基于转录组学数据和堆叠监督自编码器的肺腺癌预后预测研究

李鹏鹏; 陈锡程; 黄金羽; 伍亚舟

doi:10.16016/j.2097-0927.202212025

您当前的位置：

首页 >

文章列表页 >

基于转录组学数据和堆叠监督自编码器的肺腺癌预后预测研究

生物医学工程 | 更新时间：2026-01-09

- 基于转录组学数据和堆叠监督自编码器的肺腺癌预后预测研究
- Prognostic prediction of lung adenocarcinoma based on transcriptomic data and stacked supervised autoencoder
- 陆军军医大学学报 2023年45卷第6期页码：579-585
- 作者机构：
  
  400038 重庆，陆军军医大学(第三军医大学)军事预防医学系军队卫生统计学教研室
- 作者简介：
  
  [伍亚舟，E-mail: asiawu@tmmu.edu.cn WU Yazhou, E-mail: asiawu@tmmu.edu.cn
- 基金信息：
  
  国家自然科学基金项目(82173621);国家自然科学基金项目(81872716)
- DOI：10.16016/j.2097-0927.202212025
  中图分类号： R394.3;R730.7;R734.2
- 收稿：2022-12-04，
  
  修回：2023-01-05，
  
  纸质出版：2023-03-30
- 稿件说明：
移动端阅览
李鹏鹏, 陈锡程, 黄金羽, 等. 基于转录组学数据和堆叠监督自编码器的肺腺癌预后预测研究[J]. 陆军军医大学学报, 2023,45(6):579-585.

Pengpeng LI, Xicheng CHEN, Jinyu HUANG, et al. Prognostic prediction of lung adenocarcinoma based on transcriptomic data and stacked supervised autoencoder[J]. Journal of Army Medical University, 2023, 45(6): 579-585.
李鹏鹏, 陈锡程, 黄金羽, 等. 基于转录组学数据和堆叠监督自编码器的肺腺癌预后预测研究[J]. 陆军军医大学学报, 2023,45(6):579-585. DOI： 10.16016/j.2097-0927.202212025.

Pengpeng LI, Xicheng CHEN, Jinyu HUANG, et al. Prognostic prediction of lung adenocarcinoma based on transcriptomic data and stacked supervised autoencoder[J]. Journal of Army Medical University, 2023, 45(6): 579-585. DOI： 10.16016/j.2097-0927.202212025.

摘要

目的

基于转录组学数据构建堆叠监督自编码器(stacked supervised autoencode，SSAE)模型，旨在提高肺腺癌(lung adenocarcinoma，LUAD)预后预测的能力。

方法

收集癌症基因组图谱(the Cancer Genome Atlas，TCGA)数据库的转录组学数据(包含475例样本和25 481个基因)，对LUAD患者进行生存预后分析和基因差异表达分析，方法包括SSAE、随机生存森林(random survival forest，RSF)和DeepSurv，使用一致性指数(concordance index，CI)和Log-rank检验以

值评估各方法性能。

结果

相较于RSF(CI=0.54，

=0.15)和DeepSurv(CI=0.55，

=0.10)，SSAE获得了更高的一致性指数(CI=0.58)和更低的Log-rank检验

值(

=0.05)。在生存分析上，高危组和低危组的生存结局有显著差异(

: 2.841，95%

: 1.907~4.232，Log-rank检验

0.001)。生信分析选出了

IGFBP

1、

ANXA

13、

MUC

2、

CIDEC

、

NTSR

1、

DSG

3等21个上调的代表性差异基因。

结论

相较于既往研究，利用组学数据构建的SSAE可有效提高LUAD预后预测的能力。深度学习和组学研究的交叉融合可为癌症相关的诊断、治疗、预后研究提供新的方案。

Abstract

Objective

To build a stacked supervised autoencoder (SSAE) model based on transcriptomic data

so as to improve the prognostic prediction of lung adenocarcinoma (LUAD).

Methods

Transcriptomic data (475 samples and 25 481 genes) from the Cancer Genome Atlas (TCGA) database were collected

and the survival prognosis and gene diff

erential expression analyses were performed in LUAD patients

using SSAE

random survival forest (RSF)

and DeepSurv methods

respectively. Concordance index (CI) and

-value of Log-rank test were adopted to evaluate the performance of each method.

Results

SSAE had a higher concordance index (CI=0.58) and a lower Log-rank test

value (

=0.05) than RSF (CI=0.54

=0.15) and DeepSurv (CI=0.55

=0.10). There were significant differences in survival outcomes between the high-risk and low-risk groups in the survival analysis (HR=2.841; 95%

: 1.907~4.232; Log-rank test

0.001). Biogenic analysis identified 21 representative differentially upregulated genes

including

IGFBP

ANXA

MUC

CIDEC

NTSR

1 and

DSG

Conclusion

SSAE with omics data significantly improves the prognostic prediction of LUAD. The cross-fusion of deep learning and omics research provides a novel scheme for cancer-related research of diagnosis

treatment

and prognosis.

关键词

Keywords

references

SUNG H, FERLAY J, SIEGEL R L, et al . Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J ] . CA Cancer J Clin, 2021, 71(3): 209-249. DOI: 10.3322/caac.21660.

SPELLA M, STATHOPOULOS G T. Immune resistance in lung adenocarcinoma[J]. Cancers (Basel), 2021, 13(3): 384. DOI: 10.3390/cancers13030384.

ZAPPA C, MOUSA S A. Non-small cell lung cancer: current treatment and future advances[J]. Transl Lung Cancer Res, 2016, 5(3): 288-300. DOI: 10.21037/tlcr.2016.06.07.

COURAUD S, ZALCMAN G, MILLERON B, et al . Lung cancer in never smokers-A review[J ] . Eur J Cancer, 2012, 48(9): 1299-1311. DOI: 10.1016/j.ejca.2012.03.007.

LIU L P, LU L, ZHAO Q Q, et al . Identification and validation of the pyroptosis-related molecular subtypes of lung adenocarcinoma by bioinformatics and machine learning[J ] . Front Cell Dev Biol, 2021, 9: 756340. DOI: 10.3389/fcell.2021 .756340.

QIU M, YANG S, WANG M, et al . Prognostic evaluation of esophageal cancer patients with stages Ⅰ-Ⅲ[J ] . Aging (Albany NY), 2020, 12(14): 14736-14753. DOI: 10.18632/aging.103532.

HOESSEINI A, OFFERMAN M P J, VAN DE WALL-NEECKE B J, et al . Physicians' clinical prediction of survival in head and neck cancer patients in the palliative phase[J ] . BMC Palliat Care, 2020, 19(1): 176. DOI: 10.1186/s12904-020-00682-2.

李娟, 石锐, 余萍, 等. 癌症相关性乏力预测非小细胞肺癌患者手术预后的临床研究[J]. 华西医学, 2013, 28(09): 1411-1414.

LI J, SHI R, YU P, et al . A clinical study of predicting role of cancer-related fatigue for the post-surgery prognosis in patients with non-small cell Lung cancer[J ] . West China Med J, 2013, 28(9): 1411-1414.

CHEN X, LAN H, HE D, et al . Analysis of autophagy-related signatures identified two distinct subtypes for evaluating the tumor immune microenvironment and predicting prognosis in ovarian cancer[J ] . Front Oncol, 2021, 11: 616133. DOI: 10.3389/fonc.2021.616133.

TIAN R, LI Y, LIU Q, et al . Id entification and validation of an immune-associated RNA-binding proteins signature to predict clinical outcomes and therapeutic responses in glioma patients[J ] . Cancers (Basel), 2021, 13(7): 1730. DOI: 10.3390/cancers13071730.

TAYLOR J M G. Random survival forests[J]. J Thorac Oncol 2011, 6(12): 1974-1975. DOI: 10.1097/JTO.0b013e318233d835.

WEYER V, BINDER H. A weighting approach for judging the effect of patient strata on high-dimensional risk prediction signatures[J]. BMC Bioinformatics, 2015, 16(1): 294. DOI: 10.1186/s12859-015-0716-8.

CHING T, ZHU X, GARMIRE L X. Cox-nnet: An artificial neural network method for prognosis prediction of high-throughput omics data[J]. PLoS Comput Biol, 2018, 14(4): e1006076. DOI: 10.1371/journal.pcbi.1006076.

KATZMAN J L, SHAHAM U, CLONINGER A, et al . DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network[J ] . BMC Med Res Methodol, 2018, 18(1): 24. DOI: 10.1186/s12874-018-0482-1.

李炜, 宋威, 王晨妮, 张雨轩. 标签约束的半监督栈式自编码器分类算法[J]. 小型微型计算机系统, 2019, 40(03): 488-492.

LI W, SONG W, W ANG C N, et al . Label regularization semi-supervised stacked autoencoder classification algorithm[J ] . J Chin Comput Syst, 2019, 40(3): 488-492.

HUANG Z, JOHNSON T S, HAN Z, et al . Deep learning-based cancer survival prognosis from RNA-seq data: approaches and evaluations[J ] . BMC Med Genomics, 2020, 13(S5): 41. DOI: 10.1186/s12920-020-0686-1.

闫静, 张雪英, 李凤莲, 等. 基于栈式监督AE和可变加权ELM的回归预测算法及应用[J ] . 计算机工程: 1-10[2022-12-02 ] . DOI: 10.19678/j.issn.1000-3428.0062416 http://dx.doi.org/10.19678/j.issn.1000-3428.0062416 .

YAN J, ZHANG X Y, LI F L, et al . Regression prediction model combining stack supervised AE and variable weighted ELM[J ] . Comput Eng, 2022, 48(8)p: 62-69, 76. DOI: 10.19678/j.issn.1000-3428.0062416 http://dx.doi.org/10.19678/j.issn.1000-3428.0062416 ..

THOMPSON J A, CHRISTENSEN B C, MARSIT C J. Methylation-to-expression feature models of breast cancer accurately predict overall survival, distant-recurrence free survival, and pathologic complete response in multiple cohorts[J]. Sci Rep, 2018, 8(1): 5190. DOI: 10.1038/s41598-018-23494-0.

WANG W, ZHANG X, DAI D Q. DeFusion: a denoised network regularization framework for multi-omics integration[J]. Brief Bioinform, 2021, 22(5): bbab057. DOI: 10.1093/bib/bbab057.

WU Z X, HUANG X, CAI M J, et al . Development and validation of a prognostic index based on genes participating in autophagy in patients with lung adenocarcinoma[J ] . Front Oncol, 2022, 11: 799759. DOI: 10.3389/fonc.2021.799759.

XUE G, ZHANG C, ZHENG G, et al . Annexin A13 predicts poor prognosis for lung adenocarcinoma patients and accelerates the proliferation and migration of lung adenocarcinoma cells by modulating epithelial-mesenchymal transition[J ] . Fundam Clin Pharmacol, 2020, 34(6): 687-696. DOI: 10.1111/fcp.12555.

TAO Y, LI Y, LIANG B. Comprehensive analysis of microenvironment-related genes in lung adenocarcinoma[J]. Future Oncol, 2020, 16(24): 1825-1837. DOI: 10.2217/fon-2019-0829.

GUO F, YUAN D, ZHANG J, et al . Silencing of ARL14 gene induces lung adenocarcinoma cells to a dormant state[J ] . Front Cell Dev Biol, 2019, 7: 238. DOI: 10.3389/fcell.2019.00238.

MAO S, CHEN Z, WU Y, et al . Crosstalk of eight types of rna modification regulators defines tumor microenvironments, cancer hallmarks, and prognosis of lung adenocarcinoma[J ] . J Oncol, 2022, 2022: 1-19. DOI: 10.1155/2022/1285632.

DONG Y, LI S, SUN X, et al . Desmoglein 3 and keratin 14 for distinguishing between lung adenocarcinoma and lung squamous cell carcinoma[J ] . Onco Targets Ther, 2020, Volume 13: 11111-11124. DOI: 10.2147/OTT.S270398.

GU T, ZHAOX. Integrating multi-platform genomic datasets for kidney renal clear cell carcinoma subtyping using stacked denoising autoencoders[J]. Sci Rep, 2019, 9(1): 16668. DOI: 10.1038/s41598-019-53048-x.

LI Y, GE D, GU J, et al . A large cohort study identifying a novel prognosis prediction model for lung adenocarcinoma through machine learning strategies[J ] . BMC Cancer, 2019, 19(1): 886. DOI: 10.1186/s12885-019-6101-7.

ZHAO M, CHEN Z, ZHENG Y, et al . Identification of cancer stem cell-related biomarkers in lung adenocarcinoma by stemness index and weighted correlation network analysis[J ] . J Cancer Res Clin Oncol, 2020, 146(6): 1463-1472. DOI: 10.1007/s00432-020-03194-x.

HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507. DOI: 10.1126/science.1127647.

LIU Q, HU P. Association analysis of deep genomic features extracted by denoising autoencoders in breast cancer[J]. Cancers, 2019, 11(4): 494. DOI: 10.3390/cancers11040494.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于转录组学和变分自编码器的癌症分期诊断研究

肺腺癌相关tsRNA的筛选和验证

局部晚期或转移性肺腺癌罕见基因突变患者的临床特征和生存分析

腺苷脱氨酶1在肺腺癌组织中的表达及临床意义

烟草烟雾提取物激活NLRP3炎性小体促进肺腺癌PC-9细胞侵袭