Metrics

NS Nicolas Scalzitti
AK Arnaud Kress
RO Romain Orhand
TW Thomas Weber
LM Luc Moulinier
AJ Anne Jeannin-Girardon
PC Pierre Collet
OP Olivier Poch
JT Julie D. Thompson
request Request a Protocol
ask Ask a question
Favorite

SS are considered as true positives (TP) if they are correctly predicted and false positives (FP) otherwise. Nucleotides that do not correspond to a SS are considered as True Negatives (TN) if they are not predicted to be SS and False Negatives (FN) otherwise. To evaluate the performance of the CNN models, five metrics were used:

Accuracy is the ratio of the number of correct predictions to the total number of predictions:

Precision is the ratio of the number of correctly predicted SS to the total number of predicted SS:

Sensitivity (also known as recall) is the ratio of the number of correctly predicted SS to the total number of SS:

Specificity is the ratio of the number of correctly predicted non-SS sequences to the total number of non-SS sequences:

F1 Score is the harmonic mean of the precision and sensitivity and shows a balance between these two metrics:

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

post Post a Question
0 Q&A