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

Gene Characterization Index: Assessing the Depth of Gene Annotation

Figure 1

GCI Model Cross-validation Performance.

GCI Predictor Performance–Leave-One-Out cross-validation results for the final GCI predictor model utilizing the MARS method on z-score normalized data. The X-axis displays average evaluator assigned scores, while the Y-axis displays the predicted scores for each gene in the leave-one-out cross validation analysis (the score assigned when the gene was not included in the training data). As observed, the MARS model can assign scores greater than 10 (in all further analysis such scores are rounded down to 10).

Figure 1