miRAW: A deep learning-based approach to predict microRNA targets by analyzing whole microRNA transcripts
Fig 9
Performance of miRAW in relation to ΔGopen filtering threshold.
(a) Variation in accuracy with respect to ΔGopen filtering threshold. (b) Variation in positive F1-score with respect to ΔGopen filtering threshold. (c) Variation in negative F1-score with respect ΔGopen filter threshold. Graphs show that for non-canonical oriented CSSMs, the application of a ΔGopen improves accuracy and negative F1-score values as better scores are obtained when sites with higher ΔGopen values are removed. The peak in the accuracy curve and the fact that the positive F1-score reaches a plateau around ΔGopen = 10, indicates this is an optimal cutoff value. For the canonical-oriented CSSMs, accuracy and positive F1-score metrics reach a plateau around ΔGopen ≥ 23 whereas the negative F1-score curve slightly decreases from ΔGopen ≥ 18. However, the decrease is small compared to the changes in the positive F1-score chart, suggesting that ΔGopen filtering has limited relevance for these models.