Inferring Pathway Activity for Disease Classification
Author Information
Author(s): Lee Eunjung, Chuang Han-Yu, Kim Jong-Won, Ideker Trey, Lee Doheon
Primary Institution: KAIST, Daejeon, South Korea
Hypothesis
Can pathway information improve disease classification based on gene expression profiles?
Conclusion
Incorporating pathway information into disease classification improves accuracy and provides biologically meaningful insights.
Supporting Evidence
- Pathway-based classifiers outperformed conventional gene-based classifiers in distinguishing disease phenotypes.
- Condition-responsive genes (CORGs) were identified to enhance the discriminative power of pathway activities.
- Pathway markers provided biologically informative models for lung cancer prognosis.
Takeaway
This study shows that looking at groups of genes working together in pathways helps doctors better understand and classify diseases like cancer.
Methodology
The study used mRNA expression datasets from various cancer types to identify condition-responsive genes and infer pathway activities for classification.
Potential Biases
Potential biases may arise from the selection of datasets and the methods used for pathway identification.
Limitations
The study may not account for all genetic variations and complexities in different patient populations.
Participant Demographics
The study included various cancer patients, including those with prostate cancer, breast cancer, and lung cancer.
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website