Using SVM to Identify Key Genes in Mouse Embryonic Stem Cells
Author Information
Author(s): Xu Huilei, Lemischka Ihor R, Ma'ayan Avi
Primary Institution: Mount Sinai School of Medicine
Hypothesis
We can utilize data from mESCs-related mRNA microarrays profiling and genome-wide transcription factor binding profiling (ChIP-seq) to classify genes important for ES cell self-renewal and pluripotency (MSMGs).
Conclusion
The SVM approach can effectively prioritize genes for functional validation experiments in stem cell research.
Supporting Evidence
- The SVM classifier outperformed other classification methods in predicting MSMGs.
- Combining heterogeneous data types improved the accuracy of the SVM classifier.
- The classifier was able to prioritize candidate genes from genome-wide RNAi screens.
Takeaway
Scientists used a computer program to find important genes in mouse stem cells that help them grow and stay the same. This can help in future experiments.
Methodology
The study developed a classifier using support vector machines (SVM) trained on gene expression data from mESCs and ChIP-seq data.
Potential Biases
The study may have misclassified some genes due to the inherent noise in RNAi screens.
Limitations
The training sample for positive genes is relatively small since controversial candidates were discarded.
Participant Demographics
Mouse embryonic stem cells were used in the study.
Statistical Information
P-Value
5.34 × 10-12
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website