Like in DawnRank, we evaluated all non-synonymous mutations and evaluated each method using precision-recall metrics in comparison to CGC.
When inclusion cutoffs are relaxed, or iterated methods are used, recall improves, but precision often degrades, including many sequences with only partial (local) homology to the query.
To evaluate the performance of the detection and tracking method for emotional expressions, we use recall and precision as the performance measures.
For machine learning methods evaluation three parameters were used: recall – R (1), precision – P (2), and the Matthews Correlation Coefficient – MCC (3): R = TP TP + FN (1) P = TP TP + FP (2) MCC = TP · TN − FP · FN TP + FP · TP + FN · TN + FP · TN + FN (3).
On the other hand, the proposed method fails to exceed the ARTS method when using area under precision recall curve.
For this group of test data, the performance of a given stereo matching method was measured using precision, recall and running time.
Assessment of the model was carried out using four indices, area under curve (AUC), precision, modified precision, and recall (detailed in Methods), using 10 fold cross validation on the training set data.
Table 1 Precision (P), Recall (R) and F-measure (F) estimates for each method used, using cross-validation, for the Chemical Documents Indexing task (CDI) and Chemical Entity Mention task (CEM).
COED and baseline methods are compared using precision, recall, and F1 score.
For task (b) using -omics data, CliXO outperforms other methods using two -omics datasets and achieves ∼30% precision and recall using YeastNet v3, similar to an earlier approach (Network Extracted Ontology) and better than LocalFitness or standard clustering (20 25% precision, recall).
