A Multi-Label Classifier for Predicting the Subcellular Localization of Gram-Negative Bacterial Proteins with Both Single and Multiple Sites
2011

Predicting Protein Subcellular Localization in Bacteria

Sample size: 1392 publication 10 minutes Evidence: high

Author Information

Author(s): Xiao Xuan, Wu Zhi-Cheng, Chou Kuo-Chen

Primary Institution: Computer Department, Jing-De-Zhen Ceramic Institute, Jing-De-Zhen, China

Hypothesis

Can a new predictor improve the accuracy of protein subcellular localization predictions for Gram-negative bacteria?

Conclusion

The iLoc-Gneg predictor achieved an overall success rate of over 91.4%, outperforming previous methods.

Supporting Evidence

  • The iLoc-Gneg predictor outperformed Gneg-mPLoc by about 6%.
  • The dataset used contained 1,392 Gram-negative bacterial proteins.
  • The overall success rate of iLoc-Gneg was over 91.4%.

Takeaway

Scientists created a tool to help figure out where proteins are located inside bacteria, and it works really well!

Methodology

The study developed a multi-label KNN classifier using a benchmark dataset of 1,392 Gram-negative bacterial proteins to predict their subcellular locations.

Potential Biases

Potential bias from the dataset if proteins with high sequence similarity are included.

Limitations

The predictor may not perform well if the query protein is not among the eight specified locations.

Participant Demographics

The study focused on Gram-negative bacterial proteins.

Statistical Information

P-Value

0.0001

Confidence Interval

not provided

Statistical Significance

p<0.05

Digital Object Identifier (DOI)

10.1371/journal.pone.0020592

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication