Prediction of contact maps with neural networks and correlated mutations.

Contact maps of proteins are predicted with neural network-based methods, using as input codings of increasing complexity including evolutionary information, sequence conservation, correlated mutations and predicted secondary structures. Neural networks are trained on a data set comprising the contact maps of 173 non-homologous proteins as computed from their well resolved three-dimensional structures. Proteins are selected from the Protein Data Bank database provided that they align with at least 15 similar sequences in the corresponding families. The predictors are trained to learn the association rules between the covalent structure of each protein and its contact map with a standard back propagation algorithm and tested on the same protein set with a cross-validation procedure. Our results indicate that the method can assign protein contacts with an average accuracy of 0.21 and with an improvement over a random predictor of a factor >6, which is higher than that previously obtained with methods only based either on neural networks or on correlated mutations. Furthermore, filtering the network outputs with a procedure based on the residue coordination numbers, the accuracy of predictions increases up to 0.25 for all the proteins, with an 8-fold deviation from a random predictor. These scores are the highest reported so far for predicting protein contact maps.

Progress in predicting inter-residue contacts of proteins with neural networks and correlated mutations.

This article presents recent progress in predicting inter-residue contacts of proteins with a neural network-based method. Improvement over the results obtained at the previous CASP3 competition is attained by using as input to the network a complex code, which includes evolutionary information, sequence conservation, correlated mutations, and predicted secondary structures. The predictor was trained and cross-validated on a data set comprising the contact maps of 173 non-homologous proteins as computed from their well-resolved three-dimensional structures. The method could assign protein contacts with an average accuracy of 0.21 and with an improvement over a random predictor of a factor greater than 6, which is higher than that previously obtained with methods only based either on neural networks or on correlated mutations. Although far from being ideal, these scores are the highest reported so far for predicting protein contact maps. On 29 targets automatically predicted by the server (CORNET) the average accuracy is 0.14. The predictor is poorly performing on all alpha proteins, not represented in the training set. On all beta and mixed proteins (22 targets) the average accuracy is 0.16. This set comprises proteins of different complexity and different chain length, suggesting that the predictor is capable of generalization over a broad number of features.

Effective use of sequence correlation and conservation in fold recognition.

Protein families are a rich source of information; sequence conservation and sequence correlation are two of the main properties that can be derived from the analysis of multiple sequence alignments. Sequence conservation is related to the direct evolutionary pressure to retain the chemical characteristics of some positions in order to maintain a given function. Sequence correlation is attributed to the small sequence adjustments needed to maintain protein stability against constant mutational drift. Here, we showed that sequence conservation and correlation were each frequently informative enough to detect incorrectly folded proteins. Furthermore, combining conservation, correlation, and polarity, we achieved an almost perfect discrimination between native and incorrectly folded proteins. Thus, we made use of this information for threading by evaluating the models suggested by a threading method according to the degree of proximity of the corresponding correlated, conserved, and apolar residues. The results showed that the fold recognition capacity of a given threading approach could be improved almost fourfold by selecting the alignments that score best under the three different sequence-based approaches.

Structural model for family 32 of glycosyl-hydrolase enzymes.

A structural model is presented for family 32 of the glycosyl-hydrolase enzymes based on the beta-propeller fold. The model is derived from the common prediction of two different threading methods, TOPITS and THREADER. In addition, we used a correlated mutation analysis and prediction of active-site residues to corroborate the proposed model. Physical techniques (circular dichroism and differential scanning calorimetry) confirmed two aspects of the prediction, the proposed all-beta fold and the multi-domain structure. The most reliable three-dimensional model was obtained using the structure of neuraminidase (1nscA) as template. The analysis of the position of the active site residues in this model is compatible with the catalytic mechanism proposed by Reddy and Maley (J. Biol. Chem. 271:13953-13958, 1996), which includes three conserved residues, Asp, Glu, and Cys. Based on this analysis, we propose the participation of one more conserved residue (Asp 162) in the catalytic mechanism. The model will facilitate further studies of the physical and biochemical characteristics of family 32 of the glycosyl-hydrolases.

Structural model of Dex protein from Penicillium minioluteum and its implications in the mechanism of catalysis.

The DEX gene encodes an extracellular dextranase (EC 3.2.1.11); this enzyme hydrolyzes the alpha(1,6) glucosidic bond contained in dextran to release small isomaltosaccharides. Sequence analysis has revealed only one homologous sequence, CB-8 protein, from Arthrobacter sp., with 30% sequence identity. The secondary structure prediction for Dex was corroborated by circular dichroism measurements. To explore the possibility that Dex protein might adopt a fold similar to any known structure, we conducted a threading search of a three-dimensional structure database. This search revealed that the Dex sequence is compatible with the galactose oxidase/methanol dehydrogenase/sialidase fold. A structural model of Dex based on these results is physically and biologically plausible and leads to testable predictions, including the prediction that Asp246 and Glu299 might be catalytic residues. Also, according to this model the Dex enzyme has a mechanism of hydrolysis with net inversion of anomeric configuration.

Improving contact predictions by the combination of correlated mutations and other sources of sequence information.

We have previously developed a method for predicting interresidue contacts using information about correlated mutations in multiple sequence alignments. The predictions generated with this method were clearly better than random but not enough for their use in de novo protein folding experiments. We assess the possibility of improving contact predictions combining information from the following variables: correlated mutations, sequence conservation, sequence separation along the chain, alignment stability, family size, residue-specific contact occupancy and formation of contact networks. The application of a protocol for combining these independent variables leads to contact predictions that are on average two times better than those obtained initially with correlated mutations. Correlated mutations can be effectively combined with other types of information derived from multiple sequence alignments. Among the different variables tried, sequence conservation and contact density are particularly relevant for the combination with correlated mutations.