Description of the methodology used

About this website

On this website, you can explore which amino acid residues in proteins that are predicted to be early folding, this in relation to the sequence fragment it occurs in, and the final secondary structure this fragment adopts in the protein (when folded). In addition, we provide information about why the machine learning method used for the prediction has classified this residue as 'early folding'.

Sequence based predictions

The DynaMine backbone and sidechain dynamics and conformational propensities are described in:

The DynaMine-based predictions serve as input features for the pEFoldMine early folding predictions, which are described in:

With these predictions we try to capture the 'emergent' properties of the proteins, so the inherent biophysical propensities encoded in the sequence, rather than the behavior of a final folded state. This relevant as proteins are dynamic even when folded, and might not fold at all (as with intrinsically disordered proteins).