Sign in Subscribe
Autoimmune diseases

Gut Microbiota Analysis Reveals Microbial Signature for Multi-Autoimmune Diseases Based on Machine Learning Model

Strategic Insights

— 1 min read

A recent study published in Frontiers in Microbiology has provided new insights into the relationship between gut microbiota and autoimmunity. Researchers from Nankai University analyzed 1,954 gut microbiota sequencing datasets from public databases collected from 1,043 patients with 10 different autoimmune diseases (AIDs). The study aimed to identify common or unique microbial signatures for AIDs using differential abundance testing and machine learning techniques. The team evaluated five popular machine learning algorithms and found that the XGBoost model showed superior performance in predicting different diseases, achieving an area under the receiver operating characteristic curve (AUROC) ranging from 0.75 to 0.99.

Key Takeaways:

  • The study analyzed 1,954 gut microbiota sequencing datasets from public databases collected from 1,043 patients with 10 different autoimmune diseases.
  • The researchers evaluated five popular machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Multilayer Perceptron (MLP), and eXtreme Gradient Boosting (XGBoost) models.
  • The XGBoost model showed superior performance, achieving an AUROC ranging from 0.75 to 0.99 when predicting different diseases.
  • The study identified 126 significant associations between the top 77 microbiota genera and disease phenotypes, after correcting for false discovery rate (FDR).
  • The research provides important clues for understanding the characteristics of the intestinal immune microenvironment for different AIDs.
  • The study's findings suggest that gut microbiota analysis has the potential to be used as a non-invasive method for disease diagnosis.
  • The research team included Shuya Zhang, Tianfeng An, Jinjin Li, Hui Wang, Li Chen, Yiran Shi, Jingyi Wang, Sirui Han, Ruoxi Wang, Linyuan Wang, Zijing Huan, Ruiqi Yang, Desong Hao, Yanfang Liu, Xuehua Liu, and Chao Yuan.

Statistics:

  • 1,954 gut microbiota sequencing datasets were analyzed in the study.
  • The datasets were collected from 1,043 patients with 10 different autoimmune diseases.
  • The XGBoost model achieved an AUROC ranging from 0.75 to 0.99 when predicting different diseases.
  • 126 significant associations were identified between the top 77 microbiota genera and disease phenotypes, after correcting for false discovery rate (FDR).

Sources:

  • Frontiers in Microbiology (2025;16:1660775)
  • Shuya Zhang et al. (2025). Gut microbiota analysis reveals microbial signature for multi-autoimmune diseases based on machine learning model. Frontiers in Microbiology, 16, 1660775.
  • Nankai University (Tianjin, People's Republic of China)

Read more