Predicting Membrane Anchors in Proteins
Author Information
Author(s): Nicolas Sapay, Yann Guermeur, Gilbert Deléage
Primary Institution: Institut de Biologie et Chimie des Protéines, UMR 5086 CNRS-Univ. Lyon 1
Hypothesis
Can a Support Vector Machine (SVM) classifier effectively predict in-plane membrane anchors in monotopic proteins?
Conclusion
The AmphipaSeeK method is highly specific for predicting in-plane membrane anchors in monotopic proteins.
Supporting Evidence
- The method was tested on a dataset of 91 sequences, which is the most exhaustive database of IPM anchored proteins to date.
- AmphipaSeeK was shown to be highly specific compared to traditional methods.
- The method successfully retrieved IPM anchors in known membrane proteins.
Takeaway
Scientists created a computer program that helps find special parts of proteins that stick to cell membranes.
Methodology
The study used a Support Vector Machine (SVM) classifier trained on a dataset of 21 experimentally characterized monotopic proteins to predict in-plane membrane anchors.
Limitations
The method's sensitivity is low due to the imbalance between IPM and non-IPM residues, and it cannot be readily compared with other methods due to the lack of publicly available algorithms.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website