Sentence examples for performance of these predictions from inspiring English sources

We applied the same approach to murine TAP by averaging the score of precursor peptides up to a maximal extension Nmax, and assigning a weighting factor α. We tested the performance of these predictions on the same dataset used in Figure 5 for varying values of Nmax and α.

The performance of these predictions was assessed using the area under the receiver operating curve (AUC-ROC), a metric that quantifies the ability of a method to predict positive examples which, in our case, is phase specific expression.

Several methods for predicting TFBS exist, but there are no standard genome-wide datasets on which to assess the performance of these prediction methods.

The performances of these predictions were evaluated using the Brier score [ 15] and the area under the curve estimate (AUC).

Performances of these prediction models were evaluated in the validation set.

We used our context++ model to overhaul the TargetScan predictions (as described in the next section), and as a third way of testing this model, we compared the performance of these TargetScan7 predictions with that of in vivo CLIP experiments.

We assessed the performance of the predictions using a repeated hold-out scheme.

We use the union set (1,297 proteins) for verifying the performance of the predictions.

A more rigorous prediction performance of these predictors should thus be further evaluated using a third patient set from the same cell type of leukocytes.

The use of high-sensitivity gene expression profiling technologies such as the reverse transcription polymerase chain reaction, in addition to be cheaper and more user friendly, might improve the performance of these risk prediction models.

Cross-validation, using a 10% sample hold-out set, was used in the training set to estimate the performance of the prediction classifiers generated using these approaches [ 18].