In-silico prediction of disorder content using hybrid sequence representation

BMC Bioinformatics

Table 2 List of input information sources used by the disorder predictors considered in this work.

Prediction method	Method type	Inputs						Data sources for the training/benchmark dataset(s)	Reference
		AA sequence	PSI-BLAST	Secondary structure prediction	Solvent accessibility prediction	B-factor prediction	Other
DISOPRED2	Machine learning	X	X	X				PDB x-ray structures	[22]
IUPred	Relative propensity	X					Energy profile	PDB x-ray structures + curated chains	[17]
PROFbval	Machine learning	X	X	X	X			PDB x-ray structures	[29]
NORSnet	Machine learning	X	X	X	X	X	Predicted protein-protein interfaces, predicted domains	DisProt + PDB x-ray structures	[33]
Ucon	Relative propensity	X					Predicted residue contacts	DisProt + PDB x-ray structures	[19]
DISOclust	Predicted 3D structure	X					3D models	CASP7 + DisProt	[41]
MD	Meta approach	X	X	X	X	X	Predicted disorder	DisProt + PDB x-ray structures	[38]
PONDR-FIT	Meta approach						Predicted disorder	DisProt + PDB x-ray structures	[40]
MFDp	Meta approach	X	X	X	X	X	Predicted disorder	DisProt + PDB x-ray structures	[39]

ISSN: 1471-2105