Metagenomic Fingerprints in Bronchoalveolar Lavage Differentiate Pulmonary Diseases

Researchers from Zhejiang University School of Medicine in Hangzhou, People's Republic of China, have made a groundbreaking discovery in the field of oncology, specifically in the area of lung cancer research. By analyzing 402 bronchoalveolar lavage fluid (BALF) metagenomic next-generation sequencing (mNGS) datasets, the team developed a multimodal machine learning-based diagnostic approach to differentiate lung cancer and pulmonary infections. Their research reveals significant differences in microbial profiles, bacteriophage abundance, host gene and transposable element expression, immune cell composition, and tumor fraction derived from copy number variation (CNV).

Key Takeaways:

  • The researchers analyzed 402 BALF mNGS datasets, including lung cancer (n = 123), bacterial infections (n = 114), fungal infections (n = 79), and pulmonary tuberculosis (n = 86).
  • The integrated model (Model VI) achieved an AUC of 0.937 (95% CI, 0.910-0.964) in the training cohort and 0.847 (95% CI, 0.776-0.918) in the test cohort.
  • A rule-in/rule-out strategy further improved accuracy in differentiating lung cancer from tuberculosis (accuracy = 0.896), fungal (accuracy = 0.915), and bacterial (accuracy = 0.907) infections.
  • The research concluded that metagenomic fingerprints in bronchoalveolar lavage can differentiate pulmonary diseases, highlighting the potential of mNGS-based multimodal analysis as a cost-effective tool for early and accurate differential diagnosis.
  • The study was led by Dongsheng Han, Dept. of Laboratory Medicine, First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, People's Republic of China.

Sources:

  • Metagenomic fingerprints in bronchoalveolar lavage differentiate pulmonary diseases. npj Digital Medicine, 2025;8(1):599.
  • NewsRx. Findings on Lung Cancer Detailed by Researchers at Zhejiang University School of Medicine (Metagenomic fingerprints in bronchoalveolar lavage differentiate pulmonary diseases). TB & Outbreaks Week. October 21, 2025; p 1828.

Statistics:

  • 402 BALF mNGS datasets analyzed in the study
  • AUC of 0.937 (95% CI, 0.910-0.964) in the training cohort and 0.847 (95% CI, 0.776-0.918) in the test cohort for Model VI
  • Accuracy of 0.896 in differentiating lung cancer from tuberculosis, 0.915 in differentiating lung cancer from fungal infections, and 0.907 in differentiating lung cancer from bacterial infections using a rule-in/rule-out strategy.