Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Predicting Transcriptional Activity of Multiple Site p53 Mutants Based on Hybrid Properties

Figure 1

The IFS curves for one-site, two-site, three-site and four-site p53 mutants.

In the IFS curve, the x-axis is the number of features used for classification, and the y-axis is the Mathew's correlation coefficients (MCC) generated by the jackknife test. (A) The IFS curve for one-site p53 mutants. The peak of MCC is 0.678 with 8 features. The top 8 features derived by the mRMR approach form the optimal feature set for one-site p53 mutants. (B) The IFS curve for two-site p53 mutants. The peak of MCC is 0.314 with 50 features. The top 50 features derived by the mRMR approach form the optimal feature set for two-site p53 mutants. (C) The IFS curve for three-site p53 mutants. The peak of MCC is 0.705 with 282 features. The top 282 features derived from the mRMR approach form the optimal feature set for three-site p53 mutants. (D) The IFS curve for four-site p53 mutants. The peak of MCC is 0.907 with 25 features. The top 25 features derived from the mRMR approach form the optimal feature set for four-site p53 mutants.

Figure 1

doi: https://doi.org/10.1371/journal.pone.0022940.g001