Protein tertiary structure prediction

The earliest neural network attempt for protein tertiary structure prediction was done by Bohr et al. (1990). They predicted the binary distance constraints for the C-a atoms in protein backbone using a standard three-layer back-propagation network and BIN20 sequence encoding method for 61-amino acid windows. The output layer had 33 units, three for the 3-state secondary structure prediction, and the remaining to measure the distance constraints between the central amino acid and the 30 preceding residues. 

Milik et al. (1995) developed a neural network system to evaluate side-chain packing in protein structures. Instead of using protein sequence as input to the neural network as in most other studies, protein structure represented by a side-chain-side-chain contact map was used. Contact maps of globular protein structures in the Protein Data Bank were scanned using 7x7 windows, and converted to 49 binary numbers for the neural network input. One output unit was used to determine whether the contact pattern is popular in 

---

S. Sun, Reduced representation approach to protein tertiary structure prediction statistical potential and simulated annealing, J. Theor. Biol. 172 (1995), 13-32. 

Le-Grand SM, Merz KM Jr (1994) The protein folding problem and tertiary structure prediction the genetic algorithm and protein tertiary structure prediction. Birkhauser, Boston, p 109... 

Table 10.1 summarizes neural network applications for protein structure prediction. Protein secondary structure prediction is often used as the first step toward understanding and predicting tertiary structure because secondary structure elements constitute the building blocks of the folding units. An estimated 90% or so of the residues in most proteins are involved in three classes of secondary structures, the a-helices, p-strands or reverse turns. Related to the secondary structure prediction are also the prediction of solvent accessibility, transmembrane helices, and secondary structure content (10.2). Neural networks have also been applied to protein tertiary structure prediction, such as the prediction of the backbones or side-chain packing, and to structural class prediction (10.3). 

Tan, C.-W., Jones, D. Using neural networks and evolutionary information in decoy discrimination for protein tertiary structure prediction. BMC Bioinformatics 2008, 9, 94. 

Structure based approaches to function prediction is the ability to predict protein structure from sequence. Thus, in this review, we describe the state of the art of contemporary approaches to protein tertiary structure prediction, and focus in particular on reduced models. 

McAllister, S. R., 8c Floudas, C. A. (2010). An improved hybrid global optimization method for protein tertiary structure prediction. Computational Optimization and Applications, 45, 377. 

Schulze-Kremer, S. (1992) Genetic Algorithms for Protein Tertiary Structure Prediction. In R. Manner and B. Manderick (Eds.), Parallel Problem Solving from Nature 2, pp. 391-400. North Holland, Amsterdam. 

DM Standley, JR Gunn, RA Friesner, AE McDermott. Tertiary structure prediction of mixed alpha/beta proteins via energy minimization. Proteins 33 240-252, 1998. 

A Caflisch, M Karplus. Molecular dynamics studies of protein and peptide folding and unfolding. In K Merz Jr, S Le Grand, eds. The Protein Eoldmg Problem and Tertiary Structure Prediction. Boston Birkhauser, 1994, pp 193-230. 

These predictive methods are very useful in many contexts for example, in the design of novel polypeptides for the identification of possible antigenic epitopes, in the analysis of common motifs in sequences that direct proteins into specific organelles (for instance, mitochondria), and to provide starting models for tertiary structure predictions. 

ExPASy Proteomics tools (http //expasy.org/tools/), tools and online programs for protein identification and characterization, similarity searches, pattern and profile searches, posttranslational modification prediction, topology prediction, primary structure analysis, or secondary and tertiary structure prediction. 

T. Herges and W. Wenzel. An All-Atom Force Field for Tertiary Structure Prediction of Helical Proteins. Biophys. J., 87(5) 3100-3109, 2004. 

Visualizing Folded Protein Structures Primary Structure Determines Tertiary Structure Secondary Valence Forces Are the Glue That Holds Polypeptide Chains Together Domains Are Functional Units of Tertiary Structure Predicting Protein Tertiary Structure Quaternary Structure Involves the Interaction of Two or More Proteins... 

We began the discussion of globular protein tertiary structure by pointing out that the secondary and tertiary structure is determined by the primary structure and that this is probably a reflection of the fact that the native folded conformation is the most stable structure that can be formed. If this is so, then it should be possible to predict a protein s structure from its primary sequence. At this juncture, such predictions remain an elusive goal. However, most proteins are made of a limited number of domains, which tend to reappear in many different proteins. Since this is the case, it may be possible to predict the structures of many proteins in the future by using the information accumulated from x-ray diffraction studies of related proteins. 

M.J. Sippl, S. Weitckus, and H. Flockner. In search of protein folds. In Merz and LeGrand, eds., The Protein Folding Problem and Tertiary Structure Prediction, 353-407. Birkhaeuser, 1994. 

It has been observed that the use of protein tertiary structural class improved the accuracy for a 2-state secondary structure prediction (Kneller et al., 1990). A modular network architecture was proposed using separate networks (i.e., a- or P-type network) for classification of different secondary structures (Sasagawa Tajima, 1993). Recently, Chandonia Karplus (1995) trained a pair of neural networks to predict the protein secondary structure and the structural class respectively. Using predicted class information, the secondary structure prediction network realized a small increase in accuracy. 

The basic information of protein tertiary structural class can help improve the accuracy of secondary structure prediction (Kneller et al., 1990). Chandonia and Karplus (1995) showed that information obtained from a secondary structure prediction algorithm can be used to improve the accuracy for structural class prediction. The input layer had 26 units coded for the amino acid composition of the protein (20 units), the sequence length (1 unit), and characteristics of the protein (5 units) predicted by a separate secondary structure neural network. The secondary structure characteristics include the predicted percent helix and sheet, the percentage of strong helix and sheet predictions, and the predicted number of alterations between helix and sheet. The output layer had four units, one for each of the tertiary super classes (all-a, all-p, a/p, and other). The inclusion of the single-sequence secondary structure predictions improved the class prediction for non-homologous proteins significantly by more than 11%, from a predictive accuracy of 62.3% to 73.9%. 

Yi TM, Lander ES. Protein secondary structure prediction using nearest neighbor methods. J. Mol. Biol. 1993 232 1117-1129. de Dios AC, Pearson JG, Oldfield E. Secondary and tertiary structural effects on protein NMR chemical shifts an ab initio approach. Science 1993 260 1491-1496. 

In tertiary structure prediction, there are three distinct scenarios. The sequence to be modeled may be closely related to a protein whose structure has been determined experimentally. Here, there is the prospect of developing a relatively accurate structural model through comparative modeling. This prospect drops markedly with the strength of the relationship between the sequence to be modeled and known structures. As this relationship weakens, one moves from the realm of comparative modeling to an approach known as fold recognition. Here, one attempts to utilize... 

This section gives an overview of secondary structure and tertiary structure prediction methods for proteins. Methods for (secondary) structure prediction of other biomolecules, such as RNA are not discussed here. 

Ortiz, A. R., A. Kolinski, and J. Skolnick, Tertiary structure prediction of the KIX domain of CBP using Monte Carlo simulations driven by restraints derived from multiple sequence alignments. Proteins, 1998. 30(3) p. 287-94. 

---