Predicting protein disorder by analyzing amino acid sequence
2008
Predicting Protein Disorder from Amino Acid Sequences
publication
Evidence: moderate
Author Information
Author(s): Yang Jack Y, Yang Mary Qu
Primary Institution: Harvard Medical School
Hypothesis
Can machine learning algorithms effectively predict intrinsically unstructured proteins (IUP) from amino acid sequences?
Conclusion
The IUP predictor is a viable alternative software tool for identifying IUP protein regions and proteins.
Supporting Evidence
- The study found that using features based on physiochemical properties improved prediction accuracy.
- The IUP predictor performed comparably to existing predictors like PONDR.
Takeaway
This study created a tool to help find proteins that don't fold into specific shapes, which is important for understanding how they work.
Methodology
The study developed machine learning algorithms to extract features from amino acid sequences and compared the performance of their IUP predictor with existing tools.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website