Sentence examples for predictions were converted from inspiring English sources

For the purpose of evaluating screening libraries the quantitative model predictions were converted into permeable/impermeable categories leading to a success rate of ~80%%.

In case of cons-PPISP, which returns a set of clusters, the predictions were converted to a score based on the cluster rank, rather than the confidence score provided for each cluster (see Text S1).

All predictions were converted to FASTA-format and searched for at least 30 nt long hits with 100% identity to candidate sequences.

These point predictions were converted to continuous scores using a 1000 base pair window, with the central 200 base pairs getting the full score, linearly falling to 0 at the edges, giving a trapezoid-type distribution.

The four-state predictions were converted to percentage composition values in order to minimize the effects due to differences in length across the sequences as suggested by Wise [ 12].

The structural capacity of HFC section stud found from the design rule predictions was converted into load ratio which is the ratio between the structural capacities under fire and ambient conditions, and the load ratio versus FRR curve were produced for different LSF walls.

Output of these predictions was converted to tab delimited files and thereafter to plots for visualization.

To mitigate against potential scale effects that could lead to spurious relationships, all predictions are converted to a common scale prior to analysis.

The problem of trend prediction is converted to a binary classification problem where the objective is to detect the directions of the targeted trends (in our case, crime trends).

Prediction scores were converted to integer values, by simply taking the rank of the score within the protein chain (except for SPPIDER).

Mean prediction accuracies were converted to d-prime using: d - prime = 2 ∗ erfinv (2 ∗ accuracy - 1 ) ; erfinv, inverse error function.