DataVXAdvanced SciencePaper
journal article·2026-01Open access

Predicting Immunotherapy Outcomes in NSCLC Using RNA and Pathology from Multicenter Clinical Trials

Zhaojun Wang, Yiran Fang, Xiatong Huang, Guichuang Ma, Qianqian Mao, Xiansheng Lu, Guangda Rong, Yunfang Yu, Yuanyuan Wang, Zhenhua Huang, Huiying Sun, Jiani Wu, Wenchao Gu, Na Huang, Jianhua Wu, Rui Zhou, Xiaoxiang Rong, Siting Zheng, Shaowei Li, Gaofeng Wang, Ling Wang, Wenjun Qiu, Luyang Jiang, Peng Luo, Yonggang Liu, Jianping Bin, Yulin Liao, Min Shi, Zuqiang Wu, Jiguang Wang, Wangjun Liao, Gang Chen, Dongqiang Zeng

Advanced Science· Volume 13· Issue 3
Publisher pageOpen full text
Source abstract

Abstract

Abstract Immune checkpoint inhibitors (ICIs) are widely used to treat advanced non‐small cell lung cancer (NSCLC). However, it remains crucial to identify patients who are unlikely to benefit from immunotherapy and to explore potential combination treatment strategies. In this study, 1127 advanced NSCLC patients from multicenter randomized clinical trials (OAK, POPLAR, ORIENT‐11) and an in‐house cohort who received ICIs, ICIs combined with chemotherapy, or chemotherapy alone are analyzed. Using bulk RNA‐seq transcriptomic data, an RNA‐based model, named the Lung Cancer Immunotherapy Response Assessment (LIRA), is developed, utilizing interaction analysis and a random forest algorithm to predict immunotherapy outcomes. LIRA outperforms PD‐L1 expression and tumor mutation burden in predicting responses, particularly in identifying early progression risk during ICI monotherapy (HR: 0.15, 95% CI: 0.11–0.20). Tumor profile analysis reveals that LRP8 and HDAC4 are associated with immunotherapy outcomes. Additionally, scRNA‐seq analysis of NSCLC tumors indicates a higher prevalence of T cells and a reduced proportion of epithelial cells in samples with a high LIRA‐score. The deep learning model pinpointed critical high‐attention regions within whole‐slide images that contributed decisively to the LIRA predictions. In summary, these results demonstrate that LIRA enables independent risk stratification of NSCLC patients and provides insights into potential resistance mechanisms.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Cancer Immunotherapy and Biomarkers · Ferroptosis and cancer prognosis · Radiomics and Machine Learning in Medical Imaging

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Oncology Nanfang Hospital Southern Medical University Guangzhou Guangdong 510515 P. R. China

Cancer Center the Sixth Affiliated Hospital School of Medicine South China University of Technology Foshan 528000 China

Foshan Key Laboratory of Translational Medicine in Oncology the Sixth Affiliated Hospital School of Medicine South China University of Technology Foshan 528000 China

Department of Pathology Nanfang Hospital Southern Medical University Guangzhou Guangdong 510515 P.R. China

Department of Medical Oncology Sun Yat‐sen Memorial Hospital Sun Yat‐sen University Guangzhou 510120 China

Faculty of Medicine Macau University of Science and Technology Taipa Macao 999078 China

Department of Artificial Intelligence Medicine Graduate School of Medicine Chiba University Chiba 260‐867 Japan

Department of Plastic and Aesthetic Surgery Nanfang Hospital of Southern Medical University Guangzhou Guangdong 510515 China

Department of Dermatology Johns Hopkins University School of Medicine Baltimore MD 21210 USA

Department of Oncology Zhujiang Hospital Southern Medical University Guangzhou Guangdong 510280 China

Department of Oncology The Eighth Affiliated Hospital of Southern Medical University (The First People's Hospital of Shunde, Foshan) Foshan Guangdong 528308 China

Department of Cardiology Nanfang Hospital Southern Medical University Guangzhou Guangdong 510515 P.R. China

Division of Life Science Department of Chemical and Biological Engineering Centre of Systems Biology and Human Health and State Key Laboratory of Molecular Neuroscience The Hong Kong University of Science and Technology Hong Kong 999077 P. R. China

Department of Medical Oncology Sun Yat‐sen University Cancer Center State Key Laboratory of Oncology in South China Collaborative Innovation Center for Cancer Medicine 510060 Guangdong Province China

Funding

National Natural Science Foundation of China

References (94)

Show source-provided references
1. 10.1056/NEJMoa191734610.1056/NEJMoa1917346 ↗
2. 10.1056/NEJMoa180100510.1056/NEJMoa1801005 ↗
3. 10.1200/JCO.19.0313610.1200/JCO.19.03136 ↗
4. 10.1016/S0140-6736(15)01281-710.1016/S0140-6736(15)01281-7 ↗
5. 10.1186/s12943-023-01740-y10.1186/s12943-023-01740-y ↗
6. 10.1038/s41591-021-01450-210.1038/s41591-021-01450-2 ↗
7. 10.1038/s41392-024-01823-210.1038/s41392-024-01823-2 ↗
8. 10.1056/NEJMoa120069010.1056/NEJMoa1200690 ↗
9. 10.1158/1078-0432.CCR-13-327110.1158/1078-0432.CCR-13-3271 ↗
10. 10.1038/s41591-022-01754-x10.1038/s41591-022-01754-x ↗
11. 10.1038/s41591-022-02163-w10.1038/s41591-022-02163-w ↗
12. 10.1126/science.aar359310.1126/science.aar3593 ↗
13. 10.1038/s41571-021-00520-110.1038/s41571-021-00520-1 ↗
14. 10.1038/s41423-020-00577-510.1038/s41423-020-00577-5 ↗
15. 10.1016/j.cell.2024.02.00910.1016/j.cell.2024.02.009 ↗
16. 10.1038/s41588-024-01998-y10.1038/s41588-024-01998-y ↗
17. 10.1002/advs.20241759310.1002/advs.202417593 ↗
18. 10.1016/j.cell.2023.01.03510.1016/j.cell.2023.01.035 ↗
19. 10.1186/s13045-023-01456-y10.1186/s13045-023-01456-y ↗
20. 10.1016/j.semcancer.2022.11.00810.1016/j.semcancer.2022.11.008 ↗
21. 10.1016/S2589-7500(23)00082-110.1016/S2589-7500(23)00082-1 ↗
22. 10.1016/j.semcancer.2022.08.00210.1016/j.semcancer.2022.08.002 ↗
23. 10.1016/S0140-6736(16)00587-010.1016/S0140-6736(16)00587-0 ↗
24. 10.1016/S0140-6736(16)32517-X10.1016/S0140-6736(16)32517-X ↗
25. 10.1016/j.jtho.2021.07.01510.1016/j.jtho.2021.07.015 ↗
26. 10.1214/08-AOAS16910.1214/08-AOAS169 ↗
27. 10.1016/j.ccell.2022.02.00210.1016/j.ccell.2022.02.002 ↗
28. 10.1038/s41571-022-00718-x10.1038/s41571-022-00718-x ↗
29. 10.1016/j.jtho.2022.03.01110.1016/j.jtho.2022.03.011 ↗
30. 10.3389/fimmu.2021.68797510.3389/fimmu.2021.687975 ↗
31. 10.7150/ijbs.6171710.7150/ijbs.61717 ↗
32. 10.1038/s41586-020-03046-110.1038/s41586-020-03046-1 ↗
33. 10.1038/cmi.2017.14310.1038/cmi.2017.143 ↗
34. 10.1136/jitc-2021-00366710.1136/jitc-2021-003667 ↗
35. 10.1093/nar/gky105510.1093/nar/gky1055 ↗
36. 10.1073/pnas.050658010210.1073/pnas.0506580102 ↗
37. 10.1016/j.cels.2015.12.00410.1016/j.cels.2015.12.004 ↗
38. 10.1158/1078-0432.CCR-20-330510.1158/1078-0432.CCR-20-3305 ↗
39. 10.1158/1078-0432.CCR-19-130510.1158/1078-0432.CCR-19-1305 ↗
40. 10.1038/s41467-017-00988-510.1038/s41467-017-00988-5 ↗
41. 10.1016/j.patter.2021.10029310.1016/j.patter.2021.100293 ↗
42. 10.1016/j.cell.2017.12.02610.1016/j.cell.2017.12.026 ↗
43. 10.1158/0008-5472.CAN-22-182110.1158/0008-5472.CAN-22-1821 ↗
44. 10.1007/s13402-022-00694-510.1007/s13402-022-00694-5 ↗
45. 10.1016/j.cmet.2024.05.01310.1016/j.cmet.2024.05.013 ↗
46. 10.1158/2326-6066.CIR-21-012410.1158/2326-6066.CIR-21-0124 ↗
47. 10.1038/s41467-020-16164-110.1038/s41467-020-16164-1 ↗
48. 10.1126/science.aax024910.1126/science.aax0249 ↗
49. 10.1038/s41551-020-00682-w10.1038/s41551-020-00682-w ↗
50. 10.1038/s41467-023-36328-z10.1038/s41467-023-36328-z ↗
51. 10.1038/s41467-023-42972-210.1038/s41467-023-42972-2 ↗
52. 10.1021/jacs.3c0803210.1021/jacs.3c08032 ↗
53. 10.1038/s41422-020-0337-210.1038/s41422-020-0337-2 ↗
54. 10.1200/JCO.19.0093410.1200/JCO.19.00934 ↗
55. 10.1056/NEJMoa150764310.1056/NEJMoa1507643 ↗
56. 10.1038/s41568-019-0116-x10.1038/s41568-019-0116-x ↗
57. 10.1200/JCO.2018.78.227610.1200/JCO.2018.78.2276 ↗
58. 10.1007/s10278-022-00770-010.1007/s10278-022-00770-0 ↗
59. 10.1016/j.isci.2024.11134010.1016/j.isci.2024.111340 ↗
60. 10.1186/s13045-020-01005-x10.1186/s13045-020-01005-x ↗
61. 10.1038/s41576-019-0150-210.1038/s41576-019-0150-2 ↗
62. 10.3389/fonc.2021.62068810.3389/fonc.2021.620688 ↗
63. 10.1038/s41571-019-0175-710.1038/s41571-019-0175-7 ↗
64. 10.1016/j.ccell.2023.02.01610.1016/j.ccell.2023.02.016 ↗
65. 10.1016/j.ccell.2020.10.00110.1016/j.ccell.2020.10.001 ↗
66. 10.1186/s13073-020-00729-210.1186/s13073-020-00729-2 ↗
67. 10.1038/s41568-024-00694-710.1038/s41568-024-00694-7 ↗
68. 10.1001/jamaoncol.2024.535610.1001/jamaoncol.2024.5356 ↗
69. 10.1016/S1470-2045(24)00599-010.1016/S1470-2045(24)00599-0 ↗
70. 10.1016/j.jhep.2022.01.01810.1016/j.jhep.2022.01.018 ↗
71. 10.1038/s41467-024-53374-310.1038/s41467-024-53374-3 ↗
72. 10.1038/nrclinonc.2017.16610.1038/nrclinonc.2017.166 ↗
73. 10.1016/j.ccell.2024.01.01010.1016/j.ccell.2024.01.010 ↗
74. 10.1038/nature2550110.1038/nature25501 ↗
75. 10.1093/bioinformatics/bty56010.1093/bioinformatics/bty560 ↗
76. T. A.Gerds B.Ozenne Publish: F1ormat Output of Various Routines in a Suitable Way for Reports and Publication2021.
77. 10.1016/j.crmeth.2024.10091010.1016/j.crmeth.2024.100910 ↗
78. 10.1089/omi.2011.011810.1089/omi.2011.0118 ↗
79. 10.1093/nar/gkaa111310.1093/nar/gkaa1113 ↗
80. 10.1038/s41587-019-0114-210.1038/s41587-019-0114-2 ↗
81. 10.1186/s13059-016-1070-510.1186/s13059-016-1070-5 ↗
82. 10.1038/ncomms361210.1038/ncomms3612 ↗
83. 10.1186/s13059-017-1349-110.1186/s13059-017-1349-1 ↗
84. 10.1016/j.cell.2021.04.04810.1016/j.cell.2021.04.048 ↗
85. 10.1186/s13059-020-02136-710.1186/s13059-020-02136-7 ↗
86. 10.1186/s13059-020-1950-610.1186/s13059-020-1950-6 ↗
87. 10.12688/f1000research.73600.110.12688/f1000research.73600.1 ↗
88. 10.1186/s13059-019-1874-110.1186/s13059-019-1874-1 ↗
89. 10.1038/s41586-018-0694-x10.1038/s41586-018-0694-x ↗
90. 10.1038/s41467-021-21246-910.1038/s41467-021-21246-9 ↗
91. 10.1038/s41592-019-0667-510.1038/s41592-019-0667-5 ↗
92. 10.1038/s41591-024-02857-310.1038/s41591-024-02857-3 ↗
93. 10.1200/JCO.2017.75.338410.1200/JCO.2017.75.3384 ↗
94. 10.1111/j.2517-6161.1995.tb02031.x10.1111/j.2517-6161.1995.tb02031.x ↗