# Systematic analysis reveals key microRNAs as diagnostic and prognostic factors in progressive stages of lung cancer

**Authors:** Dietrich Kong, Ke Wang, Qiu-Ning Zhang, Zhi-Tong Bing  
**arXiv:** [2201.05408](https://arxiv.org/abs/2201.05408)  
**Date:** 2022-01-14  
**Summary page:** https://www.summarizepaper.com/en/paper/2201.05408v1/

## Key points

- MicroRNAs play a crucial role in tumor development and are potential biomarkers in lung cancer pathology.
- The study focused on lung adenocarcinoma (LUAD) and analyzed the impact of microRNAs on diagnostic and prognostic factors at different stages of the disease.
- Dimension reduction techniques and unsupervised hierarchical clustering were used to identify unique expression patterns of microRNAs associated with diagnostic factors.
- A classification framework called Light Gradient Boosting Machine (LightGBM) along with the SHAPley Additive explanation (SHAP) algorithm was developed to identify prognostic factors.
- Enrichment analyses revealed that both diagnostic and prognostic factors were enriched in cancer-related pathways, cellular signaling transduction, and immune responses.
- Five specific microRNAs - hsa-mir-196b, hsa-mir-31, hsa-mir-891a, hsa-mir-34c, and hsa-mir-653 - showed potential as both diagnostic factors and prognostic tools for monitoring lung cancer.
- These findings provide valuable insights into the role of microRNAs in lung cancer progression and their clinical significance for diagnosis and prognosis.

## Summary

In the study titled "Systematic analysis reveals key microRNAs as diagnostic and prognostic factors in progressive stages of lung cancer," authors Dietrich Kong, Ke Wang, Qiu-Ning Zhang, and Zhi-Tong Bing investigated the role of microRNAs in lung cancer progression. MicroRNAs are known to play a crucial role in various biological processes, including tumor development. However, their specific functions as biomarkers in cancer pathology remain unclear. The researchers focused on lung adenocarcinoma (LUAD) as a prototype case and integrated clinical information with transcript expression data to analyze the impact of microRNAs on diagnostic and prognostic factors at different stages of the disease. They employed dimension reduction techniques followed by unsupervised hierarchical clustering to identify unique expression patterns of microRNAs associated with diagnostic factors at various patient stages. To identify prognostic factors, the authors developed a classification framework called Light Gradient Boosting Machine (LightGBM) along with the SHAPley Additive explanation (SHAP) algorithm. This framework allowed them to screen for microRNAs that could serve as prognostic tools for monitoring lung cancer. Enrichment analyses revealed that both diagnostic and prognostic factors were enriched not only in cancer-related pathways but also involved essential cellular signaling transduction and immune responses. Furthermore, these key microRNAs were found to influence the survival risk of LUAD patients across all or specific stages. Some of these microRNAs even targeted important Transcription Factors (TF). The study identified five specific microRNAs - hsa-mir-196b, hsa-mir-31, hsa-mir-891a, hsa-mir-34c, and hsa-mir-653 - which showed potential as both diagnostic factors and prognostic tools for monitoring lung cancer. These findings provide valuable insights into the role of microRNAs in lung cancer progression and emphasize their potential clinical significance for diagnosis and prognosis of the disease. Overall, this systematic analysis expands our understanding of the diagnostic and prognostic factors associated with microRNAs in lung cancer. The identified microRNAs hold promise as potential biomarkers for monitoring disease progression and may contribute to improved patient outcomes in the future.