Related Experiment Video
Updated: Aug 6, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
6.9K
Machine learning based combination of multi-omics data for subgroup identification in non-small cell lung cancer
Seema Khadirnaikar1, Sudhanshu Shukla2, S R M Prasanna1
1Department of Electrical Engineering, Indian Institute of Technology Dharwad, Dharwad, India.
Scientific Reports
|March 22, 2023
Summary
Machine learning identified five novel Non-small Cell Lung Cancer (NSCLC) subtypes. These subtypes show distinct molecular and clinical features, improving patient classification and prognosis prediction.
Area of Science:
- Oncology
- Bioinformatics
- Computational Biology
Background:
- Non-small Cell Lung Cancer (NSCLC) is a complex disease with varied patient outcomes.
- Identifying distinct molecular subtypes is crucial for personalized treatment strategies.
Purpose of the Study:
- To develop an end-to-end pipeline for identifying novel molecular subtypes in NSCLC.
- To classify NSCLC patients into distinct subgroups based on multi-omics data.
Main Methods:
- A machine learning (ML) approach was used to reduce dimensionality of multi-omics NSCLC data.
- Consensus K-means clustering identified five novel patient clusters (C1-C5).
- Survival analysis and molecular characterization were performed on identified clusters.
Main Results:
- Five novel NSCLC clusters (C1-C5) were identified with significant differences in overall survival (p=0.019).
- Cluster C3 exhibited minimal genetic aberrations and a favorable prognosis.
- Multi-omics-based classification models outperformed single-omic models for predicting patient subgroups.
Conclusions:
- The developed ML pipeline successfully identified five novel NSCLC clusters with distinct genetic and clinical characteristics.
- This classification method enhances the understanding of NSCLC heterogeneity.
- The findings support improved patient stratification and potentially personalized therapeutic approaches in NSCLC.
