NR-2L: A Two-Level Predictor for Identifying Nuclear Receptor Subfamilies
Author Information
Author(s): Wang Pu, Xiao Xuan, Chou Kuo-Chen
Primary Institution: Computer Department, Jing-De-Zhen Ceramic Institute, Jing-De-Zhen, China
Hypothesis
Can a two-level predictor effectively identify nuclear receptors and their subfamilies based on sequence-derived features?
Conclusion
The NR-2L predictor demonstrates high success rates in identifying nuclear receptors and their subfamilies, making it a valuable tool for research and drug development.
Supporting Evidence
- The NR-2L predictor achieved success rates of about 93% and 89% in identifying nuclear receptors and their subfamilies, respectively.
- The predictor was developed to address shortcomings of existing methods that failed to accurately identify nuclear receptors.
- A user-friendly web server for NR-2L is freely accessible for researchers to use.
Takeaway
Scientists created a tool called NR-2L that helps identify important proteins in our bodies based on their sequences, which can help in developing new medicines.
Methodology
The study developed a two-level predictor using a fuzzy K nearest neighbor classifier based on various sequence-derived features.
Potential Biases
Potential bias due to the redundancy cutoff in the training datasets.
Limitations
The predictor's effectiveness may be limited by the quality and diversity of the training datasets.
Statistical Information
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website