Analyzing Signaling Networks with Isomap
Author Information
Author(s): Ivakhno Sergii, Armstrong J Douglas
Primary Institution: Massachusetts Institute of Technology
Hypothesis
Can non-linear dimensionality reduction techniques like Isomap effectively identify clusters in signaling networks?
Conclusion
The extended Isomap approach successfully identified clusters in signaling networks corresponding to different treatment conditions.
Supporting Evidence
- Isomap was able to reconstruct clusters corresponding to different cytokine treatments.
- Isomap outperformed PCA in identifying functionally coherent clusters.
- The first three Isomap components captured 71% of the variance in the data.
Takeaway
This study used a special math tool called Isomap to help understand how different signals in cells can lead to different responses, like whether a cell lives or dies.
Methodology
The study applied an unsupervised non-linear dimensionality reduction approach, Isomap, to analyze two cell signaling networks.
Limitations
Isomap struggled to identify clusters for low-dose treatments, which formed a supercluster.
Participant Demographics
The study involved human epithelial cancer cells and RAW 264.7 macrophages.
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