Exact(2)
These models perform poor with MCC 0.27, when evaluated on Pyrimidine class of molecules.
It is a well-known fact that machine learning techniques, particularly SVM-based models perform poor especially when positive and negative dataset is unbalanced.
Similar(6)
Similarly, Rfam-based covariance models performed poor to classify the novel/non-similar sequences whereas comparatively structural information based graph-properties of RNAcon method performed well because graph-properties based features provide both local as well as global structural features of a particular class.
However, the frequency-based model performed poor in this dataset as well [Additional file 7: Table S6].
Figure 2 shows an example of a short cyclic peptide (10 residues) where PEPstrMOD approached close to the native structure while the ab initio model performed poor.
For a couple of countries (Italy and the Netherlands), however, the autoregressive model performed poorer than the base non-linear model.
Thus, they generally perform poor performance on the imbalanced datasets.
In almost all cases, these tests indicated that the Type B model performed best followed by the Type C model, with the Type A model invariably performing poorest (Table 8).
Related(2)
Write better and faster with AI suggestions while staying true to your unique style.
Since I tried Ludwig back in 2017, I have been constantly using it in both editing and translation. Ever since, I suggest it to my translators at ProSciEditing.

Justyna Jupowicz-Kozak
CEO of Professional Science Editing for Scientists @ prosciediting.com