Skip to main content
Fig. 5 | Algorithms for Molecular Biology

Fig. 5

From: DeepGRP: engineering a software tool for predicting genomic repetitive elements using Recurrent Neural Networks with attention

Fig. 5

\(MCC _{2}\) for DeepGRP and dna-brnn for all chromosomes of the human genome assembly hg19. For both tools five independently trained models were used. dna-brnn was trained with the same hyperparameter as DeepGRP for 50 epochs. All repeat classes where predicted with a single model, but the \(MCC _{2}\)-values where calculated in an one-vs-rest scheme, e.g. HSAT2,3 against not-HSAT2,3. The models used for this evaluation are the same as for the other evaluations, i.e. trained on hg19/chr11

Back to article page