+\subsection{Disorder predictors provided by JABAWS 2.0}
+For full details of each predictor and the results that Jalview can display,
+please consult
+\href{http://www.jalview.org/help/html/webServices/proteinDisorder.html}{Jalview's
+protein disorder service documentation}. Short descriptions of the methods provided in JABAWS 2.0 are given below:
+
+\subsubsection{DisEMBL}
+\href{http://dis.embl.de/}{DisEMBL (Linding et al., 2003)} is a set of machine-learning based predictors trained to
+recognise disorder-related annotation found on PDB structures.
+
+\textbf{COILS} Predicts
+loops/coils according to DSSP
+definitions\footnote{DSSP Classifications of secondary structure are: $\alpha$-helix (H), 310-helix (G), $\beta$-strand (E)
+are ordered, and all other states ($\beta$-bridge (B), $\beta$-turn (T), bend (S),
+$\pi$-helix (I), and coil (C)) considered loops or coils.}. Features mark range(s) of
+residues predicted as loops/coils, and annotation row gives raw value
+for each residue. Value over 0.516 indicates loop/coil.
+
+\textbf{HOTLOOPS} constitute a refined subset of \textbf{COILS}, namely those loops with
+a high degree of mobility as determined from C$\alpha$ temperature factors (B
+factors). It follows that highly dynamic loops should be considered
+protein disorder. Features mark range(s) of residues predicted to
+be hot loops and annotation row gives raw value for each
+residue. Values over 0.6 indicates hot loop.
+
+\textbf{REMARK465} ``Missing
+coordinates in X-ray structure as defined by remark465 entries in PDB.
+Nonassigned electron densities most often reflect intrinsic disorder,
+and have been used early on in disorder prediction.'' Features give
+range(s) of residues predicted as disordered, and annotation rows gives
+raw value for each residue. Values over 0.1204 indicates disorder.
+
+\subsubsection{RONN {\sl a.k.a.} Regional Order Neural Network}
+\href{http://www.strubi.ox.ac.uk/RONN}{RONN} employs an approach
+known as the `bio-basis' method to predict regions of disorder in
+sequences based on their local similarity with a gold-standard set of
+disordered protein sequences. It yields a set of disorder prediction
+scores, which are shown as sequence annotation below the alignment.
+
+\textbf{JRonn}\footnote{JRonn denotes the score for this server because JABAWS
+runs a Java port of RONN developed by Peter Troshin and distributed as
+part of \href{http://www.biojava.org/}{Biojava 3}} Annotation Row gives RONN score for each residue in
+the sequence. Scores above 0.5 identify regions of the protein likely
+to be disordered.
+
+\subsubsection{IUPred}
+\href{http://iupred.enzim.hu/Help.php}{IUPred} employs
+an empirical model to estimate likely regions of disorder. There are
+three different prediction types offered, each using different
+parameters optimized for slightly different applications. It provides
+raw scores based on two models for predicting regions of `long
+disorder' and `short disorder'. A third predictor identifies regions
+likely to form structured domains.
+
+\textbf{Long disorder} Annotation rows predict
+context-independent global disorder that encompasses at least 30
+consecutive residues of predicted disorder. A 100 residue
+window is used for calculation. Values above 0.5 indicates the residue is
+intrinsically disordered.
+
+\textbf{Short disorder} Annotation rows predict for short, (and
+probably) context-dependent, disordered regions, such as missing
+residues in the X-ray structure of an otherwise globular protein.
+Employs a 25 residue window for calculation, and includes adjustment
+parameter for chain termini which favors disorder prediction at the
+ends. Values above 0.5 indicate short-range disorder.
+
+\textbf{Structured domains} are marked with sequence Features. These highlight
+likely globular domains useful for structure genomics investigation. Post-analysis of disordered region profile to find continuous regions
+confidently predicted to be ordered. Neighbouring regions close to
+each other are merged, while regions shorter than the minimal domain
+size of at least 30 residues are ignored.
+
+\subsubsection{GLOBPLOT}
+\href{http://globplot.embl.de/}{GLOBPLOT} defines regions of
+globularity or natively unstructured regions based on a running sum of
+the propensity of residues to be structured or unstructured. The
+propensity is calculated based on the probability of each amino acid
+being observed within well defined regions of secondary structure or
+within regions of random coil. The initial signal is smoothed with a
+Savitzky-Golay filter, and its first order derivative
+computed. Residues for which the first order derivative is positive
+are designated as natively unstructured, whereas those with negative
+values are structured.
+
+{\bf Disordered region} sequence features are created marking mark range(s) of residues with positive first order derivatives, and
+\textbf{Globular Domain} features mark long stretches of order. \textbf{Dydx} annotation rows gives the first order derivative of smoothed score. Values above 0 indicates
+residue is disordered.
+
+\textbf{Smoothed Score and Raw Score} annotation rows give the smoothed and raw scores used to create the differential signal that
+indicates the presence of unstructured regions. These are hidden
+by default, but can be shown by right-clicking on the alignment
+annotation panel and selecting \textbf{Show hidden annotation}.
+
+\exercise{Protein Disorder Prediction}{
+\label{protdispredex}
+
+\exstep{Open the alignment at
+\url{http://www.jalview.org/tutorial/interleukin7.fa}. }
+
+\exstep{Run the DisEMBL disorder predictor {\slvia} the {\slWeb Services
+$\Rightarrow$ Disorder Prediction } submenu.}
+
+\exstep{Use {\sl Sequence ID $\Rightarrow$ Structure $\Rightarrow$ Discover PDB
+IDs} to retrieve all the PDB structures for the sequences.}
+
+\exstep{Open and align
+the structures for all sequences.
+
+{\sl Hint: see \ref{viewAllStructures} to see how to do this.}}
+
+\exstep{Compare the disorder predictions to the structure data by mapping any
+available temperature factors to the alignment {\sl via} the {\sl Sequence ID
+Popup $\Rightarrow$ Selection $\Rightarrow$ Add reference annotation} option.}
+
+\exstep{Apply the IUPred disorder prediction method}
+\exstep{Use the {\sl Per
+sequence option} in the {\sl Colour $\Rightarrow$ By annotation \ldots} dialog to shade
+the sequences by the long and short disorder predictors.
+Do the two methods agree with the structure ?}}
+