PIPE: A Tool for Predicting Protein Interactions
Author Information
Author(s): Pitre Sylvain, Dehne Frank, Chan Albert, Cheetham Jim, Duong Alex, Emili Andrew, Gebbia Marinella, Greenblatt Jack, Jessulat Mathew, Krogan Nevan, Luo Xuemei, Golshani Ashkan
Primary Institution: School of Computer Science, Carleton University, Ottawa, Canada
Hypothesis
Can novel protein-protein interactions be successfully predicted from amino acid sequences alone?
Conclusion
PIPE can predict yeast protein-protein interactions and study the internal architecture of yeast protein complexes.
Supporting Evidence
- PIPE showed a sensitivity of 61% for detecting yeast protein interactions.
- The specificity of PIPE was found to be 89%.
- PIPE identified a novel interaction between YGL227W and YMR135C.
- The overall accuracy of PIPE was reported as 75%.
- PIPE can analyze proteins that TAP tagging fails to identify.
Takeaway
PIPE is a computer program that helps scientists figure out how proteins in yeast interact with each other just by looking at their building blocks, called amino acids.
Methodology
PIPE uses the primary structure of proteins and known interaction data to predict interactions between yeast proteins.
Potential Biases
The algorithm may produce false positives due to frequent motifs in the dataset.
Limitations
PIPE may struggle to detect novel interactions in large datasets and has a high number of false positives compared to true positives.
Participant Demographics
Yeast proteins from Saccharomyces cerevisiae.
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