Machine learning–guided single-cell multiomics uncovers GDF15-driven immunosuppressive niches in NSCLC: A translational framework for overcoming anti-PD-1 resistance

Immune checkpoint blockade (ICB) has transformed non-small cell lung cancer (NSCLC) treatment, but durable clinical responses remain limited, underscoring the need for robust predictive biomarkers. We integrated multiomics profiling with machine learning to systematically identify determinants of IC...

Full description

Saved in:
Bibliographic Details
Main Authors: Xianfei Zhang, Zhengxin Yin, Xueyu Chen, Nengchong Zhang, Shengjia Yu, Congcong Zhu, Lianggang Zhu, Liulan Shao, Bin Li, Runsen Jin, Hecheng Li
Format: Article
Language:English
Published: Elsevier 2025-09-01
Series:Translational Oncology
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1936523325001901
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850108776485486592
author Xianfei Zhang
Zhengxin Yin
Xueyu Chen
Nengchong Zhang
Shengjia Yu
Congcong Zhu
Lianggang Zhu
Liulan Shao
Bin Li
Runsen Jin
Hecheng Li
author_facet Xianfei Zhang
Zhengxin Yin
Xueyu Chen
Nengchong Zhang
Shengjia Yu
Congcong Zhu
Lianggang Zhu
Liulan Shao
Bin Li
Runsen Jin
Hecheng Li
author_sort Xianfei Zhang
collection DOAJ
description Immune checkpoint blockade (ICB) has transformed non-small cell lung cancer (NSCLC) treatment, but durable clinical responses remain limited, underscoring the need for robust predictive biomarkers. We integrated multiomics profiling with machine learning to systematically identify determinants of ICB efficacy. Comparative evaluation of 22 survival algorithms across four NSCLC cohorts (n=156) led to the development of an Accelerated Oblique Random Survival Forest model, which outperformed conventional Cox regression and deep learning methods in predictive accuracy (training C-index=0.864; test C-index=0.748). Single-cell RNA sequencing of an immunotherapy-treated cohort revealed that high-risk tumors harbor malignant epithelial subclusters expressing growth differentiation factor 15 (GDF15), a transforming growth factor-β superfamily member implicated in immune evasion. Single-cell non-negative matrix factorization identified GDF15 as a network hub regulating proliferative dominance. External validation using melanoma cohorts (GSE91061) confirmed the pan-cancer predictive relevance of GDF15 and its associated tumor cluster. Functional studies utilizing GDF15-knockdown Lewis lung carcinoma cells showed no significant effect on intrinsic tumor proliferation or growth under immune stress (both p>0.05). GDF15 deletion significantly potentiated PD-1 inhibitor efficacy in vivo, reducing tumor mass by 94.41±6.53 % (SH1) and 94.54±5.21 % (SH2) compared with 3.39±54.90 % in empty vector controls (p<0.01 for all comparisons). CD8+ T cell infiltration was also substantially enhanced (81.62±4.79 % [SH1] and 123.50±10.02 % [SH2] vs. 29.63±22.17 % [EV], p<0.05). These findings implicate GDF15 as a regulator of the immunosuppressive tumor microenvironment. Our findings position GDF15 as a first-in-class biomarker for predicting ICB resistance; they establish a translational framework that bridges computational prediction with single-cell mechanistic insights to inform NSCLC immunotherapy.
format Article
id doaj-art-14920c67daae40df9e616355a014b733
institution OA Journals
issn 1936-5233
language English
publishDate 2025-09-01
publisher Elsevier
record_format Article
series Translational Oncology
spelling doaj-art-14920c67daae40df9e616355a014b7332025-08-20T02:38:15ZengElsevierTranslational Oncology1936-52332025-09-015910245910.1016/j.tranon.2025.102459Machine learning–guided single-cell multiomics uncovers GDF15-driven immunosuppressive niches in NSCLC: A translational framework for overcoming anti-PD-1 resistanceXianfei Zhang0Zhengxin Yin1Xueyu Chen2Nengchong Zhang3Shengjia Yu4Congcong Zhu5Lianggang Zhu6Liulan Shao7Bin Li8Runsen Jin9Hecheng Li10Department of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of MedicineDepartment of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of MedicineDepartment of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of MedicineDepartment of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of MedicineDepartment of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of MedicineDepartment of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of MedicineDepartment of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of MedicineDepartment of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of MedicineCenter for Immune-Related Diseases at Shanghai Institute of Immunology, Department of Respiratory and Critical Care Medicine of Ruijin Hospital, Department of Thoracic Surgery of Ruijin Hospital, Department of Immunology and Microbiology, Shanghai Jiao Tong University School of Medicine, Shanghai, China; Corresponding author at: Center for Immune-Related Diseases at Shanghai Institute of Immunology, Department of Respiratory and Critical Care Medicine of Ruijin Hospital, Department of Thoracic Surgery of Ruijin Hospital, Department of Immunology and Microbiology, Shanghai Jiao Tong University School of Medicine, Shanghai, 200025, China.Department of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of Medicine; Corresponding authors at: Department of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, 197 Ruijin 2nd Road, Shanghai, 200025, China.Department of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of Medicine; Corresponding authors at: Department of Thoracic Surgery, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, 197 Ruijin 2nd Road, Shanghai, 200025, China.Immune checkpoint blockade (ICB) has transformed non-small cell lung cancer (NSCLC) treatment, but durable clinical responses remain limited, underscoring the need for robust predictive biomarkers. We integrated multiomics profiling with machine learning to systematically identify determinants of ICB efficacy. Comparative evaluation of 22 survival algorithms across four NSCLC cohorts (n=156) led to the development of an Accelerated Oblique Random Survival Forest model, which outperformed conventional Cox regression and deep learning methods in predictive accuracy (training C-index=0.864; test C-index=0.748). Single-cell RNA sequencing of an immunotherapy-treated cohort revealed that high-risk tumors harbor malignant epithelial subclusters expressing growth differentiation factor 15 (GDF15), a transforming growth factor-β superfamily member implicated in immune evasion. Single-cell non-negative matrix factorization identified GDF15 as a network hub regulating proliferative dominance. External validation using melanoma cohorts (GSE91061) confirmed the pan-cancer predictive relevance of GDF15 and its associated tumor cluster. Functional studies utilizing GDF15-knockdown Lewis lung carcinoma cells showed no significant effect on intrinsic tumor proliferation or growth under immune stress (both p>0.05). GDF15 deletion significantly potentiated PD-1 inhibitor efficacy in vivo, reducing tumor mass by 94.41±6.53 % (SH1) and 94.54±5.21 % (SH2) compared with 3.39±54.90 % in empty vector controls (p<0.01 for all comparisons). CD8+ T cell infiltration was also substantially enhanced (81.62±4.79 % [SH1] and 123.50±10.02 % [SH2] vs. 29.63±22.17 % [EV], p<0.05). These findings implicate GDF15 as a regulator of the immunosuppressive tumor microenvironment. Our findings position GDF15 as a first-in-class biomarker for predicting ICB resistance; they establish a translational framework that bridges computational prediction with single-cell mechanistic insights to inform NSCLC immunotherapy.http://www.sciencedirect.com/science/article/pii/S1936523325001901Lung cancerImmunotherapyGrowth differentiation factor 15Programmed cell death protein 1
spellingShingle Xianfei Zhang
Zhengxin Yin
Xueyu Chen
Nengchong Zhang
Shengjia Yu
Congcong Zhu
Lianggang Zhu
Liulan Shao
Bin Li
Runsen Jin
Hecheng Li
Machine learning–guided single-cell multiomics uncovers GDF15-driven immunosuppressive niches in NSCLC: A translational framework for overcoming anti-PD-1 resistance
Translational Oncology
Lung cancer
Immunotherapy
Growth differentiation factor 15
Programmed cell death protein 1
title Machine learning–guided single-cell multiomics uncovers GDF15-driven immunosuppressive niches in NSCLC: A translational framework for overcoming anti-PD-1 resistance
title_full Machine learning–guided single-cell multiomics uncovers GDF15-driven immunosuppressive niches in NSCLC: A translational framework for overcoming anti-PD-1 resistance
title_fullStr Machine learning–guided single-cell multiomics uncovers GDF15-driven immunosuppressive niches in NSCLC: A translational framework for overcoming anti-PD-1 resistance
title_full_unstemmed Machine learning–guided single-cell multiomics uncovers GDF15-driven immunosuppressive niches in NSCLC: A translational framework for overcoming anti-PD-1 resistance
title_short Machine learning–guided single-cell multiomics uncovers GDF15-driven immunosuppressive niches in NSCLC: A translational framework for overcoming anti-PD-1 resistance
title_sort machine learning guided single cell multiomics uncovers gdf15 driven immunosuppressive niches in nsclc a translational framework for overcoming anti pd 1 resistance
topic Lung cancer
Immunotherapy
Growth differentiation factor 15
Programmed cell death protein 1
url http://www.sciencedirect.com/science/article/pii/S1936523325001901
work_keys_str_mv AT xianfeizhang machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT zhengxinyin machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT xueyuchen machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT nengchongzhang machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT shengjiayu machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT congcongzhu machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT lianggangzhu machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT liulanshao machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT binli machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT runsenjin machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance
AT hechengli machinelearningguidedsinglecellmultiomicsuncoversgdf15drivenimmunosuppressivenichesinnsclcatranslationalframeworkforovercomingantipd1resistance