Machine learning-enabled spatial multi-omics uncovers lactate-driven targets and tumor microenvironmental reprogramming in cancer - Summary - MDSpire

Machine learning-enabled spatial multi-omics uncovers lactate-driven targets and tumor microenvironmental reprogramming in cancer

  • By

  • Yingzheng Tan

  • Wenliang Tan

  • Yanchao Liang

  • Yunzhu Long

  • Shuanghua Chen

  • Qihao Hu

  • Yangjing Ou

  • Jingli Fu

  • Huan Chen

  • Fangyuan Ren

  • Jun Ye

  • Qing Zhou

  • Sheng Li

  • Xiaojin He

  • Qianqian Wang

  • Yueming Shen

  • Haiyuan Lu

  • Daichao Wu

  • Anbo Gao

  • Xun Chen

  • Yukun Li

  • December 30, 2025

  • 0 min

Share

Objective:

To investigate how lactate heterogeneity shapes the tumor microenvironment specifically in lung adenocarcinoma (LUAD) and identify potential therapeutic targets.

Key Findings:
  • High-lactate tumors showed increased epithelial and fibroblast abundances, while low-lactate samples were enriched in T/NK cells and monocytes/macrophages, indicating a shift in immune landscape.
  • Spatial metabolomics revealed distinct lactate and pyruvate distributions, with minimal lactate accumulation in endothelial cells, suggesting targeted areas for intervention.
  • Endothelial subclusters in high-lactate tissues exhibited angiogenic and stress-response signatures linked to poor prognosis, highlighting potential biomarkers.
  • Machine learning models identified endothelial and fibroblast programs as key determinants of high-lactate states and adverse clinical outcomes, underscoring their role in tumor progression.
Interpretation:

Lactate accumulation reprograms the LUAD microenvironment, promoting angiogenesis and immune suppression, which can inform therapeutic strategies targeting lactate-driven pathways for improved patient outcomes.

Limitations:
  • Study based on a limited number of patient samples (n = 3 per group), which may restrict the robustness of the findings.
  • Findings may not be generalizable to all LUAD cases due to heterogeneity, necessitating further validation in larger cohorts.
Conclusion:

Lactate-driven metabolic reprogramming significantly influences the LUAD microenvironment, highlighting the potential for lactate-centered therapeutic interventions.

Original Source(s)

Machine learning-enabled spatial multi-omics uncovers lactate-driven targets and tumor microenvironmental reprogramming in cancer

  • by Yingzheng Tan, Wenliang Tan, Yanchao Liang, Yunzhu Long, Shuanghua Chen, Qihao Hu, Yangjing Ou, Jingli Fu, Huan Chen, Fangyuan Ren, Jun Ye, Qing Zhou, Sheng Li, Xiaojin He, Qianqian Wang, Yueming Shen, Haiyuan Lu, Daichao Wu, Anbo Gao, Xun Chen, Yukun Li

  • December 30, 2025

Related Content

Metagenomic fingerprints in bronchoalveolar lavage differentiate pulmonary diseases

Barriers and Variations in Cancer Diagnosis: A Cross-Sectional Analysis of Patient Journeys and Healthcare Provider Timelines in Public Health Systems of Chile, Colombia, and Ecuador

Worldwide Impact of Respiratory Cancers in 2022 and Projections for 2050: Incidence and Mortality Data from GLOBOCAN