Skip to content
DraconiticResearch
Search Sources API
182,460 studies31 sourcesUpdated 59 min ago
Peer-reviewedCC BY-NC-NDBMC pulmonary medicine

Machine learning-guided identification of determinants of PD-L1 expression and tumor mutational burden in lung squamous cell carcinoma.

  • Hongwei Shang1
  • Chao Li2
  • Jundong Wang3
  • Dongyun Xu4
  • Kailun Bai5
  • Shuiqing Zhou6
6 affiliations
  1. 1Department of Cardiothoracic Surgery, the People's Liberation Army Joint Logistic, Support Force No 983rd Hospital, Tianjin, 300142, China. [email protected].
  2. 2Department of Cardiothoracic Surgery, the People's Liberation Army Joint Logistic, Support Force No 983rd Hospital, Tianjin, 300142, China.
  3. 3Department of Cardiothoracic Surgery, Dali Bai Autonomous Prefecture People's Hospital, Yunnan Dali, 671099, China.
  4. 4Department of Oncology, Huaihai Hospital Affiliated to Xuzhou Medical University, Jiangsu Xuzhou, 221004, China.
  5. 5University of Victoria, Victoria, Canada.
  6. 6Innovation Research Institute, Zhejiang Univerity of Technology, ShengZhou, China.
Read full textPDFDOICite

Abstract

Background

Programmed death-ligand 1 (PD-L1) expression and tumor mutational burden (TMB) are widely used immunotherapy biomarkers, yet their variability and determinants in lung squamous cell carcinoma (LUSC) remain incompletely characterized in real-world testing settings.Methods

We analyzed a retrospective real-world LUSC cohort with clinical PD-L1 immunohistochemistry and next-generation sequencing. PD-L1 tumor proportion score (TPS) was modeled as an ordered endpoint using three clinically used categories (< 1%, 1-49%, ≥ 50%) via proportional-odds ordinal regression; TMB was modeled as a continuous outcome after log transformation using multivariable linear regression. To address the practical question of whether imperfect real-world biomarker data can still support hypothesis generation, we additionally applied random forest and XGBoost as exploratory tools for prediction-oriented feature prioritization and evaluated uncertainty using repeated resampling and permutation-based perturbation analyses.Results

Regression models provided an interpretable adjusted effect landscape but yielded limited statistically significant associations after adjustment. In contrast, tree-based models prioritized a small subset of clinicogenomic features with predictive information for PD-L1 TPS and TMB variability. Resampling and permutation analyses provided an internal assessment of uncertainty, rank stability, and sensitivity of these feature-prioritization signals.Conclusions

In small, heterogeneous real-world LUSC cohorts where conventional regression-based inference may provide limited resolution, machine learning-guided feature prioritization combined with resampling- and permutation-based uncertainty assessment may help identify candidate clinicogenomic signals associated with PD-L1 TPS category and TMB variability. These findings should be interpreted as hypothesis-generating and require validation in larger independent cohorts.

Related

  1. Identification of Mitochondrial Dynamics-Related Genes as Diagnostic Biomarkers for Osteoarthritis Using Weighted Gene Co-expression Network Analysis and Machine Learning
    Hui Wang, Peng Zhang, Xinqiang Ren +3
    Clinics in orthopedic surgeryPeer-reviewedCC BY-NCFull textSurgery & anaesthesiaEurope PMC
  2. Mutational profiles of hepatocellular carcinoma that arose in outbred mice after heavy-ion particle and γ-ray radiation
    Liang-Hao Ding, Michael D. Story, Shoukath Sulthana +3
    BMC GenomicsPeer-reviewedCC BY-NC-ND 4.0OncologyCrossref
  3. Exploratory clinical-CT machine learning characterization of CK7 expression in clear cell renal cell carcinoma
    Qiansen Lin, Gengyun Miao, Xi Jia +5
    BMC CancerPeer-reviewedCC BYFull textMedical imaging & radiologyDOAJ
  4. Deep Learning-Based Inference of Mutational Signature Exposures from Histology Across Tumour Types
    Byeong Chang Sim, JunSik Kim, Jiyeon Park +5
    CancersPeer-reviewedCC BY 4.0OncologyCrossref
  5. Identification of candidate selenium-associated transcriptomic biomarkers in chronic obstructive pulmonary disease: an integrated bioinformatics and expression validation study
    Yang Li, Zhuxiu Jiang, Zhibo Xu +3
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{shang2026machine,
  title = {{Machine learning-guided identification of determinants of PD-L1 expression and tumor mutational burden in lung squamous cell carcinoma.}},
  author = {Hongwei Shang and Chao Li and Jundong Wang and Dongyun Xu and Kailun Bai and Shuiqing Zhou},
  journal = {BMC pulmonary medicine},
  year = {2026},
  month = jul,
  doi = {10.1186/s12890-026-04554-y},
  url = {https://europepmc.org/article/MED/42958183},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - Machine learning-guided identification of determinants of PD-L1 expression and tumor mutational burden in lung squamous cell carcinoma.
AU  - Hongwei Shang
AU  - Chao Li
AU  - Jundong Wang
AU  - Dongyun Xu
AU  - Kailun Bai
AU  - Shuiqing Zhou
PY  - 2026
DA  - 2026/07/31
JO  - BMC pulmonary medicine
DO  - 10.1186/s12890-026-04554-y
UR  - https://europepmc.org/article/MED/42958183
AB  - Background  Programmed death-ligand 1 (PD-L1) expression and tumor mutational burden (TMB) are widely used immunotherapy biomarkers, yet their variability and determinants in lung squamous cell carcinoma (LUSC) remain incompletely characterized in real-world testing settings.Methods  We analyzed a retrospective real-world LUSC cohort with clinical PD-L1 immunohistochemistry and next-generation sequencing. PD-L1 tumor proportion score (TPS) was modeled as an ordered endpoint using three clinically used categories (< 1%, 1-49%, ≥ 50%) via proportional-odds ordinal regression; TMB was modeled as a continuous outcome after log transformation using multivariable linear regression. To address the practical question of whether imperfect real-world biomarker data can still support hypothesis generation, we additionally applied random forest and XGBoost as exploratory tools for prediction-oriented feature prioritization and evaluated uncertainty using repeated resampling and permutation-based perturbation analyses.Results  Regression models provided an interpretable adjusted effect landscape but yielded limited statistically significant associations after adjustment. In contrast, tree-based models prioritized a small subset of clinicogenomic features with predictive information for PD-L1 TPS and TMB variability. Resampling and permutation analyses provided an internal assessment of uncertainty, rank stability, and sensitivity of these feature-prioritization signals.Conclusions  In small, heterogeneous real-world LUSC cohorts where conventional regression-based inference may provide limited resolution, machine learning-guided feature prioritization combined with resampling- and permutation-based uncertainty assessment may help identify candidate clinicogenomic signals associated with PD-L1 TPS category and TMB variability. These findings should be interpreted as hypothesis-generating and require validation in larger independent cohorts.
SN  - 1471-2466
ER  -