NoD: A Tool for Detecting Nucleolar Localization Sequences in Proteins
Author Information
Author(s): Scott Michelle S, Troshin Peter V, Barton Geoffrey J
Primary Institution: University of Dundee
Hypothesis
Can a web server and command line program effectively predict nucleolar localization sequences in proteins?
Conclusion
NoD is the first tool to provide predictions of nucleolar localization sequences in diverse eukaryotes and viruses.
Supporting Evidence
- The NoD sensitivity and positive predictive value were estimated to be 71% and 79%, respectively.
- NoD can be run interactively online or downloaded for local use.
- The command line version of NoD is suitable for processing multiple sequences.
Takeaway
NoD is a computer program that helps scientists find special signals in proteins that tell them to go to a part of the cell called the nucleolus.
Methodology
The NoD web server uses a human-trained artificial neural network to predict nucleolar localization sequences based on protein sequences.
Potential Biases
The training dataset may not fully represent the diversity of nucleolar localization sequences across all species.
Limitations
The predictor was primarily trained on human sequences, which may limit its accuracy for other organisms.
Participant Demographics
The study focused on eukaryotic and viral proteins, particularly those from humans and other mammals.
Statistical Information
P-Value
0.71
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website