2.4. Performance Evaluation Metrics
This protocol is extracted from research article:
iBLP: An XGBoost-Based Predictor for Identifying Bioluminescent Proteins
Comput Math Methods Med, Jan 7, 2021; DOI: 10.1155/2021/6664362

How to objectively evaluate the predictor quality is a key point for developing a powerful predictor and estimating its potential application value for BLP prediction. Thus, the following metrics [4346], sensitivity (Sn), specificity (Sp), overall accuracy (Acc), and Matthew's correlation coefficient (MCC), are used in our work and can be, respectively, calculated as follows:

where TP, TN, FP, and FN indicate the true positives (i.e., correctly predicted as BLPs), true negatives (i.e., correctly predicted as non-BLPs), false positives (i.e., incorrectly predicted as BLPs), and false negatives (i.e., incorrectly predicted as non-BLPs), respectively. The higher the value of Acc, Sn, and Sp are, the more robust the predictor is. Moreover, a value of MCC = 1 indicates the best possible prediction while MCC = −1 indicates the worst possible prediction (or anticorrelation). MCC = 0 would be expected for a random prediction scheme.

Additionally, the receiver operating characteristic (ROC) curve [4749] can present the model behavior of the true positive rate (TPR = sensitivity) against the false positive rate (FPR = 1 − specificity) in a visual way. The area under the ROC (AUC) is also used as performance evaluation metric in this study which can quantitatively and objectively measure the performance of the proposed method. A perfect predictor is proved to have the value of AUC = 1, and the random performance is proved to have the value of AUC = 0.5.

Note: The content above has been extracted from a research article, so it may not display correctly.

Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.

We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.