PNAC: a protein nucleolar association classifier
2011

PNAC: a protein nucleolar association classifier

Sample size: 200 publication 10 minutes Evidence: moderate

Author Information

Author(s): Scott Michelle S, Boisvert François-Michel, Lamond Angus I, Barton Geoffrey J

Primary Institution: University of Dundee

Hypothesis

Can a computational method classify the degree of nucleolar association of human proteins?

Conclusion

The study provides a novel classification of nucleolar-associated proteins, enhancing our understanding of the nucleolus's role in cellular processes.

Supporting Evidence

  • The classifier achieved an overall accuracy of 0.85 on an independent literature-based test set.
  • Leave-one-out cross-validation tests revealed sensitivity values for the four classes ranging from 0.72 to 0.90.
  • The study identified thousands of human proteins that associate with the nucleolus.

Takeaway

This study created a tool to help scientists understand which proteins are found in the nucleolus, a part of the cell that makes ribosomes.

Methodology

The study used a probabilistic predictor trained on a curated dataset of nucleolar proteins to classify human proteins into four categories based on their nucleolar association.

Potential Biases

Potential bias due to reliance on manually curated datasets and the limited scope of tested conditions.

Limitations

The classifier's accuracy may be affected by the limited number of proteins and conditions examined.

Statistical Information

P-Value

0.05

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1186/1471-2164-12-74

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication