。
Genes (Basel). 2024 Nov 12;15(11):1458. doi: 10.3390/genes15111458.
4
Integrating anoikis and ErbB signaling insights with machine learning and single-cell analysis for predicting prognosis and immune-targeted therapy outcomes in hepatocellular carcinoma.将失巢凋亡和 ErbB 信号通路的见解与机器学习和单细胞分析相结合，预测肝细胞癌的预后和免疫靶向治疗结果。
Front Immunol. 2024 Oct 11;15:1446961. doi: 10.3389/fimmu.2024.1446961. eCollection 2024.
5
Evaluating the prognostic potential of telomerase signature in breast cancer through advanced machine learning model.通过先进的机器学习模型评估端粒酶特征在乳腺癌中的预后潜力。
Front Immunol. 2024 Nov 28;15:1462953. doi: 10.3389/fimmu.2024.1462953. eCollection 2024.
6
Comprehensive single-cell and bulk transcriptomic analyses to develop an NK cell-derived gene signature for prognostic assessment and precision medicine in breast cancer.全面的单细胞和批量转录组分析，为乳腺癌的预后评估和精准医学开发 NK 细胞衍生的基因特征。
Front Immunol. 2024 Oct 23;15:1460607. doi: 10.3389/fimmu.2024.1460607. eCollection 2024.
7
Artificial intelligence-assisted RNA-binding protein signature for prognostic stratification and therapeutic guidance in breast cancer.用于乳腺癌预后分层和治疗指导的人工智能辅助RNA结合蛋白特征
Front Immunol. 2025 Apr 16;16:1583103. doi: 10.3389/fimmu.2025.1583103. eCollection 2025.
8
Anoikis resistance regulates immune infiltration and drug sensitivity in clear-cell renal cell carcinoma: insights from multi omics, single cell analysis and experiment.失巢凋亡抵抗调节透明细胞肾细胞癌中的免疫浸润和药物敏感性：多组学、单细胞分析和实验的见解。
Front Immunol. 2024 Jun 17;15:1427475. doi: 10.3389/fimmu.2024.1427475. eCollection 2024.
9
Anoikis-related genes in breast cancer patients: reliable biomarker of prognosis.乳腺癌患者的 anoikis 相关基因：可靠的预后生物标志物。
BMC Cancer. 2024 Sep 19;24(1):1163. doi: 10.1186/s12885-024-12830-5.
10
Integrating Machine Learning and Bulk and Single-Cell RNA Sequencing to Decipher Diverse Cell Death Patterns for Predicting the Prognosis of Neoadjuvant Chemotherapy in Breast Cancer.整合机器学习与批量及单细胞RNA测序以解析多种细胞死亡模式用于预测乳腺癌新辅助化疗的预后
Int J Mol Sci. 2025 Apr 13;26(8):3682. doi: 10.3390/ijms26083682.

引用本文的文献

1
Revolutionizing breast cancer immunotherapy by integrating AI and nanotechnology approaches: review of current applications and future directions.通过整合人工智能和纳米技术方法革新乳腺癌免疫疗法：当前应用与未来方向综述
Bioelectron Med. 2025 May 30;11(1):13. doi: 10.1186/s42234-025-00173-w.

本文引用的文献

1
Integrating PANoptosis insights to enhance breast cancer prognosis and therapeutic decision-making.将 PANoptosis 见解整合起来，以增强乳腺癌的预后和治疗决策。
Front Immunol. 2024 Mar 5;15:1359204. doi: 10.3389/fimmu.2024.1359204. eCollection 2024.
2
PD-1 maintains CD8 T cell tolerance towards cutaneous neoantigens.PD-1 维持 CD8 T 细胞对皮肤新生抗原的耐受。
Nature. 2023 Jul;619(7968):151-159. doi: 10.1038/s41586-023-06217-y. Epub 2023 Jun 21.
3
Comprehensive machine-learning survival framework develops a consensus model in large-scale multicenter cohorts for pancreatic cancer.
综合机器学习生存框架在大型多中心队列中为胰腺癌开发共识模型。
Elife. 2022 Oct 25;11:e80150. doi: 10.7554/eLife.80150.
4
Application of Artificial Intelligence Techniques to Predict Risk of Recurrence of Breast Cancer: A Systematic Review.应用人工智能技术预测乳腺癌复发风险：一项系统综述。
J Pers Med. 2022 Sep 13;12(9):1496. doi: 10.3390/jpm12091496.
5
Nuclear import of PTPN18 inhibits breast cancer metastasis mediated by MVP and importin β2.核输入的 PTPN18 通过 MVP 和 importinβ2 抑制乳腺癌转移。
Cell Death Dis. 2022 Aug 18;13(8):720. doi: 10.1038/s41419-022-05167-z.
6
Immunogenomic Landscape in Breast Cancer Reveals Immunotherapeutically Relevant Gene Signatures.乳腺癌的免疫基因组景观揭示了免疫治疗相关的基因特征。
Front Immunol. 2022 Jan 27;13:805184. doi: 10.3389/fimmu.2022.805184. eCollection 2022.
7
circCDYL2 promotes trastuzumab resistance via sustaining HER2 downstream signaling in breast cancer.环状 CDYL2 通过维持乳腺癌中 HER2 下游信号转导促进曲妥珠单抗耐药。
Mol Cancer. 2022 Jan 3;21(1):8. doi: 10.1186/s12943-021-01476-7.
8
A Systematic Review on the Therapeutic Potentiality of PD-L1-Inhibiting MicroRNAs for Triple-Negative Breast Cancer: Toward Single-Cell Sequencing-Guided Biomimetic Delivery.PD-L1 抑制性 microRNAs 治疗三阴性乳腺癌的系统评价：迈向单细胞测序指导的仿生递药。
Genes (Basel). 2021 Aug 4;12(8):1206. doi: 10.3390/genes12081206.
9
IOBR: Multi-Omics Immuno-Oncology Biological Research to Decode Tumor Microenvironment and Signatures.IOBR：多组学免疫肿瘤生物学研究解码肿瘤微环境和特征。
Front Immunol. 2021 Jul 2;12:687975. doi: 10.3389/fimmu.2021.687975. eCollection 2021.
10
A single-cell RNA expression atlas of normal, preneoplastic and tumorigenic states in the human breast.人类乳腺正常、癌前病变和肿瘤发生状态的单细胞 RNA 表达图谱。
EMBO J. 2021 Jun 1;40(11):e107333. doi: 10.15252/embj.2020107333. Epub 2021 May 5.