A Machine-Learning Approach to Developing a Predictive Signature Based on Transcriptome Profiling of Ground-Glass Opacities for Accurate Classification and Exploring the Immune Microenvironment of Early-Stage LUAD

Screening for early-stage lung cancer with low-dose computed tomography is recommended for high-risk populations; consequently, the incidence of pure ground-glass opacity (pGGO) is increasing. Ground-glass opacity (GGO) is considered the appearance of early lung cancer, and there remains an unmet cl...

Full description

Bibliographic Details
Main Authors: Zhenyu Zhao, Wei Yin, Xiong Peng, Qidong Cai, Boxue He, Shuai Shi, Weilin Peng, Guangxu Tu, Yunping Li, Dateng Li, Yongguang Tao, Muyun Peng, Xiang Wang, Fenglei Yu
Format: Article
Language:English
Published: Frontiers Media S.A. 2022-05-01
Series:Frontiers in Immunology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fimmu.2022.872387/full
_version_ 1811255400407760896
author Zhenyu Zhao
Zhenyu Zhao
Wei Yin
Wei Yin
Xiong Peng
Xiong Peng
Qidong Cai
Qidong Cai
Boxue He
Boxue He
Shuai Shi
Shuai Shi
Weilin Peng
Weilin Peng
Guangxu Tu
Guangxu Tu
Yunping Li
Dateng Li
Yongguang Tao
Yongguang Tao
Yongguang Tao
Yongguang Tao
Muyun Peng
Muyun Peng
Xiang Wang
Xiang Wang
Fenglei Yu
Fenglei Yu
author_facet Zhenyu Zhao
Zhenyu Zhao
Wei Yin
Wei Yin
Xiong Peng
Xiong Peng
Qidong Cai
Qidong Cai
Boxue He
Boxue He
Shuai Shi
Shuai Shi
Weilin Peng
Weilin Peng
Guangxu Tu
Guangxu Tu
Yunping Li
Dateng Li
Yongguang Tao
Yongguang Tao
Yongguang Tao
Yongguang Tao
Muyun Peng
Muyun Peng
Xiang Wang
Xiang Wang
Fenglei Yu
Fenglei Yu
author_sort Zhenyu Zhao
collection DOAJ
description Screening for early-stage lung cancer with low-dose computed tomography is recommended for high-risk populations; consequently, the incidence of pure ground-glass opacity (pGGO) is increasing. Ground-glass opacity (GGO) is considered the appearance of early lung cancer, and there remains an unmet clinical need to understand the pathology of small GGO (<1 cm in diameter). The objective of this study was to use the transcriptome profiling of pGGO specimens <1 cm in diameter to construct a pGGO-related gene risk signature to predict the prognosis of early-stage lung adenocarcinoma (LUAD) and explore the immune microenvironment of GGO. pGGO-related differentially expressed genes (DEGs) were screened to identify prognostic marker genes with two machine learning algorithms. A 15-gene risk signature was constructed from the DEGs that were shared between the algorithms. Risk scores were calculated using the regression coefficients for the pGGO-related DEGs. Patients with Stage I/II LUAD or Stage IA LUAD and high-risk scores had a worse prognosis than patients with low-risk scores. The prognosis of high-risk patients with Stage IA LUAD was almost identical to that of patients with Stage II LUAD, suggesting that treatment strategies for patients with Stage II LUAD may be beneficial in high-risk patients with Stage IA LUAD. pGGO-related DEGs were mainly enriched in immune-related pathways. Patients with high-risk scores and high tumor mutation burden had a worse prognosis and may benefit from immunotherapy. A nomogram was constructed to facilitate the clinical application of the 15-gene risk signature. Receiver operating characteristic curves and decision curve analysis validated the predictive ability of the nomogram in patients with Stage I LUAD in the TCGA-LUAD cohort and GEO datasets.
first_indexed 2024-04-12T17:23:14Z
format Article
id doaj.art-2ccd6d10ec35421dac075298e3b6e39f
institution Directory Open Access Journal
issn 1664-3224
language English
last_indexed 2024-04-12T17:23:14Z
publishDate 2022-05-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Immunology
spelling doaj.art-2ccd6d10ec35421dac075298e3b6e39f2022-12-22T03:23:23ZengFrontiers Media S.A.Frontiers in Immunology1664-32242022-05-011310.3389/fimmu.2022.872387872387A Machine-Learning Approach to Developing a Predictive Signature Based on Transcriptome Profiling of Ground-Glass Opacities for Accurate Classification and Exploring the Immune Microenvironment of Early-Stage LUADZhenyu Zhao0Zhenyu Zhao1Wei Yin2Wei Yin3Xiong Peng4Xiong Peng5Qidong Cai6Qidong Cai7Boxue He8Boxue He9Shuai Shi10Shuai Shi11Weilin Peng12Weilin Peng13Guangxu Tu14Guangxu Tu15Yunping Li16Dateng Li17Yongguang Tao18Yongguang Tao19Yongguang Tao20Yongguang Tao21Muyun Peng22Muyun Peng23Xiang Wang24Xiang Wang25Fenglei Yu26Fenglei Yu27Department of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Ophthalmology, The Second Xiangya Hospital of Central South University, Changsha, ChinaWhite Plains, NY, United StatesDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaKey Laboratory of Carcinogenesis and Cancer Invasion, Ministry of Education, Department of Pathology, Xiangya Hospital, Central South University, Changsha, ChinaNational Health Council (NHC) Key Laboratory of Carcinogenesis (Central South University), Cancer Research Institute and School of Basic Medicine, Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaDepartment of Thoracic Surgery, The Second Xiangya Hospital of Central South University, Changsha, ChinaHunan Key Laboratory of Early Diagnosis and Precise Treatment of Lung Cancer, The Second Xiangya Hospital of Central South University, Changsha, ChinaScreening for early-stage lung cancer with low-dose computed tomography is recommended for high-risk populations; consequently, the incidence of pure ground-glass opacity (pGGO) is increasing. Ground-glass opacity (GGO) is considered the appearance of early lung cancer, and there remains an unmet clinical need to understand the pathology of small GGO (<1 cm in diameter). The objective of this study was to use the transcriptome profiling of pGGO specimens <1 cm in diameter to construct a pGGO-related gene risk signature to predict the prognosis of early-stage lung adenocarcinoma (LUAD) and explore the immune microenvironment of GGO. pGGO-related differentially expressed genes (DEGs) were screened to identify prognostic marker genes with two machine learning algorithms. A 15-gene risk signature was constructed from the DEGs that were shared between the algorithms. Risk scores were calculated using the regression coefficients for the pGGO-related DEGs. Patients with Stage I/II LUAD or Stage IA LUAD and high-risk scores had a worse prognosis than patients with low-risk scores. The prognosis of high-risk patients with Stage IA LUAD was almost identical to that of patients with Stage II LUAD, suggesting that treatment strategies for patients with Stage II LUAD may be beneficial in high-risk patients with Stage IA LUAD. pGGO-related DEGs were mainly enriched in immune-related pathways. Patients with high-risk scores and high tumor mutation burden had a worse prognosis and may benefit from immunotherapy. A nomogram was constructed to facilitate the clinical application of the 15-gene risk signature. Receiver operating characteristic curves and decision curve analysis validated the predictive ability of the nomogram in patients with Stage I LUAD in the TCGA-LUAD cohort and GEO datasets.https://www.frontiersin.org/articles/10.3389/fimmu.2022.872387/fullGGO (ground-glass opacity)LUADTCGAGEOprognosis
spellingShingle Zhenyu Zhao
Zhenyu Zhao
Wei Yin
Wei Yin
Xiong Peng
Xiong Peng
Qidong Cai
Qidong Cai
Boxue He
Boxue He
Shuai Shi
Shuai Shi
Weilin Peng
Weilin Peng
Guangxu Tu
Guangxu Tu
Yunping Li
Dateng Li
Yongguang Tao
Yongguang Tao
Yongguang Tao
Yongguang Tao
Muyun Peng
Muyun Peng
Xiang Wang
Xiang Wang
Fenglei Yu
Fenglei Yu
A Machine-Learning Approach to Developing a Predictive Signature Based on Transcriptome Profiling of Ground-Glass Opacities for Accurate Classification and Exploring the Immune Microenvironment of Early-Stage LUAD
Frontiers in Immunology
GGO (ground-glass opacity)
LUAD
TCGA
GEO
prognosis
title A Machine-Learning Approach to Developing a Predictive Signature Based on Transcriptome Profiling of Ground-Glass Opacities for Accurate Classification and Exploring the Immune Microenvironment of Early-Stage LUAD
title_full A Machine-Learning Approach to Developing a Predictive Signature Based on Transcriptome Profiling of Ground-Glass Opacities for Accurate Classification and Exploring the Immune Microenvironment of Early-Stage LUAD
title_fullStr A Machine-Learning Approach to Developing a Predictive Signature Based on Transcriptome Profiling of Ground-Glass Opacities for Accurate Classification and Exploring the Immune Microenvironment of Early-Stage LUAD
title_full_unstemmed A Machine-Learning Approach to Developing a Predictive Signature Based on Transcriptome Profiling of Ground-Glass Opacities for Accurate Classification and Exploring the Immune Microenvironment of Early-Stage LUAD
title_short A Machine-Learning Approach to Developing a Predictive Signature Based on Transcriptome Profiling of Ground-Glass Opacities for Accurate Classification and Exploring the Immune Microenvironment of Early-Stage LUAD
title_sort machine learning approach to developing a predictive signature based on transcriptome profiling of ground glass opacities for accurate classification and exploring the immune microenvironment of early stage luad
topic GGO (ground-glass opacity)
LUAD
TCGA
GEO
prognosis
url https://www.frontiersin.org/articles/10.3389/fimmu.2022.872387/full
work_keys_str_mv AT zhenyuzhao amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT zhenyuzhao amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT weiyin amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT weiyin amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT xiongpeng amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT xiongpeng amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT qidongcai amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT qidongcai amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT boxuehe amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT boxuehe amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT shuaishi amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT shuaishi amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT weilinpeng amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT weilinpeng amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT guangxutu amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT guangxutu amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yunpingli amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT datengli amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yongguangtao amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yongguangtao amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yongguangtao amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yongguangtao amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT muyunpeng amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT muyunpeng amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT xiangwang amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT xiangwang amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT fengleiyu amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT fengleiyu amachinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT zhenyuzhao machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT zhenyuzhao machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT weiyin machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT weiyin machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT xiongpeng machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT xiongpeng machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT qidongcai machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT qidongcai machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT boxuehe machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT boxuehe machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT shuaishi machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT shuaishi machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT weilinpeng machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT weilinpeng machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT guangxutu machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT guangxutu machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yunpingli machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT datengli machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yongguangtao machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yongguangtao machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yongguangtao machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT yongguangtao machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT muyunpeng machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT muyunpeng machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT xiangwang machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT xiangwang machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT fengleiyu machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad
AT fengleiyu machinelearningapproachtodevelopingapredictivesignaturebasedontranscriptomeprofilingofgroundglassopacitiesforaccurateclassificationandexploringtheimmunemicroenvironmentofearlystageluad