Predicting turns in proteins with a unified model

Abstract

Motivation: Turns are a critical element of the structure of a protein; turns play a crucial role in loops, folds, and interactions. Current prediction methods are well developed for the prediction of individual turn types, including α-turn, β-turn, and γ-turn, etc. However, for further protein structure and function prediction it is necessary to develop a uniform model that can accurately predict all types of turns simultaneously.

Results: In this study, we present a novel approach, TurnP, which offers the ability to investigate all the turns in a protein based on a unified model. The main characteristics of TurnP are: (i) using newly exploited features of structural evolution information (secondary structure and shape string of protein) based on structure homologies, (ii) considering all types of turns in a unified model, and (iii) practical capability of accurate prediction of all turns simultaneously for a query. TurnP utilizes predicted secondary structures and predicted shape strings, both of which have greater accuracy, based on innovative technologies which were both developed by our group. Then, sequence and structural evolution features, which are profile of sequence, profile of secondary structures and profile of shape strings are generated by sequence and structure alignment. When TurnP was validated on a non-redundant dataset (4,107 entries) by five-fold cross-validation, we achieved an accuracy of 88.8% and a sensitivity of 71.8%, which exceeded the most state-of-the-art predictors of certain type of turn. Newly determined sequences, the EVA and CASP9 datasets were used as independent tests and the results we achieved were outstanding for turn predictions and confirmed the good performance of TurnP for practical applications.

Figure 1. The flowchart of TurnP.

Figure 2. Diagram of profile.

We used 3 kinds of profiles in this study: PSSM, SPSSM and Shape string profile. They have 20, 3 and 8 specific elements for each amino acid respectively obtained by sequence alignment and sequence-structure alignment. Each square represents a element that is normalized frequency. The red squares represent large values near ‘1′ and blue ones represent small values near ‘0′; and the deeper the color of the square is, the closer the value to extreme values.

Figure 3. Comparison chart between Train_0925 5-fold validation and evaluation result of Test_1025, EVAset1 and CASP9.

Figure 4. An example of prediction of TurnP, 1B9W_A. in Figure 4(a), the red curve represents turn residues which have been marked as turn, while the other grey curve represents Random Coil.

The marine spiral represents Helix, and the green arrow represents Sheet. In the Figure 4(b), all turns in 1B9W_A were shown as blocks to make them more clearly to see. The line represents the sequence, the red blocks represent turn residues which have been predicted correctly, while the grey ones represent turn residues that have not been predicted by TurnP. Position number is counted every 10 residues for convenience, and the position of relevent turns were signed in (a). The illustration of the 3D structure was drawn by PyMOL .